diff --git a/docs/source/distributions/k8s/all-manifests.yaml b/docs/source/distributions/k8s/all-manifests.yaml new file mode 100644 index 000000000..7bee389d1 --- /dev/null +++ b/docs/source/distributions/k8s/all-manifests.yaml @@ -0,0 +1,6284 @@ +--- +# Source: kube-prometheus-stack/charts/grafana/templates/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +automountServiceAccountToken: true +metadata: + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus +--- +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +automountServiceAccountToken: true +metadata: + labels: + helm.sh/chart: kube-state-metrics-6.1.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "2.16.0" + release: kube-prometheus-stack-1754164871 + name: kube-prometheus-stack-1754164871-kube-state-metrics + namespace: prometheus +--- +# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + name: kube-prometheus-stack-1754164871-prometheus-node-exporter + namespace: prometheus + labels: + helm.sh/chart: prometheus-node-exporter-4.47.3 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "1.9.1" + release: kube-prometheus-stack-1754164871 +automountServiceAccountToken: false +--- +# Source: kube-prometheus-stack/templates/alertmanager/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + name: kube-prometheus-stack-1754-alertmanager + namespace: prometheus + labels: + app: kube-prometheus-stack-alertmanager + app.kubernetes.io/name: kube-prometheus-stack-alertmanager + app.kubernetes.io/component: alertmanager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +automountServiceAccountToken: true +--- +# Source: kube-prometheus-stack/templates/prometheus-operator/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + name: kube-prometheus-stack-1754-operator + namespace: prometheus + labels: + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + app: kube-prometheus-stack-operator + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/component: prometheus-operator +automountServiceAccountToken: true +--- +# Source: kube-prometheus-stack/templates/prometheus/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + name: kube-prometheus-stack-1754-prometheus + namespace: prometheus + labels: + app: kube-prometheus-stack-prometheus + app.kubernetes.io/name: kube-prometheus-stack-prometheus + app.kubernetes.io/component: prometheus + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +automountServiceAccountToken: true +--- +# Source: kube-prometheus-stack/charts/grafana/templates/secret.yaml +apiVersion: v1 +kind: Secret +metadata: + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" +type: Opaque +data: + + admin-user: "YWRtaW4=" + admin-password: "cHJvbS1vcGVyYXRvcg==" + ldap-toml: "" +--- +# Source: kube-prometheus-stack/templates/alertmanager/secret.yaml +apiVersion: v1 +kind: Secret +metadata: + name: alertmanager-kube-prometheus-stack-1754-alertmanager + namespace: prometheus + labels: + app: kube-prometheus-stack-alertmanager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + alertmanager.yaml: "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" +--- +# Source: kube-prometheus-stack/charts/grafana/templates/configmap-dashboard-provider.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" + name: kube-prometheus-stack-1754164871-grafana-config-dashboards + namespace: prometheus +data: + provider.yaml: |- + apiVersion: 1 + providers: + - name: 'sidecarProvider' + orgId: 1 + folder: '' + folderUid: '' + type: file + disableDeletion: false + allowUiUpdates: false + updateIntervalSeconds: 30 + options: + foldersFromFilesStructure: false + path: /tmp/dashboards +--- +# Source: kube-prometheus-stack/charts/grafana/templates/configmap.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" +data: + + grafana.ini: | + [analytics] + check_for_updates = true + [grafana_net] + url = https://grafana.net + [log] + mode = console + [paths] + data = /var/lib/grafana/ + logs = /var/log/grafana + plugins = /var/lib/grafana/plugins + provisioning = /etc/grafana/provisioning + [server] + domain = '' +--- +# Source: kube-prometheus-stack/templates/grafana/configmaps-datasources.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: kube-prometheus-stack-1754-grafana-datasource + namespace: prometheus + labels: + grafana_datasource: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + datasource.yaml: |- + apiVersion: 1 + datasources: + - name: "Prometheus" + type: prometheus + uid: prometheus + url: http://kube-prometheus-stack-1754-prometheus.prometheus:9090/ + access: proxy + isDefault: true + jsonData: + httpMethod: POST + timeInterval: 30s + - name: "Alertmanager" + type: alertmanager + uid: alertmanager + url: http://kube-prometheus-stack-1754-alertmanager.prometheus:9093/ + access: proxy + jsonData: + handleGrafanaManagedAlerts: false + implementation: prometheus +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/alertmanager-overview.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-alertmanager-overview + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + alertmanager-overview.json: |- + {"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"Alerts","type":"row"},{"datasource":{"type":"prometheus","uid":"$datasource"},"description":"current set of alerts stored in the Alertmanager","fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"none"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(alertmanager_alerts{namespace=~\"$namespace\",service=~\"$service\"}) by (namespace,service,instance)","intervalFactor":2,"legendFormat":"{{instance}}"}],"title":"Alerts","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"$datasource"},"description":"rate of successful and invalid alerts received by the Alertmanager","fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(alertmanager_alerts_received_total{namespace=~\"$namespace\",service=~\"$service\"}[$__rate_interval])) by (namespace,service,instance)","intervalFactor":2,"legendFormat":"{{instance}} Received"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(alertmanager_alerts_invalid_total{namespace=~\"$namespace\",service=~\"$service\"}[$__rate_interval])) by (namespace,service,instance)","intervalFactor":2,"legendFormat":"{{instance}} Invalid"}],"title":"Alerts receive rate","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"panels":[],"title":"Notifications","type":"row"},{"datasource":{"type":"prometheus","uid":"$datasource"},"description":"rate of successful and invalid notifications sent by the Alertmanager","fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":9},"id":5,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","repeat":"integration","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(alertmanager_notifications_total{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (integration,namespace,service,instance)","intervalFactor":2,"legendFormat":"{{instance}} Total"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(alertmanager_notifications_failed_total{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (integration,namespace,service,instance)","intervalFactor":2,"legendFormat":"{{instance}} Failed"}],"title":"$integration: Notifications Send Rate","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"$datasource"},"description":"latency of notifications sent by the Alertmanager","fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"s"}},"gridPos":{"h":7,"w":12,"x":12,"y":9},"id":6,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","repeat":"integration","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (le,namespace,service,instance)\n)\n","intervalFactor":2,"legendFormat":"{{instance}} 99th Percentile"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.50,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (le,namespace,service,instance)\n)\n","intervalFactor":2,"legendFormat":"{{instance}} Median"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(alertmanager_notification_latency_seconds_sum{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (namespace,service,instance)\n/\nsum(rate(alertmanager_notification_latency_seconds_count{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (namespace,service,instance)\n","intervalFactor":2,"legendFormat":"{{instance}} Average"}],"title":"$integration: Notification Duration","type":"timeseries"}],"schemaVersion":39,"tags":["alertmanager-mixin"],"templating":{"list":[{"current":{"selected":false,"text":"Prometheus","value":"Prometheus"},"hide":0,"label":"Data Source","name":"datasource","query":"prometheus","type":"datasource"},{"current":{"selected":false,"text":"","value":""},"datasource":{"type":"prometheus","uid":"${datasource}"},"includeAll":false,"label":"namespace","name":"namespace","query":"label_values(alertmanager_alerts, namespace)","refresh":2,"sort":1,"type":"query"},{"current":{"selected":false,"text":"","value":""},"datasource":{"type":"prometheus","uid":"${datasource}"},"includeAll":false,"label":"service","name":"service","query":"label_values(alertmanager_alerts, service)","refresh":2,"sort":1,"type":"query"},{"current":{"selected":false,"text":"$__all","value":"$__all"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"includeAll":true,"name":"integration","query":"label_values(alertmanager_notifications_total{integration=~\".*\"}, integration)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["30s"]},"timezone": "utc","title":"Alertmanager / Overview","uid":"alertmanager-overview"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/apiserver.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-apiserver + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + apiserver.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.","gridPos":{"h":2,"w":24,"x":0,"y":0},"id":1,"options":{"content":"The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only."},"pluginVersion":"v11.4.0","title":"Notice","type":"text"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many percent of requests (both read and write) in 30 days have been answered successfully and fast enough?","fieldConfig":{"defaults":{"decimals":3,"unit":"percentunit"}},"gridPos":{"h":7,"w":8,"x":0,"y":2},"id":2,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"}"}],"title":"Availability (30d) > 99.000%","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How much error budget is left looking at our 0.990% availability guarantees?","fieldConfig":{"defaults":{"custom":{"fillOpacity":100},"decimals":3,"unit":"percentunit"}},"gridPos":{"h":7,"w":16,"x":8,"y":2},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"100 * (apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"} - 0.990000)","legendFormat":"errorbudget"}],"title":"ErrorBudget (30d) > 99.000%","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many percent of read requests (LIST,GET) in 30 days have been answered successfully and fast enough?","fieldConfig":{"defaults":{"decimals":3,"unit":"percentunit"}},"gridPos":{"h":7,"w":6,"x":0,"y":9},"id":4,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"apiserver_request:availability30d{verb=\"read\", cluster=\"$cluster\"}"}],"title":"Read Availability (30d)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many read requests (LIST,GET) per second do the apiservers get by code?","fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"stacking":{"mode":"normal"}},"unit":"reqps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/2../i"},"properties":[{"id":"color","value":"#56A64B"}]},{"matcher":{"id":"byRegexp","options":"/3../i"},"properties":[{"id":"color","value":"#F2CC0C"}]},{"matcher":{"id":"byRegexp","options":"/4../i"},"properties":[{"id":"color","value":"#3274D9"}]},{"matcher":{"id":"byRegexp","options":"/5../i"},"properties":[{"id":"color","value":"#E02F44"}]}]},"gridPos":{"h":7,"w":6,"x":6,"y":9},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})","legendFormat":"{{ code }}"}],"title":"Read SLI - Requests","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many percent of read requests (LIST,GET) per second are returned with errors (5xx)?","fieldConfig":{"defaults":{"min":0,"unit":"percentunit"}},"gridPos":{"h":7,"w":6,"x":12,"y":9},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})","legendFormat":"{{ resource }}"}],"title":"Read SLI - Errors","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many seconds is the 99th percentile for reading (LIST|GET) a given resource?","fieldConfig":{"defaults":{"unit":"s"}},"gridPos":{"h":7,"w":6,"x":18,"y":9},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile{verb=\"read\", cluster=\"$cluster\"}","legendFormat":"{{ resource }}"}],"title":"Read SLI - Duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many percent of write requests (POST|PUT|PATCH|DELETE) in 30 days have been answered successfully and fast enough?","fieldConfig":{"defaults":{"decimals":3,"unit":"percentunit"}},"gridPos":{"h":7,"w":6,"x":0,"y":16},"id":8,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"apiserver_request:availability30d{verb=\"write\", cluster=\"$cluster\"}"}],"title":"Write Availability (30d)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many write requests (POST|PUT|PATCH|DELETE) per second do the apiservers get by code?","fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"stacking":{"mode":"normal"}},"unit":"reqps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/2../i"},"properties":[{"id":"color","value":"#56A64B"}]},{"matcher":{"id":"byRegexp","options":"/3../i"},"properties":[{"id":"color","value":"#F2CC0C"}]},{"matcher":{"id":"byRegexp","options":"/4../i"},"properties":[{"id":"color","value":"#3274D9"}]},{"matcher":{"id":"byRegexp","options":"/5../i"},"properties":[{"id":"color","value":"#E02F44"}]}]},"gridPos":{"h":7,"w":6,"x":6,"y":16},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})","legendFormat":"{{ code }}"}],"title":"Write SLI - Requests","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many percent of write requests (POST|PUT|PATCH|DELETE) per second are returned with errors (5xx)?","fieldConfig":{"defaults":{"min":0,"unit":"percentunit"}},"gridPos":{"h":7,"w":6,"x":12,"y":16},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})","legendFormat":"{{ resource }}"}],"title":"Write SLI - Errors","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many seconds is the 99th percentile for writing (POST|PUT|PATCH|DELETE) a given resource?","fieldConfig":{"defaults":{"unit":"s"}},"gridPos":{"h":7,"w":6,"x":18,"y":16},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$cluster\"}","legendFormat":"{{ resource }}"}],"title":"Write SLI - Duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"min":0,"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":23},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":false},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)","legendFormat":"{{instance}} {{name}}"}],"title":"Work Queue Add Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":12,"y":23},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":false},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)","legendFormat":"{{instance}} {{name}}"}],"title":"Work Queue Depth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"min":0,"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":30},"id":14,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name, le))","legendFormat":"{{instance}} {{name}}"}],"title":"Work Queue Latency","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":37},"id":15,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"process_resident_memory_bytes{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}","legendFormat":"{{instance}}"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"min":0,"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":37},"id":16,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])","legendFormat":"{{instance}}"}],"title":"CPU usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":37},"id":17,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"go_goroutines{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}","legendFormat":"{{instance}}"}],"title":"Goroutines","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"apiserver\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"name":"instance","query":"label_values(up{job=\"apiserver\", cluster=\"$cluster\"}, instance)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / API server","uid":"09ec8aa1e996d6ffcd6817bbaff4db1b"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/cluster-total.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-cluster-total + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + cluster-total.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bytes/"},"properties":[{"id":"unit","value":"binBps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill down","url":"/d/8b7a8b326d7a6f1f04244066368c67af/kubernetes-networking-namespace-pods?${datasource:queryparam}&var-cluster=${cluster}&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":9,"w":24,"x":0,"y":9},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg by (namespace) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg by (namespace) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true}],"title":"Current Status","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true,"Time 8":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Time 8":7,"Value #A":9,"Value #B":10,"Value #C":11,"Value #D":12,"Value #E":13,"Value #F":14,"Value #G":15,"Value #H":16,"namespace":8},"renameByName":{"Value #A":"Rx Bytes","Value #B":"Tx Bytes","Value #C":"Rx Bytes (Avg)","Value #D":"Tx Bytes (Avg)","Value #E":"Rx Packets","Value #F":"Tx Packets","Value #G":"Rx Packets Dropped","Value #H":"Tx Packets Dropped","namespace":"Namespace"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg by (namespace) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Average Rate of Bytes Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg by (namespace) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Average Rate of Bytes Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":27},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":27},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":36},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":36},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":45},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":45},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"percentunit"}},"gridPos":{"h":9,"w":12,"x":0,"y":54},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (instance) (\n rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$__rate_interval]) / rate(node_netstat_Tcp_OutSegs{cluster=\"$cluster\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of TCP Retransmits out of all sent segments","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"percentunit"}},"gridPos":{"h":9,"w":12,"x":12,"y":54},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (instance) (\n rate(node_netstat_TcpExt_TCPSynRetrans{cluster=\"$cluster\"}[$__rate_interval]) / rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of TCP SYN Retransmits out of all retransmits","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Networking / Cluster","uid":"ff635a025bcfea7bc3dd4f508990a3e9"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/controller-manager.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-controller-manager + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + controller-manager.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(up{cluster=\"$cluster\", job=\"kube-controller-manager\"})","instant":true}],"title":"Up","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":20,"x":4,"y":0},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(workqueue_adds_total{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)","legendFormat":"{{cluster}} {{instance}} {{name}}"}],"title":"Work Queue Add Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(workqueue_depth{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)","legendFormat":"{{cluster}} {{instance}} {{name}}"}],"title":"Work Queue Depth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name, le))","legendFormat":"{{cluster}} {{instance}} {{name}}"}],"title":"Work Queue Latency","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":8,"x":0,"y":21},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","legendFormat":"2xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","legendFormat":"3xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","legendFormat":"4xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","legendFormat":"5xx"}],"title":"Kube API Request Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":16,"x":8,"y":21},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, le))","legendFormat":"{{verb}}"}],"title":"Post Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":28},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, le))","legendFormat":"{{verb}}"}],"title":"Get Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":35},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":35},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}[$__rate_interval])","legendFormat":"{{instance}}"}],"title":"CPU usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":35},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"go_goroutines{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Goroutines","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-controller-manager\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"instance","name":"instance","query":"label_values(up{cluster=\"$cluster\", job=\"kube-controller-manager\"}, instance)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Controller Manager","uid":"72e0e05bef5099e5f049b05fdc429ed4"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/etcd.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-etcd + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + etcd.json: |- + {"description":"etcd sample Grafana dashboard with Prometheus","panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"gridPos":{"h":7,"w":6,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none","graphMode":"none","reduceOptions":{"calcs":["lastNotNull"]}},"pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(etcd_server_has_leader{job=~\".*etcd.*\", job=\"$cluster\"})","legendFormat":"{{cluster}} - {{namespace}}\n"}],"title":"Up","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"ops"}},"gridPos":{"h":7,"w":10,"x":6,"y":0},"id":2,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(grpc_server_started_total{job=~\".*etcd.*\", job=\"$cluster\",grpc_type=\"unary\"}[$__rate_interval]))","legendFormat":"RPC rate"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(grpc_server_handled_total{job=~\".*etcd.*\", job=\"$cluster\",grpc_type=\"unary\",grpc_code=~\"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded\"}[$__rate_interval]))","legendFormat":"RPC failed rate"}],"title":"RPC rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"}}},"gridPos":{"h":7,"w":8,"x":16,"y":0},"id":3,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(grpc_server_started_total{job=~\".*etcd.*\",job=\"$cluster\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"})","legendFormat":"Watch streams"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(grpc_server_started_total{job=~\".*etcd.*\",job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"})","legendFormat":"Lease streams"}],"title":"Active streams","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":25},"id":4,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"etcd_mvcc_db_total_size_in_bytes{job=~\".*etcd.*\", job=\"$cluster\"}","legendFormat":"{{instance}} DB size"}],"title":"DB size","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"s"}},"gridPos":{"h":7,"w":8,"x":8,"y":25},"id":5,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}} WAL fsync"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}} DB fsync"}],"title":"Disk sync duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":16,"y":25},"id":6,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"process_resident_memory_bytes{job=~\".*etcd.*\", job=\"$cluster\"}","legendFormat":"{{instance}} resident memory"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":0,"y":50},"id":7,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(etcd_network_client_grpc_received_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])","legendFormat":"{{instance}} client traffic in"}],"title":"Client traffic in","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":6,"y":50},"id":8,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(etcd_network_client_grpc_sent_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])","legendFormat":"{{instance}} client traffic out"}],"title":"Client traffic out","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":12,"y":50},"id":9,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(etcd_network_peer_received_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}} peer traffic in"}],"title":"Peer traffic in","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":18,"y":50},"id":10,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(etcd_network_peer_sent_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}} peer traffic out"}],"title":"Peer traffic out","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"}}},"gridPos":{"h":7,"w":8,"x":0,"y":75},"id":11,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"changes(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\", job=\"$cluster\"}[1d])","legendFormat":"{{instance}} total leader elections per day"}],"title":"Raft proposals","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"}}},"gridPos":{"h":7,"w":8,"x":8,"y":75},"id":12,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"changes(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\", job=\"$cluster\"}[1d])","legendFormat":"{{instance}} total leader elections per day"}],"title":"Total leader elections per day","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"s"}},"gridPos":{"h":7,"w":8,"x":16,"y":75},"id":13,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99, sum by (instance, le) (rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])))","legendFormat":"{{instance}} peer round trip time"}],"title":"Peer round trip time","type":"timeseries"}],"refresh":"10s","schemaVersion":36,"tags":["etcd-mixin"],"templating":{"list":[{"label":"Data Source","name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"label":"cluster","name":"cluster","query":"label_values(etcd_server_has_leader{job=~\".*etcd.*\"}, job)","refresh":2,"type":"query","allValue":".*","hide":2}]},"time":{"from":"now-15m","to":"now"},"timezone": "utc","title":"etcd","uid":"c2f4e12cdf69feb95caa41a5a1b423d9"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/grafana-overview.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-grafana-overview + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + grafana-overview.json: |- + {"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","target":{"limit":100,"matchAny":false,"tags":[],"type":"dashboard"},"type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":0,"id":3085,"iteration":1631554945276,"links":[],"panels":[{"datasource":"$datasource","fieldConfig":{"defaults":{"mappings":[],"noValue":"0","thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":5,"w":6,"x":0,"y":0},"id":6,"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["mean"],"fields":"","values":false},"text":{},"textMode":"auto"},"pluginVersion":"8.1.3","targets":[{"expr":"grafana_alerting_result_total{job=~\"$job\", instance=~\"$instance\", state=\"alerting\"}","instant":true,"interval":"1m","legendFormat":"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Firing Alerts","type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":5,"w":6,"x":6,"y":0},"id":8,"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["mean"],"fields":"","values":false},"text":{},"textMode":"auto"},"pluginVersion":"8.1.3","targets":[{"expr":"sum(grafana_stat_totals_dashboard{job=~\"$job\", instance=~\"$instance\"})","interval":"1m","legendFormat":"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Dashboards","type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{"align":null,"displayMode":"auto"},"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":5,"w":12,"x":12,"y":0},"id":10,"options":{"showHeader":true},"pluginVersion":"8.1.3","targets":[{"expr":"grafana_build_info{job=~\"$job\", instance=~\"$instance\"}","instant":true,"interval":"1m","legendFormat":"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Build Info","transformations":[{"id":"labelsToFields","options":{}},{"id":"organize","options":{"excludeByName":{"Time":true,"Value":true,"branch":true,"container":true,"goversion":true,"namespace":true,"pod":true,"revision":true},"indexByName":{"Time":7,"Value":11,"branch":4,"container":8,"edition":2,"goversion":6,"instance":1,"job":0,"namespace":9,"pod":10,"revision":5,"version":3},"renameByName":{}}}],"type":"table"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":8,"w":12,"x":0,"y":5},"hiddenSeries":false,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.1.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (status_code) (irate(grafana_http_request_duration_seconds_count{job=~\"$job\", instance=~\"$instance\"}[1m])) ","interval":"1m","legendFormat":"{{status_code}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"RPS","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"$$hashKey":"object:157","format":"reqps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"$$hashKey":"object:158","format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":8,"w":12,"x":12,"y":5},"hiddenSeries":false,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.1.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"exemplar":true,"expr":"histogram_quantile(0.99, sum(irate(grafana_http_request_duration_seconds_bucket{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) by (le)) * 1","interval":"1m","legendFormat":"99th Percentile","refId":"A"},{"exemplar":true,"expr":"histogram_quantile(0.50, sum(irate(grafana_http_request_duration_seconds_bucket{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) by (le)) * 1","interval":"1m","legendFormat":"50th Percentile","refId":"B"},{"exemplar":true,"expr":"sum(irate(grafana_http_request_duration_seconds_sum{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) * 1 / sum(irate(grafana_http_request_duration_seconds_count{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval]))","interval":"1m","legendFormat":"Average","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Request Latency","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"$$hashKey":"object:210","format":"ms","label":null,"logBase":1,"max":null,"min":null,"show":true},{"$$hashKey":"object:211","format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"schemaVersion":30,"tags":[],"templating":{"list":[{"current":{"selected":true,"text":"dev-cortex","value":"dev-cortex"},"description":null,"error":null,"hide":0,"includeAll":false,"label":null,"multi":false,"name":"datasource","options":[],"query":"prometheus","queryValue":"","refresh":1,"regex":"","skipUrlSync":false,"type":"datasource"},{"allValue":".*","current":{"selected":false,"text":["default/grafana"],"value":["default/grafana"]},"datasource":"$datasource","definition":"label_values(grafana_build_info, job)","description":null,"error":null,"hide":0,"includeAll":true,"label":null,"multi":true,"name":"job","options":[],"query":{"query":"label_values(grafana_build_info, job)","refId":"Billing Admin-job-Variable-Query"},"refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tagsQuery":"","type":"query","useTags":false},{"allValue":".*","current":{"selected":false,"text":"All","value":"$__all"},"datasource":"$datasource","definition":"label_values(grafana_build_info, instance)","description":null,"error":null,"hide":0,"includeAll":true,"label":null,"multi":true,"name":"instance","options":[],"query":{"query":"label_values(grafana_build_info, instance)","refId":"Billing Admin-instance-Variable-Query"},"refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-6h","to":"now"},"timepicker":{"refresh_intervals":["10s","30s","1m","5m","15m","30m","1h","2h","1d"]},"timezone": "utc","title":"Grafana Overview","uid":"6be0s85Mk","version":2} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-coredns.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-k8s-coredns + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + k8s-coredns.json: |- + {"annotations":{"list":[{"builtIn":1,"datasource":{"type":"datasource","uid":"grafana"},"enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"description":"A dashboard for the CoreDNS DNS server with updated metrics for version 1.7.0+. Based on the CoreDNS dashboard by buhay.","editable":true,"fiscalYearStartMonth":0,"gnetId":12539,"graphTooltip":0,"id":7,"links":[{"icon":"external link","tags":[],"targetBlank":true,"title":"CoreDNS.io","type":"link","url":"https://coredns.io"}],"liveNow":false,"panels":[{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":8,"x":0,"y":0},"id":2,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_request_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (proto) or\nsum(rate(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (proto)","format":"time_series","interval":"1m","intervalFactor":2,"legendFormat":"{{ proto }}","refId":"A","step":60}],"title":"Requests (total)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":8,"x":8,"y":0},"id":4,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_request_type_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (type) or \nsum(rate(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (type)","interval":"1m","intervalFactor":2,"legendFormat":"{{ type }}","refId":"A","step":60}],"title":"Requests (by qtype)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":8,"x":16,"y":0},"id":6,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_request_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (zone) or\nsum(rate(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (zone)","interval":"1m","intervalFactor":2,"legendFormat":"{{ zone }}","refId":"A","step":60}],"title":"Requests (by zone)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":0,"y":7},"id":8,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_request_do_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) or\nsum(rate(coredns_dns_do_requests_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m]))","interval":"1m","intervalFactor":2,"legendFormat":"DO","refId":"A","step":40},{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_request_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) or\nsum(rate(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m]))","interval":"1m","intervalFactor":2,"legendFormat":"total","refId":"B","step":40}],"title":"Requests (DO bit)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"bytes","unitScale":true},"overrides":[{"matcher":{"id":"byName","options":"tcp:90"},"properties":[{"id":"unit","value":"short"}]},{"matcher":{"id":"byName","options":"tcp:99 "},"properties":[{"id":"unit","value":"short"}]},{"matcher":{"id":"byName","options":"tcp:50"},"properties":[{"id":"unit","value":"short"}]}]},"gridPos":{"h":7,"w":6,"x":12,"y":7},"id":10,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"none"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.99, (sum(rate(coredns_dns_request_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)))","interval":"1m","intervalFactor":2,"legendFormat":"{{ proto }}:99 ","refId":"A","step":60},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.90, (sum(rate(coredns_dns_request_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)))","intervalFactor":2,"legendFormat":"{{ proto }}:90","refId":"B","step":60},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.50, (sum(rate(coredns_dns_request_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)))","intervalFactor":2,"legendFormat":"{{ proto }}:50","refId":"C","step":60}],"title":"Requests (size, udp)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"bytes","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":6,"x":18,"y":7},"id":12,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"none"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.99, (sum(rate(coredns_dns_request_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto)))","format":"time_series","interval":"1m","intervalFactor":2,"legendFormat":"{{ proto }}:99 ","refId":"A","step":60},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.90, (sum(rate(coredns_dns_request_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto)))","format":"time_series","interval":"1m","intervalFactor":2,"legendFormat":"{{ proto }}:90","refId":"B","step":60},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.50, (sum(rate(coredns_dns_request_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto)))","format":"time_series","interval":"1m","intervalFactor":2,"legendFormat":"{{ proto }}:50","refId":"C","step":60}],"title":"Requests (size,tcp)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":0,"y":14},"id":14,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_response_rcode_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (rcode) or\nsum(rate(coredns_dns_responses_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (rcode)","interval":"1m","intervalFactor":2,"legendFormat":"{{ rcode }}","refId":"A","step":40}],"title":"Responses (by rcode)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"s","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":12,"y":14},"id":32,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"none"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.99, (sum(rate(coredns_dns_request_duration_seconds{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (job)) or (sum(rate(coredns_dns_request_duration_seconds_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (le, job)))","format":"time_series","intervalFactor":2,"legendFormat":"99%","refId":"A","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.90, (sum(rate(coredns_dns_request_duration_seconds{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by ()) or (sum(rate(coredns_dns_request_duration_seconds_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (le)))","format":"time_series","intervalFactor":2,"legendFormat":"90%","refId":"B","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.50, (sum(rate(coredns_dns_request_duration_seconds{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by ()) or (sum(rate(coredns_dns_request_duration_seconds_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (le)))","format":"time_series","intervalFactor":2,"legendFormat":"50%","refId":"C","step":40}],"title":"Responses (duration)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"bytes","unitScale":true},"overrides":[{"matcher":{"id":"byName","options":"tcp:50%"},"properties":[{"id":"unit","value":"short"}]},{"matcher":{"id":"byName","options":"tcp:90%"},"properties":[{"id":"unit","value":"short"}]},{"matcher":{"id":"byName","options":"tcp:99%"},"properties":[{"id":"unit","value":"short"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":21},"id":18,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"none"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.99, (sum(rate(coredns_dns_response_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))) ","interval":"1m","intervalFactor":2,"legendFormat":"{{ proto }}:99%","refId":"A","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.90, (sum(rate(coredns_dns_response_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))) ","interval":"1m","intervalFactor":2,"legendFormat":"{{ proto }}:90%","refId":"B","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.50, (sum(rate(coredns_dns_response_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))) ","hide":false,"intervalFactor":2,"legendFormat":"{{ proto }}:50%","metric":"","refId":"C","step":40}],"title":"Responses (size, udp)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"bytes","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":12,"y":21},"id":20,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"none"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.99, (sum(rate(coredns_dns_response_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))) ","format":"time_series","intervalFactor":2,"legendFormat":"{{ proto }}:99%","refId":"A","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.90, (sum(rate(coredns_dns_response_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))) ","format":"time_series","intervalFactor":2,"legendFormat":"{{ proto }}:90%","refId":"B","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.50, (sum(rate(coredns_dns_response_size_bytes{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (proto)) or (sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))) ","format":"time_series","intervalFactor":2,"legendFormat":"{{ proto }}:50%","metric":"","refId":"C","step":40}],"title":"Responses (size, tcp)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"decbytes","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":0,"y":28},"id":22,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(coredns_cache_size{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}) by (type) or\nsum(coredns_cache_entries{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}) by (type)","interval":"1m","intervalFactor":2,"legendFormat":"{{ type }}","refId":"A","step":40}],"title":"Cache (size)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":12,"y":28},"id":24,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_cache_hits_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (type)","hide":false,"intervalFactor":2,"legendFormat":"hits:{{ type }}","refId":"A","step":40},{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_cache_misses_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (type)","hide":false,"intervalFactor":2,"legendFormat":"misses","refId":"B","step":40}],"title":"Cache (hitrate)","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["dns","coredns"],"templating":{"list":[{"current":{},"hide":0,"includeAll":false,"multi":false,"name":"datasource","options":[],"query":"prometheus","queryValue":"","refresh":1,"regex":"","skipUrlSync":false,"type":"datasource"},{"allValue":".*","current":{"selected":false,"text":"All","value":"$__all"},"datasource":{"type":"prometheus","uid":"$datasource"},"definition":"label_values(coredns_dns_requests_total, cluster)","hide":2,"includeAll":true,"label":"Cluster","multi":false,"name":"cluster","options":[],"query":"label_values(coredns_dns_requests_total, cluster)","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tagsQuery":"","type":"query","useTags":false},{"allValue":".*","current":{"selected":false,"text":"All","value":"$__all"},"datasource":{"type":"prometheus","uid":"${datasource}"},"definition":"label_values(coredns_dns_requests_total{cluster=~\"$cluster\"},job)","hide":0,"includeAll":true,"label":"Job","multi":false,"name":"job","options":[],"query":{"qryType":1,"query":"label_values(coredns_dns_requests_total{cluster=~\"$cluster\"},job)","refId":"PrometheusVariableQueryEditor-VariableQuery"},"refresh":2,"regex":"","skipUrlSync":false,"sort":1,"type":"query"},{"allValue":".*","current":{"selected":false,"text":"All","value":"$__all"},"datasource":{"type":"prometheus","uid":"$datasource"},"definition":"label_values(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\"}, instance)","hide":0,"includeAll":true,"label":"Instance","multi":false,"name":"instance","options":[],"query":"label_values(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\"}, instance)","refresh":2,"regex":"","skipUrlSync":false,"sort":3,"tagValuesQuery":"","tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-3h","to":"now"},"timepicker":{"refresh_intervals":["10s","30s","1m","5m","15m","30m","1h","2h","1d"]},"timezone": "utc","title":"CoreDNS","uid":"vkQ0UHxik","version":3,"weekStart":""} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-cluster.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-k8s-resources-cluster + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + k8s-resources-cluster.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"cluster:node_cpu:ratio_rate5m{cluster=\"$cluster\"}","instant":true}],"title":"CPU Utilisation","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":4,"y":0},"id":2,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})","instant":true}],"title":"CPU Requests Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":8,"y":0},"id":3,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})","instant":true}],"title":"CPU Limits Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":12,"y":0},"id":4,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\",cluster=\"$cluster\"})","instant":true}],"title":"Memory Utilisation","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":16,"y":0},"id":5,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})","instant":true}],"title":"Memory Requests Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":20,"y":0},"id":6,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})","instant":true}],"title":"Memory Limits Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}}},"gridPos":{"h":6,"w":24,"x":0,"y":6},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\"}) by (namespace)","legendFormat":"__auto"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":12},"id":8,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Value #A":8,"Value #B":9,"Value #C":10,"Value #D":11,"Value #E":12,"Value #F":13,"Value #G":14,"namespace":7},"renameByName":{"Value #A":"Pods","Value #B":"Workloads","Value #C":"CPU Usage","Value #D":"CPU Requests","Value #E":"CPU Requests %","Value #F":"CPU Limits","Value #G":"CPU Limits %","namespace":"Namespace"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":6,"w":24,"x":0,"y":18},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)","legendFormat":"__auto"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Memory Usage"},"properties":[{"id":"unit","value":"bytes"}]},{"matcher":{"id":"byName","options":"Memory Requests"},"properties":[{"id":"unit","value":"bytes"}]},{"matcher":{"id":"byName","options":"Memory Limits"},"properties":[{"id":"unit","value":"bytes"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":24},"id":10,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true}],"title":"Memory Requests by Namespace","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Value #A":8,"Value #B":9,"Value #C":10,"Value #D":11,"Value #E":12,"Value #F":13,"Value #G":14,"namespace":7},"renameByName":{"Value #A":"Pods","Value #B":"Workloads","Value #C":"Memory Usage","Value #D":"Memory Requests","Value #E":"Memory Requests %","Value #F":"Memory Limits","Value #G":"Memory Limits %","namespace":"Namespace"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":30},"id":11,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true}],"title":"Current Network Usage","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"namespace":6},"renameByName":{"Value #A":"Current Receive Bandwidth","Value #B":"Current Transmit Bandwidth","Value #C":"Rate of Received Packets","Value #D":"Rate of Transmitted Packets","Value #E":"Rate of Received Packets Dropped","Value #F":"Rate of Transmitted Packets Dropped","namespace":"Namespace"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":6,"w":24,"x":0,"y":36},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":6,"w":24,"x":0,"y":42},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":6,"w":24,"x":0,"y":48},"id":14,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Namespace: Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":6,"w":24,"x":0,"y":54},"id":15,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Namespace: Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":6,"w":24,"x":0,"y":60},"id":16,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":6,"w":24,"x":0,"y":66},"id":17,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":6,"w":24,"x":0,"y":72},"id":18,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":6,"w":24,"x":0,"y":78},"id":19,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"iops"}},"gridPos":{"h":6,"w":24,"x":0,"y":84},"id":20,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"ceil(sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval])))","legendFormat":"__auto"}],"title":"IOPS(Reads+Writes)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":6,"w":24,"x":0,"y":90},"id":21,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"ThroughPut(Read+Write)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/IOPS/"},"properties":[{"id":"unit","value":"iops"}]},{"matcher":{"id":"byRegexp","options":"/Throughput/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":96},"id":22,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true}],"title":"Current Storage IO","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"namespace":6},"renameByName":{"Value #A":"IOPS(Reads)","Value #B":"IOPS(Writes)","Value #C":"IOPS(Reads + Writes)","Value #D":"Throughput(Read)","Value #E":"Throughput(Write)","Value #F":"Throughput(Read + Write)","namespace":"Namespace"}}}],"type":"table"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Cluster","uid":"efa86fd1d0c121a26444b636a3f509a8"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-multicluster.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-k8s-resources-multicluster + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + k8s-resources-multicluster.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":3,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:node_cpu:ratio_rate5m) / count(cluster:node_cpu:ratio_rate5m)","instant":true}],"title":"CPU Utilisation","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":4,"y":0},"id":2,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"cpu\"})","instant":true}],"title":"CPU Requests Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":8,"y":0},"id":3,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"cpu\"})","instant":true}],"title":"CPU Limits Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":12,"y":0},"id":4,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"1 - sum(:node_memory_MemAvailable_bytes:sum) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\"})","instant":true}],"title":"Memory Utilisation","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":16,"y":0},"id":5,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"memory\"})","instant":true}],"title":"Memory Requests Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":20,"y":0},"id":6,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"memory\"})","instant":true}],"title":"Memory Limits Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"}}},"gridPos":{"h":7,"w":24,"x":0,"y":1},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m) by (cluster)","legendFormat":"__auto"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Cluster"},"properties":[{"id":"links","value":[{"title":"Drill down","url":"/d/efa86fd1d0c121a26444b636a3f509a8/kubernetes-compute-resources-cluster?${datasource:queryparam}&var-cluster=${__data.fields.Cluster}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":2},"id":8,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m) by (cluster) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m) by (cluster) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"cluster","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value #C":8,"Value #D":9,"Value #E":10,"cluster":5},"renameByName":{"Value #A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU Limits","Value #E":"CPU Limits %","cluster":"Cluster"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"bytes"}},"gridPos":{"h":7,"w":24,"x":0,"y":3},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster)","legendFormat":"__auto"}],"title":"Memory Usage (w/o cache)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Cluster"},"properties":[{"id":"links","value":[{"title":"Drill down","url":"/d/efa86fd1d0c121a26444b636a3f509a8/kubernetes-compute-resources-cluster?${datasource:queryparam}&var-cluster=${__data.fields.Cluster}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":4},"id":10,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true}],"title":"Memory Requests by Cluster","transformations":[{"id":"joinByField","options":{"byField":"cluster","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value #C":8,"Value #D":9,"Value #E":10,"cluster":5},"renameByName":{"Value #A":"Memory Usage","Value #B":"Memory Requests","Value #C":"Memory Requests %","Value #D":"Memory Limits","Value #E":"Memory Limits %","cluster":"Cluster"}}}],"type":"table"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Multi-Cluster","uid":"b59e6c9f2fcbe2e16d77fc492374cc4f"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-namespace.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-k8s-resources-namespace + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + k8s-resources-namespace.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})","instant":true}],"title":"CPU Utilisation (from requests)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":6,"y":0},"id":2,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})","instant":true}],"title":"CPU Utilisation (from limits)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":12,"y":0},"id":3,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})","instant":true}],"title":"Memory Utilisation (from requests)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":18,"y":0},"id":4,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})","instant":true}],"title":"Memory Utilisation (from limits)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","legendFormat":"__auto"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"}))","legendFormat":"quota - requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"}))","legendFormat":"quota - limits"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":6,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value #C":8,"Value #D":9,"Value #E":10,"pod":5},"renameByName":{"Value #A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU Limits","Value #E":"CPU Limits %","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":21},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)","legendFormat":"__auto"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"}))","legendFormat":"quota - requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"}))","legendFormat":"quota - limits"}],"title":"Memory Usage (w/o cache)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":28},"id":8,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_cache{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)","format":"table","instant":true}],"title":"Memory Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true,"Time 8":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Time 8":7,"Value #A":9,"Value #B":10,"Value #C":11,"Value #D":12,"Value #E":13,"Value #F":14,"Value #G":15,"Value #H":16,"pod":8},"renameByName":{"Value #A":"Memory Usage","Value #B":"Memory Requests","Value #C":"Memory Requests %","Value #D":"Memory Limits","Value #E":"Memory Limits %","Value #F":"Memory Usage (RSS)","Value #G":"Memory Usage (Cache)","Value #H":"Memory Usage (Swap)","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":35},"id":9,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true}],"title":"Current Network Usage","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"pod":6},"renameByName":{"Value #A":"Current Receive Bandwidth","Value #B":"Current Transmit Bandwidth","Value #C":"Rate of Received Packets","Value #D":"Rate of Transmitted Packets","Value #E":"Rate of Received Packets Dropped","Value #F":"Rate of Transmitted Packets Dropped","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":56},"id":14,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":56},"id":15,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"iops"}},"gridPos":{"h":7,"w":12,"x":0,"y":63},"id":16,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])))","legendFormat":"__auto"}],"title":"IOPS(Reads+Writes)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":63},"id":17,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"ThroughPut(Read+Write)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/IOPS/"},"properties":[{"id":"unit","value":"iops"}]},{"matcher":{"id":"byRegexp","options":"/Throughput/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":70},"id":18,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true}],"title":"Current Storage IO","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"pod":6},"renameByName":{"Value #A":"IOPS(Reads)","Value #B":"IOPS(Writes)","Value #C":"IOPS(Reads + Writes)","Value #D":"Throughput(Read)","Value #E":"Throughput(Write)","Value #F":"Throughput(Read + Write)","pod":"Pod"}}}],"type":"table"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"namespace","name":"namespace","query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Namespace (Pods)","uid":"85a562078cdf77779eaa1add43ccec1e"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-node.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-k8s-resources-node + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + k8s-resources-node.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true,"stacking":{"mode":"normal"}}},"overrides":[{"matcher":{"id":"byName","options":"max capacity"},"properties":[{"id":"color","value":{"fixedColor":"red","mode":"fixed"}},{"id":"custom.stacking","value":{"mode":"none"}},{"id":"custom.hideFrom","value":{"legend":false,"tooltip":true,"viz":false}},{"id":"custom.lineStyle","value":{"dash":[10,10],"fill":"dash"}}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_node_status_capacity{cluster=\"$cluster\", job=\"kube-state-metrics\", node=~\"$node\", resource=\"cpu\"})","legendFormat":"max capacity"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","legendFormat":"{{pod}}"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":6},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"renameByName":{"Value #A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU Limits","Value #E":"CPU Limits %","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true,"stacking":{"mode":"normal"}},"unit":"bytes"},"overrides":[{"matcher":{"id":"byName","options":"max capacity"},"properties":[{"id":"color","value":{"fixedColor":"red","mode":"fixed"}},{"id":"custom.stacking","value":{"mode":"none"}},{"id":"custom.hideFrom","value":{"legend":false,"tooltip":true,"viz":false}},{"id":"custom.lineStyle","value":{"dash":[10,10],"fill":"dash"}}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":12},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_node_status_capacity{cluster=\"$cluster\", job=\"kube-state-metrics\", node=~\"$node\", resource=\"memory\"})","legendFormat":"max capacity"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)","legendFormat":"{{pod}}"}],"title":"Memory Usage (w/cache)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true,"stacking":{"mode":"normal"}},"unit":"bytes"},"overrides":[{"matcher":{"id":"byName","options":"max capacity"},"properties":[{"id":"color","value":{"fixedColor":"red","mode":"fixed"}},{"id":"custom.stacking","value":{"mode":"none"}},{"id":"custom.hideFrom","value":{"legend":false,"tooltip":true,"viz":false}},{"id":"custom.lineStyle","value":{"dash":[10,10],"fill":"dash"}}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":18},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_node_status_capacity{cluster=\"$cluster\", job=\"kube-state-metrics\", node=~\"$node\", resource=\"memory\"})","legendFormat":"max capacity"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)","legendFormat":"{{pod}}"}],"title":"Memory Usage (w/o cache)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":24},"id":5,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true}],"title":"Memory Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true,"Time 8":true},"renameByName":{"Value #A":"Memory Usage","Value #B":"Memory Requests","Value #C":"Memory Requests %","Value #D":"Memory Limits","Value #E":"Memory Limits %","Value #F":"Memory Usage (RSS)","Value #G":"Memory Usage (Cache)","Value #H":"Memory Usage (Swap)","pod":"Pod"}}}],"type":"table"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"node","multi":true,"name":"node","query":"label_values(kube_node_info{cluster=\"$cluster\"}, node)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Node (Pods)","uid":"200ac8fdbfbb74b39aff88118e4d1c2c"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-pod.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-k8s-resources-pod + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + k8s-resources-pod.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\", container!=\"\"}) by (container)","legendFormat":"__auto"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n","legendFormat":"requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n","legendFormat":"limits"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"axisColorMode":"thresholds","axisSoftMax":1,"axisSoftMin":0,"fillOpacity":10,"showPoints":"never","spanNulls":true,"thresholdsStyle":{"mode":"dashed+area"}},"unit":"percentunit"},"overrides":[{"matcher":{"id":"byFrameRefID","options":"A"},"properties":[{"id":"thresholds","value":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":0.25}]}},{"id":"color","value":{"mode":"thresholds","seriesBy":"lastNotNull"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(increase(container_cpu_cfs_throttled_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container) /sum(increase(container_cpu_cfs_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)","legendFormat":"__auto"}],"title":"CPU Throttling","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"container","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value #C":8,"Value #D":9,"Value #E":10,"container":5},"renameByName":{"Value #A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU Limits","Value #E":"CPU Limits %","container":"Container"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":21},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)","legendFormat":"__auto"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n","legendFormat":"requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n","legendFormat":"limits"}],"title":"Memory Usage (WSS)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":28},"id":5,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_cache{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)","format":"table","instant":true}],"title":"Memory Quota","transformations":[{"id":"joinByField","options":{"byField":"container","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true,"Time 8":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Time 8":7,"Value #A":9,"Value #B":10,"Value #C":11,"Value #D":12,"Value #E":13,"Value #F":14,"Value #G":15,"Value #H":16,"container":8},"renameByName":{"Value #A":"Memory Usage","Value #B":"Memory Requests","Value #C":"Memory Requests %","Value #D":"Memory Limits","Value #E":"Memory Limits %","Value #F":"Memory Usage (RSS)","Value #G":"Memory Usage (Cache)","Value #H":"Memory Usage (Swap)","container":"Container"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":35},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":35},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"iops"}},"gridPos":{"h":7,"w":12,"x":0,"y":56},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"ceil(sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))","legendFormat":"Reads"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"ceil(sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))","legendFormat":"Writes"}],"title":"IOPS (Pod)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":56},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))","legendFormat":"Reads"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))","legendFormat":"Writes"}],"title":"ThroughPut (Pod)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"iops"}},"gridPos":{"h":7,"w":12,"x":0,"y":63},"id":14,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"ceil(sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval])))","legendFormat":"__auto"}],"title":"IOPS (Containers)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":63},"id":15,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"ThroughPut (Containers)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/IOPS/"},"properties":[{"id":"unit","value":"iops"}]},{"matcher":{"id":"byRegexp","options":"/Throughput/"},"properties":[{"id":"unit","value":"Bps"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":70},"id":16,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\",device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true}],"title":"Current Storage IO","transformations":[{"id":"joinByField","options":{"byField":"container","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"container":6},"renameByName":{"Value #A":"IOPS(Reads)","Value #B":"IOPS(Writes)","Value #C":"IOPS(Reads + Writes)","Value #D":"Throughput(Read)","Value #E":"Throughput(Write)","Value #F":"Throughput(Read + Write)","container":"Container"}}}],"type":"table"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"namespace","name":"namespace","query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"pod","name":"pod","query":"label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, pod)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Pod","uid":"6581e46e4e5c7ba40a07646395ef7b23"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workload.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-k8s-resources-workload + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + k8s-resources-workload.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}}},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","legendFormat":"__auto"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value #C":8,"Value #D":9,"Value #E":10,"pod":5},"renameByName":{"Value #A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU Limits","Value #E":"CPU Limits %","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","legendFormat":"__auto"}],"title":"Memory Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":21},"id":4,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true}],"title":"Memory Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":9,"Value #B":10,"Value #C":11,"Value #D":12,"Value #E":13,"pod":8},"renameByName":{"Value #A":"Memory Usage","Value #B":"Memory Requests","Value #C":"Memory Requests %","Value #D":"Memory Limits","Value #E":"Memory Limits %","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":28},"id":5,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true}],"title":"Current Network Usage","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"pod":6},"renameByName":{"Value #A":"Current Receive Bandwidth","Value #B":"Current Transmit Bandwidth","Value #C":"Rate of Received Packets","Value #D":"Rate of Transmitted Packets","Value #E":"Rate of Received Packets Dropped","Value #F":"Rate of Transmitted Packets Dropped","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":35},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":35},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(avg(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Pod: Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(avg(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Pod: Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":56},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":56},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"namespace","name":"namespace","query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"workload_type","name":"type","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload_type)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"workload","name":"workload","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}, workload)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Workload","uid":"a164a7f0339f99e89cea5cb47e9be617"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workloads-namespace.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-k8s-resources-workloads-namespace + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + k8s-resources-workloads-namespace.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","legendFormat":"{{workload}} - {{workload_type}}"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=~\"requests.cpu|cpu\"}))","legendFormat":"quota - requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=~\"limits.cpu\"}))","legendFormat":"quota - limits"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Workload"},"properties":[{"id":"links","value":[{"title":"Drill down to workloads","url":"/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-type=${__data.fields.Type}&var-workload=${__data.fields.Workload}"}]}]},{"matcher":{"id":"byName","options":"Running Pods"},"properties":[{"id":"unit","value":"none"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload, workload_type)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"workload","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"workload_type 2":true,"workload_type 3":true,"workload_type 4":true,"workload_type 5":true,"workload_type 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":8,"Value #B":9,"Value #C":10,"Value #D":11,"Value #E":12,"Value #F":13,"workload":6,"workload_type 1":7,"workload_type 2":14,"workload_type 3":15,"workload_type 4":16,"workload_type 5":17,"workload_type 6":18},"renameByName":{"Value #A":"Running Pods","Value #B":"CPU Usage","Value #C":"CPU Requests","Value #D":"CPU Requests %","Value #E":"CPU Limits","Value #F":"CPU Limits %","workload":"Workload","workload_type 1":"Type"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","legendFormat":"{{workload}} - {{workload_type}}"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=~\"requests.memory|memory\"}))","legendFormat":"quota - requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=~\"limits.memory\"}))","legendFormat":"quota - limits"}],"title":"Memory Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Workload"},"properties":[{"id":"links","value":[{"title":"Drill down to workloads","url":"/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-type=${__data.fields.Type}&var-workload=${__data.fields.Workload}"}]}]},{"matcher":{"id":"byName","options":"Running Pods"},"properties":[{"id":"unit","value":"none"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":21},"id":4,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload, workload_type)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true}],"title":"Memory Quota","transformations":[{"id":"joinByField","options":{"byField":"workload","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"workload_type 2":true,"workload_type 3":true,"workload_type 4":true,"workload_type 5":true,"workload_type 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":8,"Value #B":9,"Value #C":10,"Value #D":11,"Value #E":12,"Value #F":13,"workload":6,"workload_type 1":7,"workload_type 2":14,"workload_type 3":15,"workload_type 4":16,"workload_type 5":17,"workload_type 6":18},"renameByName":{"Value #A":"Running Pods","Value #B":"Memory Usage","Value #C":"Memory Requests","Value #D":"Memory Requests %","Value #E":"Memory Limits","Value #F":"Memory Limits %","workload":"Workload","workload_type 1":"Type"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Workload"},"properties":[{"id":"links","value":[{"title":"Drill down to workloads","url":"/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-type=${__data.fields.Type}&var-workload=${__data.fields.Workload}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":28},"id":5,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true}],"title":"Current Network Usage","transformations":[{"id":"joinByField","options":{"byField":"workload","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"workload":6},"renameByName":{"Value #A":"Current Receive Bandwidth","Value #B":"Current Transmit Bandwidth","Value #C":"Rate of Received Packets","Value #D":"Rate of Transmitted Packets","Value #E":"Rate of Received Packets Dropped","Value #F":"Rate of Transmitted Packets Dropped","workload":"Workload"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":35},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":35},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(avg(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Workload: Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(avg(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Workload: Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":56},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":56},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"namespace","name":"namespace","query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"workload_type","name":"type","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Namespace (Workloads)","uid":"a87fb0d919ec0ea5f6543124e16c42a5"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/kubelet.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-kubelet + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + kubelet.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kubelet_node_name{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"})","instant":true}],"title":"Running Kubelets","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":4,"y":0},"id":2,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})","instant":true}],"title":"Running Pods","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":8,"y":0},"id":3,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})","instant":true}],"title":"Running Containers","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":12,"y":0},"id":4,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\", state=\"actual_state_of_world\"})","instant":true}],"title":"Actual Volume Count","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":16,"y":0},"id":5,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",state=\"desired_state_of_world\"})","instant":true}],"title":"Desired Volume Count","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":20,"y":0},"id":6,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval]))","instant":true}],"title":"Config Error Count","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":7},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (operation_type, instance)","legendFormat":"{{instance}} {{operation_type}}"}],"title":"Operation Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":12,"y":7},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)","legendFormat":"{{instance}} {{operation_type}}"}],"title":"Operation Error Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))","legendFormat":"{{instance}} {{operation_type}}"}],"title":"Operation Duration 99th quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":21},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}} pod"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}} worker"}],"title":"Pod Start Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":12,"x":12,"y":21},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}} pod"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}} worker"}],"title":"Pod Start Duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":28},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)","legendFormat":"{{instance}} {{operation_name}} {{volume_plugin}}"}],"title":"Storage Operation Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":12,"y":28},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)","legendFormat":"{{instance}} {{operation_name}} {{volume_plugin}}"}],"title":"Storage Operation Error Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":35},"id":14,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin, le))","legendFormat":"{{instance}} {{operation_name}} {{volume_plugin}}"}],"title":"Storage Operation Duration 99th quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":15,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)","legendFormat":"{{operation_type}}"}],"title":"Cgroup manager operation rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":16,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))","legendFormat":"{{instance}} {{operation_type}}"}],"title":"Cgroup manager 99th quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":17,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}}"}],"title":"PLEG relist rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":18,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}}"}],"title":"PLEG relist interval","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":56},"id":19,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}}"}],"title":"PLEG relist duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":24,"x":0,"y":63},"id":20,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","legendFormat":"2xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","legendFormat":"3xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","legendFormat":"4xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","legendFormat":"5xx"}],"title":"RPC rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":70},"id":21,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, verb, le))","legendFormat":"{{instance}} {{verb}}"}],"title":"Request duration 99th quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":77},"id":22,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":77},"id":23,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])","legendFormat":"{{instance}}"}],"title":"CPU usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":77},"id":24,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"go_goroutines{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Goroutines","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"instance","name":"instance","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics\",cluster=\"$cluster\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Kubelet","uid":"3138fa155d5915769fbded898ac09fd9"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-pod.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-namespace-by-pod + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + namespace-by-pod.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$namespace","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Received","type":"gauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$namespace","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Transmitted","type":"gauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down","url":"/d/7a18067ce943a40ae25454675c19ff5c/kubernetes-networking-pod?${datasource:queryparam}&var-cluster=${cluster}&var-namespace=${namespace}&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":9,"w":24,"x":0,"y":9},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true}],"title":"Current Network Usage","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"pod":6},"renameByName":{"Value #A":"Current Receive Bandwidth","Value #B":"Current Transmit Bandwidth","Value #C":"Rate of Received Packets","Value #D":"Rate of Transmitted Packets","Value #E":"Rate of Received Packets Dropped","Value #F":"Rate of Transmitted Packets Dropped","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":27},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":27},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":36},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":36},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"allValue":".+","current":{"selected":false,"text":"kube-system","value":"kube-system"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"namespace","name":"namespace","query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Networking / Namespace (Pods)","uid":"8b7a8b326d7a6f1f04244066368c67af"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-workload.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-namespace-by-workload + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + namespace-by-workload.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Received","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Transmitted","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bytes/"},"properties":[{"id":"unit","value":"binBps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Workload"},"properties":[{"id":"links","value":[{"title":"Drill down","url":"/d/728bf77cc1166d2f3133bf25846876cc/kubernetes-networking-workload?${datasource:queryparam}&var-cluster=${cluster}&var-namespace=${namespace}&var-type=${__data.fields.Type}&var-workload=${__data.fields.Workload}"}]}]}]},"gridPos":{"h":9,"w":24,"x":0,"y":9},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true}],"title":"Current Status","transformations":[{"id":"joinByField","options":{"byField":"workload","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true,"Time 8":true,"workload_type 2":true,"workload_type 3":true,"workload_type 4":true,"workload_type 5":true,"workload_type 6":true,"workload_type 7":true,"workload_type 8":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Time 8":7,"Value #A":10,"Value #B":11,"Value #C":12,"Value #D":13,"Value #E":14,"Value #F":15,"Value #G":16,"Value #H":17,"workload":8,"workload_type 1":9,"workload_type 2":18,"workload_type 3":19,"workload_type 4":20,"workload_type 5":21,"workload_type 6":22,"workload_type 7":23,"workload_type 8":24},"renameByName":{"Value #A":"Rx Bytes","Value #B":"Tx Bytes","Value #C":"Rx Bytes (Avg)","Value #D":"Tx Bytes (Avg)","Value #E":"Rx Packets","Value #F":"Tx Packets","Value #G":"Rx Packets Dropped","Value #H":"Tx Packets Dropped","workload":"Workload","workload_type 1":"Type"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":27},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Workload: Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":27},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Workload: Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":36},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":36},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":45},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":45},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"current":{"selected":false,"text":"kube-system","value":"kube-system"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"namespace","name":"namespace","query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"workload_type","name":"type","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Networking / Namespace (Workload)","uid":"bbb2a765a623ae38130206c7d94a160f"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/node-cluster-rsrc-use.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-node-cluster-rsrc-use + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + node-cluster-rsrc-use.json: |- + {"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"CPU","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"((\n instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n *\n instance:node_num_cpu:sum{job=\"node-exporter\", cluster=\"$cluster\"}\n) != 0 )\n/ scalar(sum(instance:node_num_cpu:sum{job=\"node-exporter\", cluster=\"$cluster\"}))\n","legendFormat":"{{ instance }}"}],"title":"CPU Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n instance:node_load1_per_cpu:ratio{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance:node_load1_per_cpu:ratio{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n","legendFormat":"{{ instance }}"}],"title":"CPU Saturation (Load1 per CPU)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"panels":[],"title":"Memory","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":9},"id":5,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n instance:node_memory_utilisation:ratio{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance:node_memory_utilisation:ratio{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n","legendFormat":"{{ instance }}"}],"title":"Memory Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"rds"}},"gridPos":{"h":7,"w":12,"x":12,"y":9},"id":6,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}","legendFormat":"{{ instance }}"}],"title":"Memory Saturation (Major Page Faults)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":16},"id":7,"panels":[],"title":"Network","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"Bps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/Transmit/"},"properties":[{"id":"custom.transform","value":"negative-Y"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":17},"id":8,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0","legendFormat":"{{ instance }} Receive"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0","legendFormat":"{{ instance }} Transmit"}],"title":"Network Utilisation (Bytes Receive/Transmit)","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"Bps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/Transmit/"},"properties":[{"id":"custom.transform","value":"negative-Y"}]}]},"gridPos":{"h":7,"w":12,"x":12,"y":17},"id":9,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0","legendFormat":"{{ instance }} Receive"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0","legendFormat":"{{ instance }} Transmit"}],"title":"Network Saturation (Drops Receive/Transmit)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":24},"id":10,"panels":[],"title":"Disk IO","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":25},"id":11,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n/ scalar(count(instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}))\n","legendFormat":"{{ instance }} {{device}}"}],"title":"Disk IO Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":12,"y":25},"id":12,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n/ scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}))\n","legendFormat":"{{ instance }} {{device}}"}],"title":"Disk IO Saturation","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":34},"id":13,"panels":[],"title":"Disk Space","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":24,"x":0,"y":35},"id":14,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum without (device) (\n max without (fstype, mountpoint) ((\n node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"}\n -\n node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"}\n ) != 0)\n)\n/ scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"})))\n","legendFormat":"{{ instance }}"}],"title":"Disk Space Utilisation","type":"timeseries"}],"refresh":"30s","schemaVersion":39,"tags":["node-exporter-mixin"],"templating":{"list":[{"name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"includeAll":false,"name":"cluster","query":"label_values(node_time_seconds, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Node Exporter / USE Method / Cluster","uid":"3e97d1d02672cdd0861f4c97c64f89b2"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/node-rsrc-use.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-node-rsrc-use + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + node-rsrc-use.json: |- + {"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"CPU","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Utilisation"}],"title":"CPU Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_load1_per_cpu:ratio{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Saturation"}],"title":"CPU Saturation (Load1 per CPU)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"panels":[],"title":"Memory","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":9},"id":5,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_memory_utilisation:ratio{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Utilisation"}],"title":"Memory Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"rds"}},"gridPos":{"h":7,"w":12,"x":12,"y":9},"id":6,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Major page Faults"}],"title":"Memory Saturation (Major Page Faults)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":16},"id":7,"panels":[],"title":"Network","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"Bps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/Transmit/"},"properties":[{"id":"custom.transform","value":"negative-Y"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":17},"id":8,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Receive"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Transmit"}],"title":"Network Utilisation (Bytes Receive/Transmit)","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"Bps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/Transmit/"},"properties":[{"id":"custom.transform","value":"negative-Y"}]}]},"gridPos":{"h":7,"w":12,"x":12,"y":17},"id":9,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Receive"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Transmit"}],"title":"Network Saturation (Drops Receive/Transmit)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":24},"id":10,"panels":[],"title":"Disk IO","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":25},"id":11,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"{{device}}"}],"title":"Disk IO Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":12,"y":25},"id":12,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"{{device}}"}],"title":"Disk IO Saturation","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":34},"id":13,"panels":[],"title":"Disk Space","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":24,"x":0,"y":35},"id":14,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sort_desc(1 -\n (\n max without (mountpoint, fstype) (node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\", cluster=\"$cluster\"})\n /\n max without (mountpoint, fstype) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\", cluster=\"$cluster\"})\n ) != 0\n)\n","legendFormat":"{{device}}"}],"title":"Disk Space Utilisation","type":"timeseries"}],"refresh":"30s","schemaVersion":39,"tags":["node-exporter-mixin"],"templating":{"list":[{"name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"includeAll":false,"name":"cluster","query":"label_values(node_time_seconds, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"name":"instance","query":"label_values(node_exporter_build_info{job=\"node-exporter\", cluster=\"$cluster\"}, instance)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Node Exporter / USE Method / Node","uid":"fac67cfbe174d3ef53eb473d73d9212f"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes-aix.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-nodes-aix + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + nodes-aix.json: |- + {"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"CPU","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"max":1,"min":0,"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\", cluster=\"$cluster\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\", cluster=\"$cluster\"})\n)\n","intervalFactor":5,"legendFormat":"{{cpu}}"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load1{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"1m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load5{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"5m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load15{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"15m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", mode=\"idle\"})","legendFormat":"logical cores"}],"title":"Load Average","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"title":"Memory","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"none"}},"min":0,"unit":"bytes"}},"gridPos":{"h":7,"w":18,"x":0,"y":9},"id":5,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"Physical Memory"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} -\n node_memory_available_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n)\n","legendFormat":"Memory Used"}],"title":"Memory Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"max":100,"min":0,"thresholds":{"steps":[{"color":"rgba(50, 172, 45, 0.97)"},{"color":"rgba(237, 129, 40, 0.89)","value":80},{"color":"rgba(245, 54, 54, 0.9)","value":90}]},"unit":"percent"}},"gridPos":{"h":7,"w":6,"x":18,"y":9},"id":6,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"100 -\n(\n avg(node_memory_available_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}) /\n avg(node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"})\n * 100\n)\n"}],"title":"Memory Usage","type":"gauge"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":18},"id":7,"panels":[],"title":"Disk","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0},"overrides":[{"matcher":{"id":"byRegexp","options":"/ read| written/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/ io time/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":19},"id":8,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} read"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} written"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} io time"}],"title":"Disk I/O","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"thresholds":{"steps":[{"color":"green"},{"color":"yellow","value":0.8},{"color":"red","value":0.9}]},"unit":"decbytes"},"overrides":[{"matcher":{"id":"byName","options":"Mounted on"},"properties":[{"id":"custom.width","value":260}]},{"matcher":{"id":"byName","options":"Size"},"properties":[{"id":"custom.width","value":93}]},{"matcher":{"id":"byName","options":"Used"},"properties":[{"id":"custom.width","value":72}]},{"matcher":{"id":"byName","options":"Available"},"properties":[{"id":"custom.width","value":88}]},{"matcher":{"id":"byName","options":"Used, %"},"properties":[{"id":"unit","value":"percentunit"},{"id":"custom.cellOptions","value":{"type":"gauge"}},{"id":"max","value":1},{"id":"min","value":0}]}]},"gridPos":{"h":7,"w":12,"x":12,"y":19},"id":9,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""}],"title":"Disk Space Usage","transformations":[{"id":"groupBy","options":{"fields":{"Value #A":{"aggregations":["lastNotNull"],"operation":"aggregate"},"Value #B":{"aggregations":["lastNotNull"],"operation":"aggregate"},"mountpoint":{"aggregations":[],"operation":"groupby"}}}},{"id":"merge"},{"id":"calculateField","options":{"alias":"Used","binary":{"left":"Value #A (lastNotNull)","operator":"-","reducer":"sum","right":"Value #B (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"calculateField","options":{"alias":"Used, %","binary":{"left":"Used","operator":"/","reducer":"sum","right":"Value #A (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"organize","options":{"excludeByName":{},"indexByName":{},"renameByName":{"Value #A (lastNotNull)":"Size","Value #B (lastNotNull)":"Available","mountpoint":"Mounted on"}}},{"id":"sortBy","options":{"fields":{},"sort":[{"field":"Mounted on"}]}}],"type":"table"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":26},"id":10,"panels":[],"title":"Network","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network received (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":27},"id":11,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Received","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network transmitted (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":27},"id":12,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Transmitted","type":"timeseries"}],"refresh":"30s","schemaVersion":39,"tags":["node-exporter-mixin"],"templating":{"list":[{"name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"Cluster","name":"cluster","query":"label_values(node_uname_info{job=\"node-exporter\", sysname!=\"Darwin\"}, cluster)","refresh":2,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"label":"Instance","name":"instance","query":"label_values(node_uname_info{job=\"node-exporter\", cluster=\"$cluster\", sysname!=\"Darwin\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Node Exporter / AIX","uid":"7e0a61e486f727d763fb1d86fdd629c2"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes-darwin.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-nodes-darwin + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + nodes-darwin.json: |- + {"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"CPU","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"max":1,"min":0,"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\", cluster=\"$cluster\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\", cluster=\"$cluster\"})\n)\n","intervalFactor":5,"legendFormat":"{{cpu}}"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load1{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"1m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load5{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"5m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load15{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"15m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", mode=\"idle\"})","legendFormat":"logical cores"}],"title":"Load Average","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"title":"Memory","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"none"}},"min":0,"unit":"bytes"}},"gridPos":{"h":7,"w":18,"x":0,"y":9},"id":5,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"Physical Memory"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} -\n node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} +\n node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} +\n node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n)\n","legendFormat":"Memory Used"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} -\n node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n)\n","legendFormat":"App Memory"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"Wired Memory"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"Compressed"}],"title":"Memory Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"max":100,"min":0,"thresholds":{"steps":[{"color":"rgba(50, 172, 45, 0.97)"},{"color":"rgba(237, 129, 40, 0.89)","value":80},{"color":"rgba(245, 54, 54, 0.9)","value":90}]},"unit":"percent"}},"gridPos":{"h":7,"w":6,"x":18,"y":9},"id":6,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n (\n avg(node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}) -\n avg(node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}) +\n avg(node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}) +\n avg(node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"})\n ) /\n avg(node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"})\n)\n*\n100\n"}],"title":"Memory Usage","type":"gauge"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":18},"id":7,"panels":[],"title":"Disk","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0},"overrides":[{"matcher":{"id":"byRegexp","options":"/ read| written/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/ io time/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":19},"id":8,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} read"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} written"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} io time"}],"title":"Disk I/O","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"thresholds":{"steps":[{"color":"green"},{"color":"yellow","value":0.8},{"color":"red","value":0.9}]},"unit":"decbytes"},"overrides":[{"matcher":{"id":"byName","options":"Mounted on"},"properties":[{"id":"custom.width","value":260}]},{"matcher":{"id":"byName","options":"Size"},"properties":[{"id":"custom.width","value":93}]},{"matcher":{"id":"byName","options":"Used"},"properties":[{"id":"custom.width","value":72}]},{"matcher":{"id":"byName","options":"Available"},"properties":[{"id":"custom.width","value":88}]},{"matcher":{"id":"byName","options":"Used, %"},"properties":[{"id":"unit","value":"percentunit"},{"id":"custom.cellOptions","value":{"type":"gauge"}},{"id":"max","value":1},{"id":"min","value":0}]}]},"gridPos":{"h":7,"w":12,"x":12,"y":19},"id":9,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""}],"title":"Disk Space Usage","transformations":[{"id":"groupBy","options":{"fields":{"Value #A":{"aggregations":["lastNotNull"],"operation":"aggregate"},"Value #B":{"aggregations":["lastNotNull"],"operation":"aggregate"},"mountpoint":{"aggregations":[],"operation":"groupby"}}}},{"id":"merge"},{"id":"calculateField","options":{"alias":"Used","binary":{"left":"Value #A (lastNotNull)","operator":"-","reducer":"sum","right":"Value #B (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"calculateField","options":{"alias":"Used, %","binary":{"left":"Used","operator":"/","reducer":"sum","right":"Value #A (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"organize","options":{"excludeByName":{},"indexByName":{},"renameByName":{"Value #A (lastNotNull)":"Size","Value #B (lastNotNull)":"Available","mountpoint":"Mounted on"}}},{"id":"sortBy","options":{"fields":{},"sort":[{"field":"Mounted on"}]}}],"type":"table"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":26},"id":10,"panels":[],"title":"Network","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network received (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":27},"id":11,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Received","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network transmitted (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":27},"id":12,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Transmitted","type":"timeseries"}],"refresh":"30s","schemaVersion":39,"tags":["node-exporter-mixin"],"templating":{"list":[{"name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"Cluster","name":"cluster","query":"label_values(node_uname_info{job=\"node-exporter\", sysname=\"Darwin\"}, cluster)","refresh":2,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"label":"Instance","name":"instance","query":"label_values(node_uname_info{job=\"node-exporter\", cluster=\"$cluster\", sysname=\"Darwin\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Node Exporter / MacOS","uid":"629701ea43bf69291922ea45f4a87d37"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-nodes + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + nodes.json: |- + {"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"CPU","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"max":1,"min":0,"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\", cluster=\"$cluster\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\", cluster=\"$cluster\"})\n)\n","intervalFactor":5,"legendFormat":"{{cpu}}"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load1{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"1m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load5{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"5m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load15{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"15m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", mode=\"idle\"})","legendFormat":"logical cores"}],"title":"Load Average","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"title":"Memory","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"min":0,"unit":"bytes"}},"gridPos":{"h":7,"w":18,"x":0,"y":9},"id":5,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n-\n node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n-\n node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n-\n node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n)\n","legendFormat":"memory used"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"memory buffers"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"memory cached"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"memory free"}],"title":"Memory Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"max":100,"min":0,"thresholds":{"steps":[{"color":"rgba(50, 172, 45, 0.97)"},{"color":"rgba(237, 129, 40, 0.89)","value":80},{"color":"rgba(245, 54, 54, 0.9)","value":90}]},"unit":"percent"}},"gridPos":{"h":7,"w":6,"x":18,"y":9},"id":6,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"100 -\n(\n avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}) /\n avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"})\n* 100\n)\n"}],"title":"Memory Usage","type":"gauge"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":18},"id":7,"panels":[],"title":"Disk","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0},"overrides":[{"matcher":{"id":"byRegexp","options":"/ read| written/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/ io time/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":19},"id":8,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} read"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} written"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} io time"}],"title":"Disk I/O","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"thresholds":{"steps":[{"color":"green"},{"color":"yellow","value":0.8},{"color":"red","value":0.9}]},"unit":"decbytes"},"overrides":[{"matcher":{"id":"byName","options":"Mounted on"},"properties":[{"id":"custom.width","value":260}]},{"matcher":{"id":"byName","options":"Size"},"properties":[{"id":"custom.width","value":93}]},{"matcher":{"id":"byName","options":"Used"},"properties":[{"id":"custom.width","value":72}]},{"matcher":{"id":"byName","options":"Available"},"properties":[{"id":"custom.width","value":88}]},{"matcher":{"id":"byName","options":"Used, %"},"properties":[{"id":"unit","value":"percentunit"},{"id":"custom.cellOptions","value":{"type":"gauge"}},{"id":"max","value":1},{"id":"min","value":0}]}]},"gridPos":{"h":7,"w":12,"x":12,"y":19},"id":9,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""}],"title":"Disk Space Usage","transformations":[{"id":"groupBy","options":{"fields":{"Value #A":{"aggregations":["lastNotNull"],"operation":"aggregate"},"Value #B":{"aggregations":["lastNotNull"],"operation":"aggregate"},"mountpoint":{"aggregations":[],"operation":"groupby"}}}},{"id":"merge"},{"id":"calculateField","options":{"alias":"Used","binary":{"left":"Value #A (lastNotNull)","operator":"-","reducer":"sum","right":"Value #B (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"calculateField","options":{"alias":"Used, %","binary":{"left":"Used","operator":"/","reducer":"sum","right":"Value #A (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"organize","options":{"excludeByName":{},"indexByName":{},"renameByName":{"Value #A (lastNotNull)":"Size","Value #B (lastNotNull)":"Available","mountpoint":"Mounted on"}}},{"id":"sortBy","options":{"fields":{},"sort":[{"field":"Mounted on"}]}}],"type":"table"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":26},"id":10,"panels":[],"title":"Network","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network received (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":27},"id":11,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Received","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network transmitted (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":27},"id":12,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Transmitted","type":"timeseries"}],"refresh":"30s","schemaVersion":39,"tags":["node-exporter-mixin"],"templating":{"list":[{"name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"Cluster","name":"cluster","query":"label_values(node_uname_info{job=\"node-exporter\", sysname!=\"Darwin\"}, cluster)","refresh":2,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"label":"Instance","name":"instance","query":"label_values(node_uname_info{job=\"node-exporter\", cluster=\"$cluster\", sysname!=\"Darwin\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Node Exporter / Nodes","uid":"7d57716318ee0dddbac5a7f451fb7753"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/persistentvolumesusage.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-persistentvolumesusage + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + persistentvolumesusage.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":18,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n","legendFormat":"Used Space"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n","legendFormat":"Free Space"}],"title":"Volume Space Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"},"max":100,"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":0},{"color":"orange","value":80},{"color":"red","value":90}]},"unit":"percent"}},"gridPos":{"h":7,"w":6,"x":18,"y":0},"id":2,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"max without(instance,node) (\n(\n topk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n topk(1, kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n/\ntopk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n","instant":true}],"title":"Volume Space Usage","type":"gauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"none"}},"gridPos":{"h":7,"w":18,"y":7},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))","legendFormat":"Used inodes"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n","legendFormat":"Free inodes"}],"title":"Volume inodes Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"},"max":100,"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":0},{"color":"orange","value":80},{"color":"red","value":90}]},"unit":"percent"}},"gridPos":{"h":7,"w":6,"x":18,"y":7},"id":4,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"max without(instance,node) (\ntopk(1, kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n/\ntopk(1, kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n","instant":true}],"title":"Volume inodes Usage","type":"gauge"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"Namespace","name":"namespace","query":"label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"PersistentVolumeClaim","name":"volume","query":"label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\"}, persistentvolumeclaim)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Persistent Volumes","uid":"919b92a8e8041bd567af9edab12c840c"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/pod-total.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-pod-total + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + pod-total.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$pod","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"Current Rate of Bytes Received","type":"gauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$pod","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"Current Rate of Bytes Transmitted","type":"gauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":9},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":9},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":18},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":27},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":27},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"allValue":".+","current":{"selected":false,"text":"kube-system","value":"kube-system"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"namespace","name":"namespace","query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"current":{"selected":false,"text":"kube-system","value":"kube-system"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"pod","name":"pod","query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Networking / Pod","uid":"7a18067ce943a40ae25454675c19ff5c"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-prometheus + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + prometheus.json: |- + {"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"Prometheus Stats","type":"row"},{"datasource":{"type":"prometheus","uid":"$datasource"},"fieldConfig":{"defaults":{"decimals":2,"displayName":"","unit":"short"},"overrides":[{"matcher":{"id":"byName","options":"Time"},"properties":[{"id":"displayName","value":"Time"},{"id":"custom.align","value":null},{"id":"custom.hidden","value":"true"}]},{"matcher":{"id":"byName","options":"cluster"},"properties":[{"id":"custom.align","value":null},{"id":"unit","value":"short"},{"id":"decimals","value":2},{"id":"displayName","value":"Cluster"}]},{"matcher":{"id":"byName","options":"job"},"properties":[{"id":"custom.align","value":null},{"id":"unit","value":"short"},{"id":"decimals","value":2},{"id":"displayName","value":"Job"}]},{"matcher":{"id":"byName","options":"instance"},"properties":[{"id":"displayName","value":"Instance"},{"id":"custom.align","value":null},{"id":"unit","value":"short"},{"id":"decimals","value":2}]},{"matcher":{"id":"byName","options":"version"},"properties":[{"id":"displayName","value":"Version"},{"id":"custom.align","value":null},{"id":"unit","value":"short"},{"id":"decimals","value":2}]},{"matcher":{"id":"byName","options":"Value #A"},"properties":[{"id":"displayName","value":"Count"},{"id":"custom.align","value":null},{"id":"unit","value":"short"},{"id":"decimals","value":2},{"id":"custom.hidden","value":"true"}]},{"matcher":{"id":"byName","options":"Value #B"},"properties":[{"id":"displayName","value":"Uptime"},{"id":"custom.align","value":null},{"id":"unit","value":"s"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":1},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"count by (cluster, job, instance, version) (prometheus_build_info{cluster=~\"$cluster\", job=~\"$job\", instance=~\"$instance\"})","format":"table","instant":true,"legendFormat":""},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (cluster, job, instance) (time() - process_start_time_seconds{cluster=~\"$cluster\", job=~\"$job\", instance=~\"$instance\"})","format":"table","instant":true,"legendFormat":""}],"title":"Prometheus Stats","type":"table"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":3,"panels":[],"title":"Discovery","type":"row"},{"datasource":{"type":"prometheus","uid":"$datasource"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never"},"min":0,"unit":"ms"}},"gridPos":{"h":7,"w":12,"x":0,"y":9},"id":4,"options":{"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(prometheus_target_sync_length_seconds_sum{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[5m])) by (cluster, job, scrape_job, instance) * 1e3","format":"time_series","legendFormat":"{{cluster}}:{{job}}:{{instance}}:{{scrape_job}}"}],"title":"Target Sync","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"$datasource"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"lineWidth":0,"showPoints":"never","stacking":{"mode":"normal"}},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":12,"y":9},"id":5,"options":{"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum by (cluster, job, instance) (prometheus_sd_discovered_targets{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"})","format":"time_series","legendFormat":"{{cluster}}:{{job}}:{{instance}}"}],"title":"Targets","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":16},"id":6,"panels":[],"title":"Retrieval","type":"row"},{"datasource":{"type":"prometheus","uid":"$datasource"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never"},"min":0,"unit":"ms"}},"gridPos":{"h":7,"w":8,"x":0,"y":17},"id":7,"options":{"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(prometheus_target_interval_length_seconds_sum{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}[5m]) / rate(prometheus_target_interval_length_seconds_count{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}[5m]) * 1e3","format":"time_series","legendFormat":"{{cluster}}:{{job}}:{{instance}} {{interval}} configured"}],"title":"Average Scrape Interval Duration","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"$datasource"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"lineWidth":0,"showPoints":"never","stacking":{"mode":"normal"}},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":17},"id":8,"options":{"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_exceeded_body_size_limit_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"exceeded body size limit: {{cluster}} {{job}} {{instance}}"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_exceeded_sample_limit_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"exceeded sample limit: {{cluster}} {{job}} {{instance}}"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"duplicate timestamp: {{cluster}} {{job}} {{instance}}"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_sample_out_of_bounds_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"out of bounds: {{cluster}} {{job}} {{instance}}"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_sample_out_of_order_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"out of order: {{cluster}} {{job}} {{instance}}"}],"title":"Scrape failures","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"$datasource"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"lineWidth":0,"showPoints":"never","stacking":{"mode":"normal"}},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":17},"id":9,"options":{"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(prometheus_tsdb_head_samples_appended_total{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}[5m])","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}}"}],"title":"Appended Samples","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":24},"id":10,"panels":[],"title":"Storage","type":"row"},{"datasource":{"type":"prometheus","uid":"$datasource"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"lineWidth":0,"showPoints":"never","stacking":{"mode":"normal"}},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":0,"y":25},"id":11,"options":{"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"prometheus_tsdb_head_series{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}} head series"}],"title":"Head Series","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"$datasource"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"lineWidth":0,"showPoints":"never","stacking":{"mode":"normal"}},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":12,"y":25},"id":12,"options":{"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"prometheus_tsdb_head_chunks{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}} head chunks"}],"title":"Head Chunks","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":32},"id":13,"panels":[],"title":"Query","type":"row"},{"datasource":{"type":"prometheus","uid":"$datasource"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"lineWidth":0,"showPoints":"never","stacking":{"mode":"normal"}},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":0,"y":33},"id":14,"options":{"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(prometheus_engine_query_duration_seconds_count{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\",slice=\"inner_eval\"}[5m])","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}}"}],"title":"Query Rate","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"$datasource"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"lineWidth":0,"showPoints":"never","stacking":{"mode":"normal"}},"min":0,"unit":"ms"}},"gridPos":{"h":7,"w":12,"x":12,"y":33},"id":15,"options":{"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (slice) (prometheus_engine_query_duration_seconds{quantile=\"0.9\",cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}) * 1e3","format":"time_series","legendFormat":"{{slice}}"}],"title":"Stage Duration","type":"timeseries"}],"schemaVersion":39,"tags":["prometheus-mixin"],"templating":{"list":[{"current":{"selected":false,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","type":"datasource"},{"allValue":".*","current":{"selected":false,"text":["$__all"],"value":["$__all"]},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"includeAll":true,"label":"cluster","multi":true,"name":"cluster","query":"label_values(prometheus_build_info{}, cluster)","refresh":2,"sort":2,"type":"query"},{"allValue":".+","datasource":{"type":"prometheus","uid":"${datasource}"},"includeAll":true,"label":"job","multi":true,"name":"job","query":"label_values(prometheus_build_info{cluster=~\"$cluster\"}, job)","refresh":2,"sort":2,"type":"query"},{"allValue":".+","datasource":{"type":"prometheus","uid":"${datasource}"},"includeAll":true,"label":"instance","multi":true,"name":"instance","query":"label_values(prometheus_build_info{cluster=~\"$cluster\", job=~\"$job\"}, instance)","refresh":2,"sort":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["60s"]},"timezone": "utc","title":"Prometheus / Overview","uid":"9fa0d141-d019-4ad7-8bc5-42196ee308bd"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/proxy.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-proxy + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + proxy.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(up{cluster=\"$cluster\", job=\"kube-proxy\"})","instant":true}],"title":"Up","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":10,"x":4,"y":0},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))","legendFormat":"rate"}],"title":"Rules Sync Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":10,"x":14,"y":0},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))","legendFormat":"{{instance}}"}],"title":"Rules Sync Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":7},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubeproxy_network_programming_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))","legendFormat":"rate"}],"title":"Network Programming Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":12,"x":12,"y":7},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}}"}],"title":"Network Programming Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":8,"x":0,"y":14},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","legendFormat":"2xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","legendFormat":"3xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","legendFormat":"4xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","legendFormat":"5xx"}],"title":"Kube API Request Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":16,"x":8,"y":14},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[$__rate_interval])) by (verb, le))","legendFormat":"{{verb}}"}],"title":"Post Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":21},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, le))","legendFormat":"{{verb}}"}],"title":"Get Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":28},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":28},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}[$__rate_interval])","legendFormat":"{{instance}}"}],"title":"CPU usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":28},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"go_goroutines{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Goroutines","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-proxy\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"allValue":".+","datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"instance","name":"instance","query":"label_values(up{job=\"kube-proxy\", cluster=\"$cluster\", job=\"kube-proxy\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Proxy","uid":"632e265de029684c40b21cb76bca4f94"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/scheduler.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-scheduler + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + scheduler.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(up{cluster=\"$cluster\", job=\"kube-scheduler\"})","instant":true}],"title":"Up","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":10,"x":4,"y":0},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","legendFormat":"{{cluster}} {{instance}} e2e"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","legendFormat":"{{cluster}} {{instance}} binding"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","legendFormat":"{{cluster}} {{instance}} scheduling algorithm"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","legendFormat":"{{cluster}} {{instance}} volume"}],"title":"Scheduling Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":10,"x":14,"y":0},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","legendFormat":"{{cluster}} {{instance}} e2e"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","legendFormat":"{{cluster}} {{instance}} binding"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","legendFormat":"{{cluster}} {{instance}} scheduling algorithm"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","legendFormat":"{{cluster}} {{instance}} volume"}],"title":"Scheduling latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":8,"x":0,"y":7},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","legendFormat":"2xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","legendFormat":"3xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","legendFormat":"4xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","legendFormat":"5xx"}],"title":"Kube API Request Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":16,"x":8,"y":7},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, le))","legendFormat":"{{verb}}"}],"title":"Post Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, le))","legendFormat":"{{verb}}"}],"title":"Get Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":21},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":21},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])","legendFormat":"{{instance}}"}],"title":"CPU usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":21},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"go_goroutines{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Goroutines","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-scheduler\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"allValue":".+","datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"instance","name":"instance","query":"label_values(up{job=\"kube-scheduler\", cluster=\"$cluster\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Scheduler","uid":"2e6b6a3b4bddf1427b3a55aa1311c656"} +--- +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/workload-total.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: prometheus + name: kube-prometheus-stack-1754-workload-total + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +data: + workload-total.json: |- + {"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Received","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Transmitted","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":9},"id":3,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Average Rate of Bytes Received","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":9},"id":4,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Average Rate of Bytes Transmitted","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":18},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":27},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":27},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":36},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":36},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(kube_pod_info{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"allValue":".+","current":{"selected":false,"text":"kube-system","value":"kube-system"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"namespace","name":"namespace","query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"workload","name":"workload","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\"}, workload)","refresh":2,"sort":1,"type":"query"},{"allValue":".+","datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"workload_type","name":"type","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Networking / Workload","uid":"728bf77cc1166d2f3133bf25846876cc"} +--- +# Source: kube-prometheus-stack/charts/grafana/templates/clusterrole.yaml +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" + name: kube-prometheus-stack-1754164871-grafana-clusterrole +rules: + - apiGroups: [""] # "" indicates the core API group + resources: ["configmaps", "secrets"] + verbs: ["get", "watch", "list"] +--- +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/role.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + helm.sh/chart: kube-state-metrics-6.1.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "2.16.0" + release: kube-prometheus-stack-1754164871 + name: kube-prometheus-stack-1754164871-kube-state-metrics +rules: + +- apiGroups: ["certificates.k8s.io"] + resources: + - certificatesigningrequests + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - configmaps + verbs: ["list", "watch"] + +- apiGroups: ["batch"] + resources: + - cronjobs + verbs: ["list", "watch"] + +- apiGroups: ["apps"] + resources: + - daemonsets + verbs: ["list", "watch"] + +- apiGroups: ["apps"] + resources: + - deployments + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - endpoints + verbs: ["list", "watch"] + +- apiGroups: ["autoscaling"] + resources: + - horizontalpodautoscalers + verbs: ["list", "watch"] + +- apiGroups: ["networking.k8s.io"] + resources: + - ingresses + verbs: ["list", "watch"] + +- apiGroups: ["batch"] + resources: + - jobs + verbs: ["list", "watch"] + +- apiGroups: ["coordination.k8s.io"] + resources: + - leases + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - limitranges + verbs: ["list", "watch"] + +- apiGroups: ["admissionregistration.k8s.io"] + resources: + - mutatingwebhookconfigurations + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - namespaces + verbs: ["list", "watch"] + +- apiGroups: ["networking.k8s.io"] + resources: + - networkpolicies + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - nodes + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - persistentvolumeclaims + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - persistentvolumes + verbs: ["list", "watch"] + +- apiGroups: ["policy"] + resources: + - poddisruptionbudgets + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - pods + verbs: ["list", "watch"] + +- apiGroups: ["apps"] + resources: + - replicasets + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - replicationcontrollers + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - resourcequotas + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - secrets + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - services + verbs: ["list", "watch"] + +- apiGroups: ["apps"] + resources: + - statefulsets + verbs: ["list", "watch"] + +- apiGroups: ["storage.k8s.io"] + resources: + - storageclasses + verbs: ["list", "watch"] + +- apiGroups: ["admissionregistration.k8s.io"] + resources: + - validatingwebhookconfigurations + verbs: ["list", "watch"] + +- apiGroups: ["storage.k8s.io"] + resources: + - volumeattachments + verbs: ["list", "watch"] +--- +# Source: kube-prometheus-stack/templates/prometheus-operator/clusterrole.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: kube-prometheus-stack-1754-operator + labels: + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + app: kube-prometheus-stack-operator + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/component: prometheus-operator +rules: +- apiGroups: + - monitoring.coreos.com + resources: + - alertmanagers + - alertmanagers/finalizers + - alertmanagers/status + - alertmanagerconfigs + - prometheuses + - prometheuses/finalizers + - prometheuses/status + - prometheusagents + - prometheusagents/finalizers + - prometheusagents/status + - thanosrulers + - thanosrulers/finalizers + - thanosrulers/status + - scrapeconfigs + - servicemonitors + - podmonitors + - probes + - prometheusrules + verbs: + - '*' +- apiGroups: + - apps + resources: + - statefulsets + verbs: + - '*' +- apiGroups: + - "" + resources: + - configmaps + - secrets + verbs: + - '*' +- apiGroups: + - "" + resources: + - pods + verbs: + - list + - delete +- apiGroups: + - "" + resources: + - services + - services/finalizers + - endpoints + verbs: + - get + - create + - update + - delete +- apiGroups: + - "" + resources: + - nodes + verbs: + - list + - watch +- apiGroups: + - "" + resources: + - namespaces + verbs: + - get + - list + - watch +- apiGroups: + - "" + resources: + - events + verbs: + - patch + - create +- apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch +- apiGroups: + - storage.k8s.io + resources: + - storageclasses + verbs: + - get +- apiGroups: + - discovery.k8s.io + resources: + - endpointslices + verbs: + - get + - create + - list + - watch + - update + - delete +--- +# Source: kube-prometheus-stack/templates/prometheus/clusterrole.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: kube-prometheus-stack-1754-prometheus + labels: + app: kube-prometheus-stack-prometheus + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +rules: +# These permissions (to examine all namespaces) are not in the kube-prometheus repo. +# They're grabbed from https://github.com/prometheus/prometheus/blob/master/documentation/examples/rbac-setup.yml +# kube-prometheus deliberately defaults to a more restrictive setup that is not appropriate for our general audience. +- apiGroups: [""] + resources: + - nodes + - nodes/metrics + - services + - endpoints + - pods + verbs: ["get", "list", "watch"] +- apiGroups: ["discovery.k8s.io"] + resources: + - endpointslices + verbs: ["get", "list", "watch"] +- apiGroups: + - "networking.k8s.io" + resources: + - ingresses + verbs: ["get", "list", "watch"] +- nonResourceURLs: ["/metrics", "/metrics/cadvisor"] + verbs: ["get"] +--- +# Source: kube-prometheus-stack/charts/grafana/templates/clusterrolebinding.yaml +kind: ClusterRoleBinding +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: kube-prometheus-stack-1754164871-grafana-clusterrolebinding + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" +subjects: + - kind: ServiceAccount + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus +roleRef: + kind: ClusterRole + name: kube-prometheus-stack-1754164871-grafana-clusterrole + apiGroup: rbac.authorization.k8s.io +--- +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/clusterrolebinding.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + helm.sh/chart: kube-state-metrics-6.1.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "2.16.0" + release: kube-prometheus-stack-1754164871 + name: kube-prometheus-stack-1754164871-kube-state-metrics +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: kube-prometheus-stack-1754164871-kube-state-metrics +subjects: +- kind: ServiceAccount + name: kube-prometheus-stack-1754164871-kube-state-metrics + namespace: prometheus +--- +# Source: kube-prometheus-stack/templates/prometheus-operator/clusterrolebinding.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: kube-prometheus-stack-1754-operator + labels: + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + app: kube-prometheus-stack-operator + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/component: prometheus-operator +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: kube-prometheus-stack-1754-operator +subjects: +- kind: ServiceAccount + name: kube-prometheus-stack-1754-operator + namespace: prometheus +--- +# Source: kube-prometheus-stack/templates/prometheus/clusterrolebinding.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: kube-prometheus-stack-1754-prometheus + labels: + app: kube-prometheus-stack-prometheus + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: kube-prometheus-stack-1754-prometheus +subjects: + - kind: ServiceAccount + name: kube-prometheus-stack-1754-prometheus + namespace: prometheus +--- +# Source: kube-prometheus-stack/charts/grafana/templates/role.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" +rules: [] +--- +# Source: kube-prometheus-stack/charts/grafana/templates/rolebinding.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: kube-prometheus-stack-1754164871-grafana +subjects: +- kind: ServiceAccount + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus +--- +# Source: kube-prometheus-stack/charts/grafana/templates/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" +spec: + type: ClusterIP + ports: + - name: http-web + port: 80 + protocol: TCP + targetPort: 3000 + selector: + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 +--- +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754164871-kube-state-metrics + namespace: prometheus + labels: + helm.sh/chart: kube-state-metrics-6.1.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "2.16.0" + release: kube-prometheus-stack-1754164871 + annotations: +spec: + type: "ClusterIP" + ports: + - name: "http" + protocol: TCP + port: 8080 + targetPort: 8080 + + selector: + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 +--- +# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754164871-prometheus-node-exporter + namespace: prometheus + labels: + helm.sh/chart: prometheus-node-exporter-4.47.3 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "1.9.1" + release: kube-prometheus-stack-1754164871 + jobLabel: node-exporter + annotations: + prometheus.io/scrape: "true" +spec: + type: ClusterIP + ports: + - port: 9100 + targetPort: 9100 + protocol: TCP + name: http-metrics + selector: + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 +--- +# Source: kube-prometheus-stack/templates/alertmanager/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754-alertmanager + namespace: prometheus + labels: + app: kube-prometheus-stack-alertmanager + self-monitor: "true" + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + ports: + - name: http-web + port: 9093 + targetPort: 9093 + protocol: TCP + - name: reloader-web + appProtocol: http + port: 8080 + targetPort: reloader-web + selector: + app.kubernetes.io/name: alertmanager + alertmanager: kube-prometheus-stack-1754-alertmanager + sessionAffinity: None + type: "ClusterIP" +--- +# Source: kube-prometheus-stack/templates/exporters/core-dns/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754-coredns + labels: + app: kube-prometheus-stack-coredns + jobLabel: coredns + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: 9153 + protocol: TCP + targetPort: 9153 + selector: + k8s-app: kube-dns +--- +# Source: kube-prometheus-stack/templates/exporters/kube-controller-manager/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754-kube-controller-manager + labels: + app: kube-prometheus-stack-kube-controller-manager + jobLabel: kube-controller-manager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: 10257 + protocol: TCP + targetPort: 10257 + selector: + component: kube-controller-manager + type: ClusterIP +--- +# Source: kube-prometheus-stack/templates/exporters/kube-etcd/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754-kube-etcd + labels: + app: kube-prometheus-stack-kube-etcd + jobLabel: kube-etcd + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: 2381 + protocol: TCP + targetPort: 2381 + selector: + component: etcd + type: ClusterIP +--- +# Source: kube-prometheus-stack/templates/exporters/kube-proxy/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754-kube-proxy + labels: + app: kube-prometheus-stack-kube-proxy + jobLabel: kube-proxy + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: 10249 + protocol: TCP + targetPort: 10249 + selector: + k8s-app: kube-proxy + type: ClusterIP +--- +# Source: kube-prometheus-stack/templates/exporters/kube-scheduler/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754-kube-scheduler + labels: + app: kube-prometheus-stack-kube-scheduler + jobLabel: kube-scheduler + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: 10259 + protocol: TCP + targetPort: 10259 + selector: + component: kube-scheduler + type: ClusterIP +--- +# Source: kube-prometheus-stack/templates/prometheus-operator/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754-operator + namespace: prometheus + labels: + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + app: kube-prometheus-stack-operator + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/component: prometheus-operator +spec: + ports: + - name: https + port: 443 + targetPort: https + selector: + app: kube-prometheus-stack-operator + release: "kube-prometheus-stack-1754164871" + type: "ClusterIP" +--- +# Source: kube-prometheus-stack/templates/prometheus/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-prometheus-stack-1754-prometheus + namespace: prometheus + labels: + app: kube-prometheus-stack-prometheus + self-monitor: "true" + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + externalTrafficPolicy: Cluster + ports: + - name: http-web + nodePort: 30090 + port: 9090 + targetPort: 9090 + - name: reloader-web + appProtocol: http + port: 8080 + targetPort: reloader-web + publishNotReadyAddresses: false + selector: + app.kubernetes.io/name: prometheus + operator.prometheus.io/name: kube-prometheus-stack-1754-prometheus + sessionAffinity: None + type: "NodePort" +--- +# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/daemonset.yaml +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: kube-prometheus-stack-1754164871-prometheus-node-exporter + namespace: prometheus + labels: + helm.sh/chart: prometheus-node-exporter-4.47.3 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "1.9.1" + release: kube-prometheus-stack-1754164871 +spec: + selector: + matchLabels: + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + revisionHistoryLimit: 10 + updateStrategy: + rollingUpdate: + maxUnavailable: 1 + type: RollingUpdate + template: + metadata: + annotations: + cluster-autoscaler.kubernetes.io/safe-to-evict: "true" + labels: + helm.sh/chart: prometheus-node-exporter-4.47.3 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "1.9.1" + release: kube-prometheus-stack-1754164871 + jobLabel: node-exporter + spec: + automountServiceAccountToken: false + securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + serviceAccountName: kube-prometheus-stack-1754164871-prometheus-node-exporter + containers: + - name: node-exporter + image: quay.io/prometheus/node-exporter:v1.9.1 + imagePullPolicy: IfNotPresent + args: + - --path.procfs=/host/proc + - --path.sysfs=/host/sys + - --path.rootfs=/host/root + - --path.udev.data=/host/root/run/udev/data + - --web.listen-address=[$(HOST_IP)]:9100 + - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/) + - --collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs|erofs)$ + securityContext: + readOnlyRootFilesystem: true + env: + - name: HOST_IP + value: 0.0.0.0 + ports: + - name: http-metrics + containerPort: 9100 + protocol: TCP + livenessProbe: + failureThreshold: 3 + httpGet: + httpHeaders: + path: / + port: http-metrics + scheme: HTTP + initialDelaySeconds: 0 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + readinessProbe: + failureThreshold: 3 + httpGet: + httpHeaders: + path: / + port: http-metrics + scheme: HTTP + initialDelaySeconds: 0 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + volumeMounts: + - name: proc + mountPath: /host/proc + readOnly: true + - name: sys + mountPath: /host/sys + readOnly: true + - name: root + mountPath: /host/root + mountPropagation: HostToContainer + readOnly: true + hostNetwork: true + hostPID: true + hostIPC: false + affinity: + nodeAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + nodeSelectorTerms: + - matchExpressions: + - key: eks.amazonaws.com/compute-type + operator: NotIn + values: + - fargate + - key: type + operator: NotIn + values: + - virtual-kubelet + nodeSelector: + kubernetes.io/os: linux + tolerations: + - effect: NoSchedule + operator: Exists + volumes: + - name: proc + hostPath: + path: /proc + - name: sys + hostPath: + path: /sys + - name: root + hostPath: + path: / +--- +# Source: kube-prometheus-stack/charts/grafana/templates/deployment.yaml +apiVersion: apps/v1 +kind: Deployment +metadata: + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" +spec: + replicas: 1 + revisionHistoryLimit: 10 + selector: + matchLabels: + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + strategy: + type: RollingUpdate + template: + metadata: + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" + annotations: + checksum/config: 0e9cbd0ea8e24e32f7dfca5bab17a2ba05652642f0a09a4882833ae88e4cc4a3 + checksum/sc-dashboard-provider-config: e70bf6a851099d385178a76de9757bb0bef8299da6d8443602590e44f05fdf24 + checksum/secret: 032056e9c62bbe9d1daa41ee49cd3d9524c076f51ca4c65adadf4ef08ef28712 + kubectl.kubernetes.io/default-container: grafana + spec: + + serviceAccountName: kube-prometheus-stack-1754164871-grafana + automountServiceAccountToken: true + shareProcessNamespace: false + securityContext: + fsGroup: 472 + runAsGroup: 472 + runAsNonRoot: true + runAsUser: 472 + enableServiceLinks: true + containers: + - name: grafana-sc-dashboard + image: "quay.io/kiwigrid/k8s-sidecar:1.30.3" + imagePullPolicy: IfNotPresent + env: + - name: METHOD + value: WATCH + - name: LABEL + value: "grafana_dashboard" + - name: LABEL_VALUE + value: "1" + - name: FOLDER + value: "/tmp/dashboards" + - name: RESOURCE + value: "both" + - name: NAMESPACE + value: "ALL" + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: kube-prometheus-stack-1754164871-grafana + key: admin-user + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: kube-prometheus-stack-1754164871-grafana + key: admin-password + - name: REQ_URL + value: http://localhost:3000/api/admin/provisioning/dashboards/reload + - name: REQ_METHOD + value: POST + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + volumeMounts: + - name: sc-dashboard-volume + mountPath: "/tmp/dashboards" + - name: grafana-sc-datasources + image: "quay.io/kiwigrid/k8s-sidecar:1.30.3" + imagePullPolicy: IfNotPresent + env: + - name: METHOD + value: WATCH + - name: LABEL + value: "grafana_datasource" + - name: LABEL_VALUE + value: "1" + - name: FOLDER + value: "/etc/grafana/provisioning/datasources" + - name: RESOURCE + value: "both" + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: kube-prometheus-stack-1754164871-grafana + key: admin-user + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: kube-prometheus-stack-1754164871-grafana + key: admin-password + - name: REQ_URL + value: http://localhost:3000/api/admin/provisioning/datasources/reload + - name: REQ_METHOD + value: POST + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + volumeMounts: + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" + - name: grafana + image: "docker.io/grafana/grafana:12.1.0" + imagePullPolicy: IfNotPresent + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + volumeMounts: + - name: config + mountPath: "/etc/grafana/grafana.ini" + subPath: grafana.ini + - name: storage + mountPath: "/var/lib/grafana" + - name: sc-dashboard-volume + mountPath: "/tmp/dashboards" + - name: sc-dashboard-provider + mountPath: "/etc/grafana/provisioning/dashboards/sc-dashboardproviders.yaml" + subPath: provider.yaml + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" + ports: + - name: grafana + containerPort: 3000 + protocol: TCP + - name: gossip-tcp + containerPort: 9094 + protocol: TCP + - name: gossip-udp + containerPort: 9094 + protocol: UDP + - name: profiling + containerPort: 6060 + protocol: TCP + env: + - name: POD_IP + valueFrom: + fieldRef: + fieldPath: status.podIP + - name: GF_SECURITY_ADMIN_USER + valueFrom: + secretKeyRef: + name: kube-prometheus-stack-1754164871-grafana + key: admin-user + - name: GF_SECURITY_ADMIN_PASSWORD + valueFrom: + secretKeyRef: + name: kube-prometheus-stack-1754164871-grafana + key: admin-password + - name: GF_PATHS_DATA + value: /var/lib/grafana/ + - name: GF_PATHS_LOGS + value: /var/log/grafana + - name: GF_PATHS_PLUGINS + value: /var/lib/grafana/plugins + - name: GF_PATHS_PROVISIONING + value: /etc/grafana/provisioning + livenessProbe: + failureThreshold: 10 + httpGet: + path: /api/health + port: 3000 + initialDelaySeconds: 60 + timeoutSeconds: 30 + readinessProbe: + httpGet: + path: /api/health + port: 3000 + volumes: + - name: config + configMap: + name: kube-prometheus-stack-1754164871-grafana + - name: storage + emptyDir: {} + - name: sc-dashboard-volume + emptyDir: {} + - name: sc-dashboard-provider + configMap: + name: kube-prometheus-stack-1754164871-grafana-config-dashboards + - name: sc-datasources-volume + emptyDir: {} +--- +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/deployment.yaml +apiVersion: apps/v1 +kind: Deployment +metadata: + name: kube-prometheus-stack-1754164871-kube-state-metrics + namespace: prometheus + labels: + helm.sh/chart: kube-state-metrics-6.1.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "2.16.0" + release: kube-prometheus-stack-1754164871 +spec: + selector: + matchLabels: + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + replicas: 1 + strategy: + type: RollingUpdate + revisionHistoryLimit: 10 + template: + metadata: + labels: + helm.sh/chart: kube-state-metrics-6.1.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "2.16.0" + release: kube-prometheus-stack-1754164871 + spec: + automountServiceAccountToken: true + hostNetwork: false + serviceAccountName: kube-prometheus-stack-1754164871-kube-state-metrics + securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + seccompProfile: + type: RuntimeDefault + dnsPolicy: ClusterFirst + containers: + - name: kube-state-metrics + args: + - --port=8080 + - --resources=certificatesigningrequests,configmaps,cronjobs,daemonsets,deployments,endpoints,horizontalpodautoscalers,ingresses,jobs,leases,limitranges,mutatingwebhookconfigurations,namespaces,networkpolicies,nodes,persistentvolumeclaims,persistentvolumes,poddisruptionbudgets,pods,replicasets,replicationcontrollers,resourcequotas,secrets,services,statefulsets,storageclasses,validatingwebhookconfigurations,volumeattachments + imagePullPolicy: IfNotPresent + image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.16.0 + ports: + - containerPort: 8080 + name: "http" + livenessProbe: + failureThreshold: 3 + httpGet: + httpHeaders: + path: /livez + port: 8080 + scheme: HTTP + initialDelaySeconds: 5 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 5 + readinessProbe: + failureThreshold: 3 + httpGet: + httpHeaders: + path: /readyz + port: 8081 + scheme: HTTP + initialDelaySeconds: 5 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 5 + resources: + {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true +--- +# Source: kube-prometheus-stack/templates/prometheus-operator/deployment.yaml +apiVersion: apps/v1 +kind: Deployment +metadata: + name: kube-prometheus-stack-1754-operator + namespace: prometheus + labels: + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + app: kube-prometheus-stack-operator + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/component: prometheus-operator +spec: + replicas: 1 + revisionHistoryLimit: 10 + selector: + matchLabels: + app: kube-prometheus-stack-operator + release: "kube-prometheus-stack-1754164871" + template: + metadata: + labels: + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + app: kube-prometheus-stack-operator + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/component: prometheus-operator + spec: + containers: + - name: kube-prometheus-stack + image: "quay.io/prometheus-operator/prometheus-operator:v0.83.0" + imagePullPolicy: "IfNotPresent" + args: + - --kubelet-service=kube-system/kube-prometheus-stack-1754-kubelet + - --kubelet-endpoints=true + - --kubelet-endpointslice=false + - --localhost=127.0.0.1 + - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0 + - --config-reloader-cpu-request=0 + - --config-reloader-cpu-limit=0 + - --config-reloader-memory-request=0 + - --config-reloader-memory-limit=0 + - --thanos-default-base-image=quay.io/thanos/thanos:v0.39.2 + - --secret-field-selector=type!=kubernetes.io/dockercfg,type!=kubernetes.io/service-account-token,type!=helm.sh/release.v1 + - --web.enable-tls=true + - --web.cert-file=/cert/cert + - --web.key-file=/cert/key + - --web.listen-address=:10250 + - --web.tls-min-version=VersionTLS13 + ports: + - containerPort: 10250 + name: https + env: + - name: GOGC + value: "30" + resources: + {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + volumeMounts: + - name: tls-secret + mountPath: /cert + readOnly: true + readinessProbe: + httpGet: + path: /healthz + port: https + scheme: HTTPS + initialDelaySeconds: 0 + periodSeconds: 10 + timeoutSeconds: 1 + successThreshold: 1 + failureThreshold: 3 + livenessProbe: + httpGet: + path: /healthz + port: https + scheme: HTTPS + initialDelaySeconds: 0 + periodSeconds: 10 + timeoutSeconds: 1 + successThreshold: 1 + failureThreshold: 3 + volumes: + - name: tls-secret + secret: + defaultMode: 420 + secretName: kube-prometheus-stack-1754-admission + securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + seccompProfile: + type: RuntimeDefault + serviceAccountName: kube-prometheus-stack-1754-operator + automountServiceAccountToken: true + terminationGracePeriodSeconds: 30 +--- +# Source: kube-prometheus-stack/templates/alertmanager/alertmanager.yaml +apiVersion: monitoring.coreos.com/v1 +kind: Alertmanager +metadata: + name: kube-prometheus-stack-1754-alertmanager + namespace: prometheus + labels: + app: kube-prometheus-stack-alertmanager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + image: "quay.io/prometheus/alertmanager:v0.28.1" + imagePullPolicy: "IfNotPresent" + version: v0.28.1 + replicas: 1 + listenLocal: false + serviceAccountName: kube-prometheus-stack-1754-alertmanager + automountServiceAccountToken: true + externalUrl: http://kube-prometheus-stack-1754-alertmanager.prometheus:9093 + paused: false + logFormat: "logfmt" + logLevel: "info" + retention: "120h" + alertmanagerConfigSelector: {} + alertmanagerConfigNamespaceSelector: + {} + routePrefix: "/" + securityContext: + fsGroup: 2000 + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + seccompProfile: + type: RuntimeDefault + affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + topologyKey: kubernetes.io/hostname + labelSelector: + matchExpressions: + - {key: app.kubernetes.io/name, operator: In, values: [alertmanager]} + - {key: alertmanager, operator: In, values: [kube-prometheus-stack-1754-alertmanager]} + portName: http-web +--- +# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/mutatingWebhookConfiguration.yaml +apiVersion: admissionregistration.k8s.io/v1 +kind: MutatingWebhookConfiguration +metadata: + name: kube-prometheus-stack-1754-admission + annotations: + + labels: + app: kube-prometheus-stack-admission + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/component: prometheus-operator-webhook +webhooks: + - name: prometheusrulemutate.monitoring.coreos.com + failurePolicy: Ignore + rules: + - apiGroups: + - monitoring.coreos.com + apiVersions: + - "*" + resources: + - prometheusrules + operations: + - CREATE + - UPDATE + clientConfig: + service: + namespace: prometheus + name: kube-prometheus-stack-1754-operator + path: /admission-prometheusrules/mutate + timeoutSeconds: 10 + admissionReviewVersions: ["v1", "v1beta1"] + sideEffects: None +--- +# Source: kube-prometheus-stack/templates/prometheus/prometheus.yaml +apiVersion: monitoring.coreos.com/v1 +kind: Prometheus +metadata: + name: kube-prometheus-stack-1754-prometheus + namespace: prometheus + labels: + app: kube-prometheus-stack-prometheus + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + automountServiceAccountToken: true + alerting: + alertmanagers: + - namespace: prometheus + name: kube-prometheus-stack-1754-alertmanager + port: http-web + pathPrefix: "/" + apiVersion: v2 + image: "quay.io/prometheus/prometheus:v3.5.0" + imagePullPolicy: "IfNotPresent" + version: v3.5.0 + externalUrl: http://kube-prometheus-stack-1754-prometheus.prometheus:9090 + paused: false + replicas: 1 + shards: 1 + logLevel: info + logFormat: logfmt + listenLocal: false + enableOTLPReceiver: false + enableAdminAPI: false + retention: "10d" + tsdb: + outOfOrderTimeWindow: 0s + walCompression: true + routePrefix: "/" + serviceAccountName: kube-prometheus-stack-1754-prometheus + serviceMonitorSelector: {} + serviceMonitorNamespaceSelector: {} + podMonitorSelector: + matchLabels: + release: "kube-prometheus-stack-1754164871" + + podMonitorNamespaceSelector: {} + probeSelector: + matchLabels: + release: "kube-prometheus-stack-1754164871" + + probeNamespaceSelector: {} + securityContext: + fsGroup: 2000 + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + seccompProfile: + type: RuntimeDefault + ruleNamespaceSelector: {} + ruleSelector: + matchLabels: + release: "kube-prometheus-stack-1754164871" + + scrapeConfigSelector: + matchLabels: + release: "kube-prometheus-stack-1754164871" + + scrapeConfigNamespaceSelector: {} + affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + topologyKey: kubernetes.io/hostname + labelSelector: + matchExpressions: + - {key: app.kubernetes.io/name, operator: In, values: [prometheus]} + - {key: app.kubernetes.io/instance, operator: In, values: [kube-prometheus-stack-1754-prometheus]} + portName: http-web + hostNetwork: false +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-alertmanager.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: alertmanager.rules + rules: + - alert: AlertmanagerFailedReload + annotations: + description: Configuration has failed to load for {{ $labels.namespace }}/{{ $labels.pod}}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedreload + summary: Reloading an Alertmanager configuration has failed. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(alertmanager_config_last_reload_successful{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus"}[5m]) == 0 + for: 10m + labels: + severity: critical + - alert: AlertmanagerMembersInconsistent + annotations: + description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has only found {{ $value }} members of the {{$labels.job}} cluster. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagermembersinconsistent + summary: A member of an Alertmanager cluster has not found all other cluster members. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(alertmanager_cluster_members{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus"}[5m]) + < on (namespace,service,cluster) group_left + count by (namespace,service,cluster) (max_over_time(alertmanager_cluster_members{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus"}[5m])) + for: 15m + labels: + severity: critical + - alert: AlertmanagerFailedToSendAlerts + annotations: + description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedtosendalerts + summary: An Alertmanager instance failed to send notifications. + expr: |- + ( + rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus"}[15m]) + / + ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus"}[15m]) + ) + > 0.01 + for: 5m + labels: + severity: warning + - alert: AlertmanagerClusterFailedToSendAlerts + annotations: + description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts + summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration. + expr: |- + min by (namespace,service, integration) ( + rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus", integration=~`.*`}[15m]) + / + ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus", integration=~`.*`}[15m]) + ) + > 0.01 + for: 5m + labels: + severity: critical + - alert: AlertmanagerClusterFailedToSendAlerts + annotations: + description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts + summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration. + expr: |- + min by (namespace,service, integration) ( + rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus", integration!~`.*`}[15m]) + / + ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus", integration!~`.*`}[15m]) + ) + > 0.01 + for: 5m + labels: + severity: warning + - alert: AlertmanagerConfigInconsistent + annotations: + description: Alertmanager instances within the {{$labels.job}} cluster have different configurations. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerconfiginconsistent + summary: Alertmanager instances within the same cluster have different configurations. + expr: |- + count by (namespace,service,cluster) ( + count_values by (namespace,service,cluster) ("config_hash", alertmanager_config_hash{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus"}) + ) + != 1 + for: 20m + labels: + severity: critical + - alert: AlertmanagerClusterDown + annotations: + description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have been up for less than half of the last 5m.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterdown + summary: Half or more of the Alertmanager instances within the same cluster are down. + expr: |- + ( + count by (namespace,service,cluster) ( + avg_over_time(up{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus"}[5m]) < 0.5 + ) + / + count by (namespace,service,cluster) ( + up{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus"} + ) + ) + >= 0.5 + for: 5m + labels: + severity: critical + - alert: AlertmanagerClusterCrashlooping + annotations: + description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have restarted at least 5 times in the last 10m.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclustercrashlooping + summary: Half or more of the Alertmanager instances within the same cluster are crashlooping. + expr: |- + ( + count by (namespace,service,cluster) ( + changes(process_start_time_seconds{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus"}[10m]) > 4 + ) + / + count by (namespace,service,cluster) ( + up{job="kube-prometheus-stack-1754-alertmanager",namespace="prometheus"} + ) + ) + >= 0.5 + for: 5m + labels: + severity: critical +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/config-reloaders.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-config-reloaders + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: config-reloaders + rules: + - alert: ConfigReloaderSidecarErrors + annotations: + description: 'Errors encountered while the {{$labels.pod}} config-reloader sidecar attempts to sync config in {{$labels.namespace}} namespace. + + As a result, configuration for service running in {{$labels.pod}} may be stale and cannot be updated anymore.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/configreloadersidecarerrors + summary: config-reloader sidecar has not had a successful reload for 10m + expr: max_over_time(reloader_last_reload_successful{namespace=~".+"}[5m]) == 0 + for: 10m + labels: + severity: warning +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-etcd + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: etcd + rules: + - alert: etcdMembersDown + annotations: + description: 'etcd cluster "{{ $labels.job }}": members are down ({{ $value }}).' + summary: etcd cluster members are down. + expr: |- + max without (endpoint) ( + sum without (instance, pod) (up{job=~".*etcd.*"} == bool 0) + or + count without (To) ( + sum without (instance, pod) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01 + ) + ) + > 0 + for: 20m + labels: + severity: warning + - alert: etcdInsufficientMembers + annotations: + description: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value }}).' + summary: etcd cluster has insufficient number of members. + expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance, pod) < ((count(up{job=~".*etcd.*"}) without (instance, pod) + 1) / 2) + for: 3m + labels: + severity: critical + - alert: etcdNoLeader + annotations: + description: 'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }} has no leader.' + summary: etcd cluster has no leader. + expr: etcd_server_has_leader{job=~".*etcd.*"} == 0 + for: 1m + labels: + severity: critical + - alert: etcdHighNumberOfLeaderChanges + annotations: + description: 'etcd cluster "{{ $labels.job }}": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.' + summary: etcd cluster has high number of leader changes. + expr: increase((max without (instance, pod) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}))[15m:1m]) >= 4 + for: 5m + labels: + severity: warning + - alert: etcdHighNumberOfFailedGRPCRequests + annotations: + description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.' + summary: etcd cluster has high number of failed grpc requests. + expr: |- + 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code) + / + sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code) + > 1 + for: 10m + labels: + severity: warning + - alert: etcdHighNumberOfFailedGRPCRequests + annotations: + description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.' + summary: etcd cluster has high number of failed grpc requests. + expr: |- + 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code) + / + sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code) + > 5 + for: 5m + labels: + severity: critical + - alert: etcdGRPCRequestsSlow + annotations: + description: 'etcd cluster "{{ $labels.job }}": 99th percentile of gRPC requests is {{ $value }}s on etcd instance {{ $labels.instance }} for {{ $labels.grpc_method }} method.' + summary: etcd grpc requests are slow + expr: |- + histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type)) + > 0.15 + for: 10m + labels: + severity: critical + - alert: etcdMemberCommunicationSlow + annotations: + description: 'etcd cluster "{{ $labels.job }}": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.' + summary: etcd cluster member communication is slow. + expr: |- + histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.15 + for: 10m + labels: + severity: warning + - alert: etcdHighNumberOfFailedProposals + annotations: + description: 'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}.' + summary: etcd cluster has high number of proposal failures. + expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5 + for: 15m + labels: + severity: warning + - alert: etcdHighFsyncDurations + annotations: + description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.' + summary: etcd cluster 99th percentile fsync durations are too high. + expr: |- + histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.5 + for: 10m + labels: + severity: warning + - alert: etcdHighFsyncDurations + annotations: + description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.' + summary: etcd cluster 99th percentile fsync durations are too high. + expr: |- + histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 1 + for: 10m + labels: + severity: critical + - alert: etcdHighCommitDurations + annotations: + description: 'etcd cluster "{{ $labels.job }}": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}.' + summary: etcd cluster 99th percentile commit durations are too high. + expr: |- + histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.25 + for: 10m + labels: + severity: warning + - alert: etcdDatabaseQuotaLowSpace + annotations: + description: 'etcd cluster "{{ $labels.job }}": database size exceeds the defined quota on etcd instance {{ $labels.instance }}, please defrag or increase the quota as the writes to etcd will be disabled when it is full.' + summary: etcd cluster database is running full. + expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m]) / last_over_time(etcd_server_quota_backend_bytes{job=~".*etcd.*"}[5m]))*100 > 95 + for: 10m + labels: + severity: critical + - alert: etcdExcessiveDatabaseGrowth + annotations: + description: 'etcd cluster "{{ $labels.job }}": Predicting running out of disk space in the next four hours, based on write observations within the past four hours on etcd instance {{ $labels.instance }}, please check as it might be disruptive.' + summary: etcd cluster database growing very fast. + expr: predict_linear(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[4h], 4*60*60) > etcd_server_quota_backend_bytes{job=~".*etcd.*"} + for: 10m + labels: + severity: warning + - alert: etcdDatabaseHighFragmentationRatio + annotations: + description: 'etcd cluster "{{ $labels.job }}": database size in use on instance {{ $labels.instance }} is {{ $value | humanizePercentage }} of the actual allocated disk space, please run defragmentation (e.g. etcdctl defrag) to retrieve the unused fragmented disk space.' + runbook_url: https://etcd.io/docs/v3.5/op-guide/maintenance/#defragmentation + summary: etcd database size in use is less than 50% of the actual allocated storage. + expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"}[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m])) < 0.5 and etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"} > 104857600 + for: 10m + labels: + severity: warning +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/general.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-general.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: general.rules + rules: + - alert: TargetDown + annotations: + description: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in {{ $labels.namespace }} namespace are down.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/targetdown + summary: One or more targets are unreachable. + expr: 100 * (count(up == 0) BY (cluster, job, namespace, service) / count(up) BY (cluster, job, namespace, service)) > 10 + for: 10m + labels: + severity: warning + - alert: Watchdog + annotations: + description: 'This is an alert meant to ensure that the entire alerting pipeline is functional. + + This alert is always firing, therefore it should always be firing in Alertmanager + + and always fire against a receiver. There are integrations with various notification + + mechanisms that send a notification when this alert is not firing. For example the + + "DeadMansSnitch" integration in PagerDuty. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog + summary: An alert that should always be firing to certify that Alertmanager is working properly. + expr: vector(1) + labels: + severity: none + - alert: InfoInhibitor + annotations: + description: 'This is an alert that is used to inhibit info alerts. + + By themselves, the info-level alerts are sometimes very noisy, but they are relevant when combined with + + other alerts. + + This alert fires whenever there''s a severity="info" alert, and stops firing when another alert with a + + severity of ''warning'' or ''critical'' starts firing on the same namespace. + + This alert should be routed to a null receiver and configured to inhibit alerts with severity="info". + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor + summary: Info-level alert inhibition. + expr: ALERTS{severity = "info"} == 1 unless on (namespace) ALERTS{alertname != "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} == 1 + labels: + severity: none +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_cpu_usage_seconds_total.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-k8s.rules.container-cpu-usage-second + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_cpu_usage_seconds_total + rules: + - expr: |- + sum by (cluster, namespace, pod, container) ( + rate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m]) + ) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) ( + 1, max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m + - expr: |- + sum by (cluster, namespace, pod, container) ( + irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m]) + ) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) ( + 1, max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_cache.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-k8s.rules.container-memory-cache + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_memory_cache + rules: + - expr: |- + container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1, + max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_cache +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_rss.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-k8s.rules.container-memory-rss + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_memory_rss + rules: + - expr: |- + container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1, + max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_rss +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_swap.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-k8s.rules.container-memory-swap + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_memory_swap + rules: + - expr: |- + container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1, + max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_swap +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_working_set_bytes.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-k8s.rules.container-memory-working-s + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_memory_working_set_bytes + rules: + - expr: |- + container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1, + max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_working_set_bytes +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_resource.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-k8s.rules.container-resource + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_resource + rules: + - expr: |- + kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} + ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_memory:kube_pod_container_resource_requests:sum + - expr: |- + kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} + ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_cpu:kube_pod_container_resource_requests:sum + - expr: |- + kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} + ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_memory:kube_pod_container_resource_limits:sum + - expr: |- + kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} + ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_cpu:kube_pod_container_resource_limits:sum +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.pod_owner.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-k8s.rules.pod-owner + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.pod_owner + rules: + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"}, + "replicaset", "$1", "owner_name", "(.*)" + ) * on (cluster, replicaset, namespace) group_left(owner_name) topk by (cluster, replicaset, namespace) ( + 1, max by (cluster, replicaset, namespace, owner_name) ( + kube_replicaset_owner{job="kube-state-metrics", owner_kind=""} + ) + ), + "workload", "$1", "replicaset", "(.*)" + ) + ) + labels: + workload_type: replicaset + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"}, + "replicaset", "$1", "owner_name", "(.*)" + ) * on (replicaset, namespace, cluster) group_left(owner_name) topk by (cluster, replicaset, namespace) ( + 1, max by (cluster, replicaset, namespace, owner_name) ( + kube_replicaset_owner{job="kube-state-metrics", owner_kind="Deployment"} + ) + ), + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: deployment + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: daemonset + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"}, + "workload", "$1", "owner_name", "(.*)") + ) + labels: + workload_type: statefulset + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + group by (cluster, namespace, workload, pod) ( + label_join( + group by (cluster, namespace, job_name, pod, owner_name) ( + label_join( + kube_pod_owner{job="kube-state-metrics", owner_kind="Job"} + , "job_name", "", "owner_name") + ) + * on (cluster, namespace, job_name) group_left() + group by (cluster, namespace, job_name) ( + kube_job_owner{job="kube-state-metrics", owner_kind=~"Pod|"} + ) + , "workload", "", "owner_name") + ) + labels: + workload_type: job + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="", owner_name=""}, + "workload", "$1", "pod", "(.+)") + ) + labels: + workload_type: barepod + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="Node"}, + "workload", "$1", "pod", "(.+)") + ) + labels: + workload_type: staticpod + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + group by (cluster, namespace, workload, workload_type, pod) ( + label_join( + label_join( + group by (cluster, namespace, job_name, pod) ( + label_join( + kube_pod_owner{job="kube-state-metrics", owner_kind="Job"} + , "job_name", "", "owner_name") + ) + * on (cluster, namespace, job_name) group_left(owner_kind, owner_name) + group by (cluster, namespace, job_name, owner_kind, owner_name) ( + kube_job_owner{job="kube-state-metrics", owner_kind!="Pod", owner_kind!=""} + ) + , "workload", "", "owner_name") + , "workload_type", "", "owner_kind") + + OR + + label_replace( + label_replace( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"} + , "replicaset", "$1", "owner_name", "(.+)" + ) + * on (cluster, namespace, replicaset) group_left(owner_kind, owner_name) + group by (cluster, namespace, replicaset, owner_kind, owner_name) ( + kube_replicaset_owner{job="kube-state-metrics", owner_kind!="Deployment", owner_kind!=""} + ) + , "workload", "$1", "owner_name", "(.+)") + OR + label_replace( + group by (cluster, namespace, pod, owner_name, owner_kind) ( + kube_pod_owner{job="kube-state-metrics", owner_kind!="ReplicaSet", owner_kind!="DaemonSet", owner_kind!="StatefulSet", owner_kind!="Job", owner_kind!="Node", owner_kind!=""} + ) + , "workload", "$1", "owner_name", "(.+)" + ) + , "workload_type", "$1", "owner_kind", "(.+)") + ) + record: namespace_workload_pod:kube_pod_owner:relabel +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kube-apiserver-availability.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - interval: 3m + name: kube-apiserver-availability.rules + rules: + - expr: avg_over_time(code_verb:apiserver_request_total:increase1h[30d]) * 24 * 30 + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"}) + labels: + verb: read + record: code:apiserver_request_total:increase30d + - expr: sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + labels: + verb: write + record: code:apiserver_request_total:increase30d + - expr: sum by (cluster, verb, scope, le) (increase(apiserver_request_sli_duration_seconds_bucket[1h])) + record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h + - expr: sum by (cluster, verb, scope, le) (avg_over_time(cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h[30d]) * 24 * 30) + record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d + - expr: sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h{le="+Inf"}) + record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h + - expr: sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{le="+Inf"}) + record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d + - expr: |- + 1 - ( + ( + # write too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + - + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le=~"1(\\.0)?"} or vector(0)) + ) + + ( + # read too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"LIST|GET"}) + - + ( + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le=~"1(\\.0)?"} or vector(0)) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le=~"5(\\.0)?"} or vector(0)) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le=~"30(\\.0)?"} or vector(0)) + ) + ) + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d) + labels: + verb: all + record: apiserver_request:availability30d + - expr: |- + 1 - ( + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"LIST|GET"}) + - + ( + # too slow + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le=~"1(\\.0)?"} or vector(0)) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le=~"5(\\.0)?"} or vector(0)) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le=~"30(\\.0)?"} or vector(0)) + ) + + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d{verb="read"}) + labels: + verb: read + record: apiserver_request:availability30d + - expr: |- + 1 - ( + ( + # too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + - + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le=~"1(\\.0)?"} or vector(0)) + ) + + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d{verb="write"}) + labels: + verb: write + record: apiserver_request:availability30d + - expr: sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m])) + labels: + verb: read + record: code_resource:apiserver_request_total:rate5m + - expr: sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) + labels: + verb: write + record: code_resource:apiserver_request_total:rate5m + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"2.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"3.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"4.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) + record: code_verb:apiserver_request_total:increase1h +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kube-apiserver-burnrate.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kube-apiserver-burnrate.rules + rules: + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1d])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[1d])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[1d])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[1d])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d])) + labels: + verb: read + record: apiserver_request:burnrate1d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[1h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[1h])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[1h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h])) + labels: + verb: read + record: apiserver_request:burnrate1h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[2h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[2h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[2h])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[2h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[2h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h])) + labels: + verb: read + record: apiserver_request:burnrate2h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[30m])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[30m])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[30m])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[30m])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m])) + labels: + verb: read + record: apiserver_request:burnrate30m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[3d])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[3d])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[3d])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[3d])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[3d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d])) + labels: + verb: read + record: apiserver_request:burnrate3d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[5m])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[5m])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[5m])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m])) + labels: + verb: read + record: apiserver_request:burnrate5m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[6h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[6h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[6h])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[6h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h])) + labels: + verb: read + record: apiserver_request:burnrate6h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1d])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[1d])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d])) + labels: + verb: write + record: apiserver_request:burnrate1d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1h])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[1h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h])) + labels: + verb: write + record: apiserver_request:burnrate1h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[2h])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[2h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h])) + labels: + verb: write + record: apiserver_request:burnrate2h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[30m])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[30m])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m])) + labels: + verb: write + record: apiserver_request:burnrate30m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[3d])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[3d])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d])) + labels: + verb: write + record: apiserver_request:burnrate3d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[5m])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) + labels: + verb: write + record: apiserver_request:burnrate5m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[6h])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[6h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h])) + labels: + verb: write + record: apiserver_request:burnrate6h +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-histogram.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kube-apiserver-histogram.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kube-apiserver-histogram.rules + rules: + - expr: histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 + labels: + quantile: '0.99' + verb: read + record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 + labels: + quantile: '0.99' + verb: write + record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kube-apiserver-slos + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kube-apiserver-slos + rules: + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum by (cluster) (apiserver_request:burnrate1h) > (14.40 * 0.01000) + and on (cluster) + sum by (cluster) (apiserver_request:burnrate5m) > (14.40 * 0.01000) + for: 2m + labels: + long: 1h + severity: critical + short: 5m + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum by (cluster) (apiserver_request:burnrate6h) > (6.00 * 0.01000) + and on (cluster) + sum by (cluster) (apiserver_request:burnrate30m) > (6.00 * 0.01000) + for: 15m + labels: + long: 6h + severity: critical + short: 30m + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum by (cluster) (apiserver_request:burnrate1d) > (3.00 * 0.01000) + and on (cluster) + sum by (cluster) (apiserver_request:burnrate2h) > (3.00 * 0.01000) + for: 1h + labels: + long: 1d + severity: warning + short: 2h + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum by (cluster) (apiserver_request:burnrate3d) > (1.00 * 0.01000) + and on (cluster) + sum by (cluster) (apiserver_request:burnrate6h) > (1.00 * 0.01000) + for: 3h + labels: + long: 3d + severity: warning + short: 6h +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-general.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kube-prometheus-general.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kube-prometheus-general.rules + rules: + - expr: count without(instance, pod, node) (up == 1) + record: count:up1 + - expr: count without(instance, pod, node) (up == 0) + record: count:up0 +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-node-recording.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kube-prometheus-node-recording.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kube-prometheus-node-recording.rules + rules: + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY (instance) + record: instance:node_cpu:rate:sum + - expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance) + record: instance:node_network_receive_bytes:rate:sum + - expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance) + record: instance:node_network_transmit_bytes:rate:sum + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT (cpu, mode) / ON (instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance) + record: instance:node_cpu:ratio + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) + record: cluster:node_cpu:sum_rate5m + - expr: cluster:node_cpu:sum_rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu)) + record: cluster:node_cpu:ratio +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-scheduler.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kube-scheduler.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kube-scheduler.rules + rules: + - expr: histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-state-metrics.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kube-state-metrics + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kube-state-metrics + rules: + - alert: KubeStateMetricsListErrors + annotations: + description: kube-state-metrics is experiencing errors at an elevated rate in list operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricslisterrors + summary: kube-state-metrics is experiencing errors in list operations. + expr: |- + (sum(rate(kube_state_metrics_list_total{job="kube-state-metrics",result="error"}[5m])) by (cluster) + / + sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])) by (cluster)) + > 0.01 + for: 15m + labels: + severity: critical + - alert: KubeStateMetricsWatchErrors + annotations: + description: kube-state-metrics is experiencing errors at an elevated rate in watch operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricswatcherrors + summary: kube-state-metrics is experiencing errors in watch operations. + expr: |- + (sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics",result="error"}[5m])) by (cluster) + / + sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])) by (cluster)) + > 0.01 + for: 15m + labels: + severity: critical + - alert: KubeStateMetricsShardingMismatch + annotations: + description: kube-state-metrics pods are running with different --total-shards configuration, some Kubernetes objects may be exposed multiple times or not exposed at all. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricsshardingmismatch + summary: kube-state-metrics sharding is misconfigured. + expr: stdvar (kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) != 0 + for: 15m + labels: + severity: critical + - alert: KubeStateMetricsShardsMissing + annotations: + description: kube-state-metrics shards are missing, some Kubernetes objects are not being exposed. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricsshardsmissing + summary: kube-state-metrics shards are missing. + expr: |- + 2^max(kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) - 1 + - + sum( 2 ^ max by (cluster, shard_ordinal) (kube_state_metrics_shard_ordinal{job="kube-state-metrics"}) ) by (cluster) + != 0 + for: 15m + labels: + severity: critical +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubelet.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kubelet.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kubelet.rules + rules: + - expr: |- + histogram_quantile( + 0.99, + sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) + * on (cluster, instance) group_left (node) + max by (cluster, instance, node) (kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + ) + labels: + quantile: '0.99' + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile + - expr: |- + histogram_quantile( + 0.9, + sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) + * on (cluster, instance) group_left (node) + max by (cluster, instance, node) (kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + ) + labels: + quantile: '0.9' + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile + - expr: |- + histogram_quantile( + 0.5, + sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) + * on (cluster, instance) group_left (node) + max by (cluster, instance, node) (kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + ) + labels: + quantile: '0.5' + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-apps.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kubernetes-apps + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kubernetes-apps + rules: + - alert: KubePodCrashLooping + annotations: + description: 'Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is in waiting state (reason: "CrashLoopBackOff") on cluster {{ $labels.cluster }}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping + summary: Pod is crash looping. + expr: max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff", job="kube-state-metrics", namespace=~".*"}[5m]) >= 1 + for: 15m + labels: + severity: warning + - alert: KubePodNotReady + annotations: + description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodnotready + summary: Pod has been in a non-ready state for more than 15 minutes. + expr: |- + sum by (namespace, pod, cluster) ( + max by (namespace, pod, cluster) ( + kube_pod_status_phase{job="kube-state-metrics", namespace=~".*", phase=~"Pending|Unknown|Failed"} + ) * on (namespace, pod, cluster) group_left(owner_kind) topk by (namespace, pod, cluster) ( + 1, max by (namespace, pod, owner_kind, cluster) (kube_pod_owner{owner_kind!="Job"}) + ) + ) > 0 + for: 15m + labels: + severity: warning + - alert: KubeDeploymentGenerationMismatch + annotations: + description: Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentgenerationmismatch + summary: Deployment generation mismatch due to possible roll-back + expr: |- + kube_deployment_status_observed_generation{job="kube-state-metrics", namespace=~".*"} + != + kube_deployment_metadata_generation{job="kube-state-metrics", namespace=~".*"} + for: 15m + labels: + severity: warning + - alert: KubeDeploymentReplicasMismatch + annotations: + description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch + summary: Deployment has not matched the expected number of replicas. + expr: |- + ( + kube_deployment_spec_replicas{job="kube-state-metrics", namespace=~".*"} + > + kube_deployment_status_replicas_available{job="kube-state-metrics", namespace=~".*"} + ) and ( + changes(kube_deployment_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}[10m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeDeploymentRolloutStuck + annotations: + description: Rollout of deployment {{ $labels.namespace }}/{{ $labels.deployment }} is not progressing for longer than 15 minutes on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentrolloutstuck + summary: Deployment rollout is not progressing. + expr: |- + kube_deployment_status_condition{condition="Progressing", status="false",job="kube-state-metrics", namespace=~".*"} + != 0 + for: 15m + labels: + severity: warning + - alert: KubeStatefulSetReplicasMismatch + annotations: + description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetreplicasmismatch + summary: StatefulSet has not matched the expected number of replicas. + expr: |- + ( + kube_statefulset_status_replicas_ready{job="kube-state-metrics", namespace=~".*"} + != + kube_statefulset_replicas{job="kube-state-metrics", namespace=~".*"} + ) and ( + changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}[10m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeStatefulSetGenerationMismatch + annotations: + description: StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetgenerationmismatch + summary: StatefulSet generation mismatch due to possible roll-back + expr: |- + kube_statefulset_status_observed_generation{job="kube-state-metrics", namespace=~".*"} + != + kube_statefulset_metadata_generation{job="kube-state-metrics", namespace=~".*"} + for: 15m + labels: + severity: warning + - alert: KubeStatefulSetUpdateNotRolledOut + annotations: + description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetupdatenotrolledout + summary: StatefulSet update has not been rolled out. + expr: |- + ( + max by (namespace, statefulset, job, cluster) ( + kube_statefulset_status_current_revision{job="kube-state-metrics", namespace=~".*"} + unless + kube_statefulset_status_update_revision{job="kube-state-metrics", namespace=~".*"} + ) + * on (namespace, statefulset, job, cluster) + ( + kube_statefulset_replicas{job="kube-state-metrics", namespace=~".*"} + != + kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~".*"} + ) + ) and on (namespace, statefulset, job, cluster) ( + changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}[5m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeDaemonSetRolloutStuck + annotations: + description: DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15m on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetrolloutstuck + summary: DaemonSet rollout is stuck. + expr: |- + ( + ( + kube_daemonset_status_current_number_scheduled{job="kube-state-metrics", namespace=~".*"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"} + ) or ( + kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~".*"} + != + 0 + ) or ( + kube_daemonset_status_updated_number_scheduled{job="kube-state-metrics", namespace=~".*"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"} + ) or ( + kube_daemonset_status_number_available{job="kube-state-metrics", namespace=~".*"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"} + ) + ) and ( + changes(kube_daemonset_status_updated_number_scheduled{job="kube-state-metrics", namespace=~".*"}[5m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeContainerWaiting + annotations: + description: 'pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason: "{{ $labels.reason }}") on cluster {{ $labels.cluster }}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting + summary: Pod container waiting longer than 1 hour + expr: kube_pod_container_status_waiting_reason{reason!="CrashLoopBackOff", job="kube-state-metrics", namespace=~".*"} > 0 + for: 1h + labels: + severity: warning + - alert: KubeDaemonSetNotScheduled + annotations: + description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled on cluster {{ $labels.cluster }}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetnotscheduled + summary: DaemonSet pods are not scheduled. + expr: |- + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"} + - + kube_daemonset_status_current_number_scheduled{job="kube-state-metrics", namespace=~".*"} > 0 + for: 10m + labels: + severity: warning + - alert: KubeDaemonSetMisScheduled + annotations: + description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run on cluster {{ $labels.cluster }}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetmisscheduled + summary: DaemonSet pods are misscheduled. + expr: kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~".*"} > 0 + for: 15m + labels: + severity: warning + - alert: KubeJobNotCompleted + annotations: + description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than {{ "43200" | humanizeDuration }} to complete on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted + summary: Job did not complete in time + expr: |- + time() - max by (namespace, job_name, cluster) (kube_job_status_start_time{job="kube-state-metrics", namespace=~".*"} + and + kube_job_status_active{job="kube-state-metrics", namespace=~".*"} > 0) > 43200 + labels: + severity: warning + - alert: KubeJobFailed + annotations: + description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobfailed + summary: Job failed to complete. + expr: kube_job_failed{job="kube-state-metrics", namespace=~".*"} > 0 + for: 15m + labels: + severity: warning + - alert: KubeHpaReplicasMismatch + annotations: + description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has not matched the desired number of replicas for longer than 15 minutes on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpareplicasmismatch + summary: HPA has not matched desired number of replicas. + expr: |- + (kube_horizontalpodautoscaler_status_desired_replicas{job="kube-state-metrics", namespace=~".*"} + != + kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"}) + and + (kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"} + > + kube_horizontalpodautoscaler_spec_min_replicas{job="kube-state-metrics", namespace=~".*"}) + and + (kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"} + < + kube_horizontalpodautoscaler_spec_max_replicas{job="kube-state-metrics", namespace=~".*"}) + and + changes(kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"}[15m]) == 0 + for: 15m + labels: + severity: warning + - alert: KubeHpaMaxedOut + annotations: + description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has been running at max replicas for longer than 15 minutes on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpamaxedout + summary: HPA is running at max replicas + expr: |- + kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"} + == + kube_horizontalpodautoscaler_spec_max_replicas{job="kube-state-metrics", namespace=~".*"} + for: 15m + labels: + severity: warning + - alert: KubePdbNotEnoughHealthyPods + annotations: + description: PDB {{ $labels.cluster }}/{{ $labels.namespace }}/{{ $labels.poddisruptionbudget }} expects {{ $value }} more healthy pods. The desired number of healthy pods has not been met for at least 15m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepdbnotenoughhealthypods + summary: PDB does not have enough healthy pods. + expr: |- + ( + kube_poddisruptionbudget_status_desired_healthy{job="kube-state-metrics", namespace=~".*"} + - + kube_poddisruptionbudget_status_current_healthy{job="kube-state-metrics", namespace=~".*"} + ) + > 0 + for: 15m + labels: + severity: warning +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kubernetes-resources + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kubernetes-resources + rules: + - alert: KubeCPUOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Pods by {{ printf "%.2f" $value }} CPU shares and cannot tolerate node failure. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit + summary: Cluster has overcommitted CPU resource requests. + expr: |- + sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0 + and + (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0 + for: 10m + labels: + severity: warning + - alert: KubeMemoryOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node failure. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit + summary: Cluster has overcommitted memory resource requests. + expr: |- + sum(namespace_memory:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0 + and + (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0 + for: 10m + labels: + severity: warning + - alert: KubeCPUQuotaOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Namespaces. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit + summary: Cluster has overcommitted CPU resource requests. + expr: |- + sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"})) by (cluster) + / + sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) by (cluster) + > 1.5 + for: 5m + labels: + severity: warning + - alert: KubeMemoryQuotaOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Namespaces. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit + summary: Cluster has overcommitted memory resource requests. + expr: |- + sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"})) by (cluster) + / + sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) + > 1.5 + for: 5m + labels: + severity: warning + - alert: KubeQuotaAlmostFull + annotations: + description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull + summary: Namespace quota is going to be full. + expr: |- + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + > 0.9 < 1 + for: 15m + labels: + severity: info + - alert: KubeQuotaFullyUsed + annotations: + description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused + summary: Namespace quota is fully used. + expr: |- + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + == 1 + for: 15m + labels: + severity: info + - alert: KubeQuotaExceeded + annotations: + description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded + summary: Namespace quota has exceeded the limits. + expr: |- + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + > 1 + for: 15m + labels: + severity: warning + - alert: CPUThrottlingHigh + annotations: + description: '{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }} on cluster {{ $labels.cluster }}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh + summary: Processes experience elevated CPU throttling. + expr: |- + sum(increase(container_cpu_cfs_throttled_periods_total{container!="", job="kubelet", metrics_path="/metrics/cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) + / on (cluster, namespace, pod, container, instance) group_left + sum(increase(container_cpu_cfs_periods_total{job="kubelet", metrics_path="/metrics/cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) + > ( 25 / 100 ) + for: 15m + labels: + severity: info +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-storage.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kubernetes-storage + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kubernetes-storage + rules: + - alert: KubePersistentVolumeFillingUp + annotations: + description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster {{ . }} {{- end }} is only {{ $value | humanizePercentage }} free. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup + summary: PersistentVolume is filling up. + expr: |- + ( + kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + / + kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + ) < 0.03 + and + kubelet_volume_stats_used_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1m + labels: + severity: critical + - alert: KubePersistentVolumeFillingUp + annotations: + description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster {{ . }} {{- end }} is expected to fill up within four days. Currently {{ $value | humanizePercentage }} is available. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup + summary: PersistentVolume is filling up. + expr: |- + ( + kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + / + kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + ) < 0.15 + and + kubelet_volume_stats_used_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0 + and + predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1h + labels: + severity: warning + - alert: KubePersistentVolumeInodesFillingUp + annotations: + description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster {{ . }} {{- end }} only has {{ $value | humanizePercentage }} free inodes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup + summary: PersistentVolumeInodes are filling up. + expr: |- + ( + kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"} + / + kubelet_volume_stats_inodes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + ) < 0.03 + and + kubelet_volume_stats_inodes_used{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1m + labels: + severity: critical + - alert: KubePersistentVolumeInodesFillingUp + annotations: + description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster {{ . }} {{- end }} is expected to run out of inodes within four days. Currently {{ $value | humanizePercentage }} of its inodes are free. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup + summary: PersistentVolumeInodes are filling up. + expr: |- + ( + kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"} + / + kubelet_volume_stats_inodes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + ) < 0.15 + and + kubelet_volume_stats_inodes_used{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0 + and + predict_linear(kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1h + labels: + severity: warning + - alert: KubePersistentVolumeErrors + annotations: + description: The persistent volume {{ $labels.persistentvolume }} {{ with $labels.cluster -}} on Cluster {{ . }} {{- end }} has status {{ $labels.phase }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeerrors + summary: PersistentVolume is having issues with provisioning. + expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0 + for: 5m + labels: + severity: critical +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-apiserver.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kubernetes-system-apiserver + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system-apiserver + rules: + - alert: KubeClientCertificateExpiration + annotations: + description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 7.0 days on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration + summary: Client certificate is about to expire. + expr: |- + histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800 + and + on (job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 + for: 5m + labels: + severity: warning + - alert: KubeClientCertificateExpiration + annotations: + description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 24.0 hours on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration + summary: Client certificate is about to expire. + expr: |- + histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400 + and + on (job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 + for: 5m + labels: + severity: critical + - alert: KubeAggregatedAPIErrors + annotations: + description: Kubernetes aggregated API {{ $labels.instance }}/{{ $labels.name }} has reported {{ $labels.reason }} errors on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors + summary: Kubernetes aggregated API has reported errors. + expr: sum by (cluster, instance, name, reason)(increase(aggregator_unavailable_apiservice_total{job="apiserver"}[1m])) > 0 + for: 10m + labels: + severity: warning + - alert: KubeAggregatedAPIDown + annotations: + description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown + summary: Kubernetes aggregated API is down. + expr: (1 - max by (name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice{job="apiserver"}[10m]))) * 100 < 85 + for: 5m + labels: + severity: warning + - alert: KubeAPIDown + annotations: + description: KubeAPI has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapidown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="apiserver"} == 1) + for: 15m + labels: + severity: critical + - alert: KubeAPITerminatedRequests + annotations: + description: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapiterminatedrequests + summary: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests. + expr: sum by (cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum by (cluster) (rate(apiserver_request_total{job="apiserver"}[10m])) + sum by (cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20 + for: 5m + labels: + severity: warning +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-controller-manager.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kubernetes-system-controller-manager + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system-controller-manager + rules: + - alert: KubeControllerManagerDown + annotations: + description: KubeControllerManager has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontrollermanagerdown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kube-controller-manager"} == 1) + for: 15m + labels: + severity: critical +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kube-proxy.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kubernetes-system-kube-proxy + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system-kube-proxy + rules: + - alert: KubeProxyDown + annotations: + description: KubeProxy has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeproxydown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kube-proxy"} == 1) + for: 15m + labels: + severity: critical +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kubernetes-system-kubelet + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system-kubelet + rules: + - alert: KubeNodeNotReady + annotations: + description: '{{ $labels.node }} has been unready for more than 15 minutes on cluster {{ $labels.cluster }}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodenotready + summary: Node is not ready. + expr: |- + kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0 + and on (cluster, node) + kube_node_spec_unschedulable{job="kube-state-metrics"} == 0 + for: 15m + labels: + severity: warning + - alert: KubeNodePressure + annotations: + description: '{{ $labels.node }} on cluster {{ $labels.cluster }} has active Condition {{ $labels.condition }}. This is caused by resource usage exceeding eviction thresholds.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodepressure + summary: Node has as active Condition. + expr: |- + kube_node_status_condition{job="kube-state-metrics",condition=~"(MemoryPressure|DiskPressure|PIDPressure)",status="true"} == 1 + and on (cluster, node) + kube_node_spec_unschedulable{job="kube-state-metrics"} == 0 + for: 10m + labels: + severity: info + - alert: KubeNodeUnreachable + annotations: + description: '{{ $labels.node }} is unreachable and some workloads may be rescheduled on cluster {{ $labels.cluster }}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodeunreachable + summary: Node is unreachable. + expr: (kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} unless ignoring(key,value) kube_node_spec_taint{job="kube-state-metrics",key=~"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn"}) == 1 + for: 15m + labels: + severity: warning + - alert: KubeletTooManyPods + annotations: + description: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods + summary: Kubelet is running at capacity. + expr: |- + ( + max by (cluster, instance) ( + kubelet_running_pods{job="kubelet", metrics_path="/metrics"} > 1 + ) + * on (cluster, instance) group_left(node) + max by (cluster, instance, node) ( + kubelet_node_name{job="kubelet", metrics_path="/metrics"} + ) + ) + / on (cluster, node) group_left() + max by (cluster, node) ( + kube_node_status_capacity{job="kube-state-metrics", resource="pods"} != 1 + ) > 0.95 + for: 15m + labels: + severity: info + - alert: KubeNodeReadinessFlapping + annotations: + description: The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping + summary: Node readiness status is flapping. + expr: |- + sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m])) by (cluster, node) > 2 + and on (cluster, node) + kube_node_spec_unschedulable{job="kube-state-metrics"} == 0 + for: 15m + labels: + severity: warning + - alert: KubeNodeEviction + annotations: + description: Node {{ $labels.node }} on {{ $labels.cluster }} is evicting Pods due to {{ $labels.eviction_signal }}. Eviction occurs when eviction thresholds are crossed, typically caused by Pods exceeding RAM/ephemeral-storage limits. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodeeviction + summary: Node is evicting pods. + expr: |- + sum(rate(kubelet_evictions{job="kubelet", metrics_path="/metrics"}[15m])) by (cluster, eviction_signal, instance) + * on (cluster, instance) group_left(node) + max by (cluster, instance, node) ( + kubelet_node_name{job="kubelet", metrics_path="/metrics"} + ) + > 0 + for: 0s + labels: + severity: info + - alert: KubeletPlegDurationHigh + annotations: + description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }} on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletplegdurationhigh + summary: Kubelet Pod Lifecycle Event Generator is taking too long to relist. + expr: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10 + for: 5m + labels: + severity: warning + - alert: KubeletPodStartUpLatencyHigh + annotations: + description: Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }} on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletpodstartuplatencyhigh + summary: Kubelet Pod startup latency is too high. + expr: histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le)) * on (cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60 + for: 15m + labels: + severity: warning + - alert: KubeletClientCertificateExpiration + annotations: + description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }} on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration + summary: Kubelet client certificate is about to expire. + expr: kubelet_certificate_manager_client_ttl_seconds < 604800 + labels: + severity: warning + - alert: KubeletClientCertificateExpiration + annotations: + description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }} on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration + summary: Kubelet client certificate is about to expire. + expr: kubelet_certificate_manager_client_ttl_seconds < 86400 + labels: + severity: critical + - alert: KubeletServerCertificateExpiration + annotations: + description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }} on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration + summary: Kubelet server certificate is about to expire. + expr: kubelet_certificate_manager_server_ttl_seconds < 604800 + labels: + severity: warning + - alert: KubeletServerCertificateExpiration + annotations: + description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }} on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration + summary: Kubelet server certificate is about to expire. + expr: kubelet_certificate_manager_server_ttl_seconds < 86400 + labels: + severity: critical + - alert: KubeletClientCertificateRenewalErrors + annotations: + description: Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes) on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificaterenewalerrors + summary: Kubelet has failed to renew its client certificate. + expr: increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: KubeletServerCertificateRenewalErrors + annotations: + description: Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes) on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificaterenewalerrors + summary: Kubelet has failed to renew its server certificate. + expr: increase(kubelet_server_expiration_renew_errors[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: KubeletDown + annotations: + description: Kubelet has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletdown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kubelet", metrics_path="/metrics"} == 1) + for: 15m + labels: + severity: critical +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-scheduler.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kubernetes-system-scheduler + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system-scheduler + rules: + - alert: KubeSchedulerDown + annotations: + description: KubeScheduler has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeschedulerdown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kube-scheduler"} == 1) + for: 15m + labels: + severity: critical +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-kubernetes-system + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system + rules: + - alert: KubeVersionMismatch + annotations: + description: There are {{ $value }} different semantic versions of Kubernetes components running on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeversionmismatch + summary: Different semantic versions of Kubernetes components running. + expr: count by (cluster) (count by (git_version, cluster) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"git_version","$1","git_version","(v[0-9]*.[0-9]*).*"))) > 1 + for: 15m + labels: + severity: warning + - alert: KubeClientErrors + annotations: + description: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors on cluster {{ $labels.cluster }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclienterrors + summary: Kubernetes API server client is experiencing errors. + expr: |- + (sum(rate(rest_client_requests_total{job="apiserver",code=~"5.."}[5m])) by (cluster, instance, job, namespace) + / + sum(rate(rest_client_requests_total{job="apiserver"}[5m])) by (cluster, instance, job, namespace)) + > 0.01 + for: 15m + labels: + severity: warning +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-node-exporter.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: node-exporter.rules + rules: + - expr: |- + count without (cpu, mode) ( + node_cpu_seconds_total{job="node-exporter",mode="idle"} + ) + record: instance:node_num_cpu:sum + - expr: |- + 1 - avg without (cpu) ( + sum without (mode) (rate(node_cpu_seconds_total{job="node-exporter", mode=~"idle|iowait|steal"}[5m])) + ) + record: instance:node_cpu_utilisation:rate5m + - expr: |- + ( + node_load1{job="node-exporter"} + / + instance:node_num_cpu:sum{job="node-exporter"} + ) + record: instance:node_load1_per_cpu:ratio + - expr: |- + 1 - ( + ( + node_memory_MemAvailable_bytes{job="node-exporter"} + or + ( + node_memory_Buffers_bytes{job="node-exporter"} + + + node_memory_Cached_bytes{job="node-exporter"} + + + node_memory_MemFree_bytes{job="node-exporter"} + + + node_memory_Slab_bytes{job="node-exporter"} + ) + ) + / + node_memory_MemTotal_bytes{job="node-exporter"} + ) + record: instance:node_memory_utilisation:ratio + - expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m]) + record: instance:node_vmstat_pgmajfault:rate5m + - expr: rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m]) + record: instance_device:node_disk_io_time_seconds:rate5m + - expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m]) + record: instance_device:node_disk_io_time_weighted_seconds:rate5m + - expr: |- + sum without (device) ( + rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_receive_bytes_excluding_lo:rate5m + - expr: |- + sum without (device) ( + rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_transmit_bytes_excluding_lo:rate5m + - expr: |- + sum without (device) ( + rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_receive_drop_excluding_lo:rate5m + - expr: |- + sum without (device) ( + rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_transmit_drop_excluding_lo:rate5m +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-node-exporter + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: node-exporter + rules: + - alert: NodeFilesystemSpaceFillingUp + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup + summary: Filesystem is predicted to run out of space within the next 24 hours. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 15 + and + predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""}[6h], 24*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: warning + - alert: NodeFilesystemSpaceFillingUp + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup + summary: Filesystem is predicted to run out of space within the next 4 hours. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 10 + and + predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""}[6h], 4*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: critical + - alert: NodeFilesystemAlmostOutOfSpace + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace + summary: Filesystem has less than 5% space left. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 5 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 30m + labels: + severity: warning + - alert: NodeFilesystemAlmostOutOfSpace + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace + summary: Filesystem has less than 3% space left. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 3 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 30m + labels: + severity: critical + - alert: NodeFilesystemFilesFillingUp + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup + summary: Filesystem is predicted to run out of inodes within the next 24 hours. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 40 + and + predict_linear(node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""}[6h], 24*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: warning + - alert: NodeFilesystemFilesFillingUp + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup + summary: Filesystem is predicted to run out of inodes within the next 4 hours. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 20 + and + predict_linear(node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""}[6h], 4*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: critical + - alert: NodeFilesystemAlmostOutOfFiles + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles + summary: Filesystem has less than 5% inodes left. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 5 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: warning + - alert: NodeFilesystemAlmostOutOfFiles + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles + summary: Filesystem has less than 3% inodes left. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 3 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: critical + - alert: NodeNetworkReceiveErrs + annotations: + description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworkreceiveerrs + summary: Network interface is reporting many receive errors. + expr: rate(node_network_receive_errs_total{job="node-exporter"}[2m]) / rate(node_network_receive_packets_total{job="node-exporter"}[2m]) > 0.01 + for: 1h + labels: + severity: warning + - alert: NodeNetworkTransmitErrs + annotations: + description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworktransmiterrs + summary: Network interface is reporting many transmit errors. + expr: rate(node_network_transmit_errs_total{job="node-exporter"}[2m]) / rate(node_network_transmit_packets_total{job="node-exporter"}[2m]) > 0.01 + for: 1h + labels: + severity: warning + - alert: NodeHighNumberConntrackEntriesUsed + annotations: + description: '{{ $labels.instance }} {{ $value | humanizePercentage }} of conntrack entries are used.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodehighnumberconntrackentriesused + summary: Number of conntrack are getting close to the limit. + expr: (node_nf_conntrack_entries{job="node-exporter"} / node_nf_conntrack_entries_limit) > 0.75 + labels: + severity: warning + - alert: NodeTextFileCollectorScrapeError + annotations: + description: Node Exporter text file collector on {{ $labels.instance }} failed to scrape. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodetextfilecollectorscrapeerror + summary: Node Exporter text file collector failed to scrape. + expr: node_textfile_scrape_error{job="node-exporter"} == 1 + labels: + severity: warning + - alert: NodeClockSkewDetected + annotations: + description: Clock at {{ $labels.instance }} is out of sync by more than 0.05s. Ensure NTP is configured correctly on this host. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclockskewdetected + summary: Clock skew detected. + expr: |- + ( + node_timex_offset_seconds{job="node-exporter"} > 0.05 + and + deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) >= 0 + ) + or + ( + node_timex_offset_seconds{job="node-exporter"} < -0.05 + and + deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) <= 0 + ) + for: 10m + labels: + severity: warning + - alert: NodeClockNotSynchronising + annotations: + description: Clock at {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclocknotsynchronising + summary: Clock not synchronising. + expr: |- + min_over_time(node_timex_sync_status{job="node-exporter"}[5m]) == 0 + and + node_timex_maxerror_seconds{job="node-exporter"} >= 16 + for: 10m + labels: + severity: warning + - alert: NodeRAIDDegraded + annotations: + description: RAID array '{{ $labels.device }}' at {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddegraded + summary: RAID Array is degraded. + expr: node_md_disks_required{job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"} - ignoring (state) (node_md_disks{state="active",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}) > 0 + for: 15m + labels: + severity: critical + - alert: NodeRAIDDiskFailure + annotations: + description: At least one device in RAID array at {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddiskfailure + summary: Failed device in RAID array. + expr: node_md_disks{state="failed",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"} > 0 + labels: + severity: warning + - alert: NodeFileDescriptorLimit + annotations: + description: File descriptors limit at {{ $labels.instance }} is currently at {{ printf "%.2f" $value }}%. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit + summary: Kernel is predicted to exhaust file descriptors limit soon. + expr: |- + ( + node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 70 + ) + for: 15m + labels: + severity: warning + - alert: NodeFileDescriptorLimit + annotations: + description: File descriptors limit at {{ $labels.instance }} is currently at {{ printf "%.2f" $value }}%. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit + summary: Kernel is predicted to exhaust file descriptors limit soon. + expr: |- + ( + node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 90 + ) + for: 15m + labels: + severity: critical + - alert: NodeCPUHighUsage + annotations: + description: 'CPU usage at {{ $labels.instance }} has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodecpuhighusage + summary: High CPU usage. + expr: sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{job="node-exporter", mode!~"idle|iowait"}[2m]))) * 100 > 90 + for: 15m + labels: + severity: info + - alert: NodeSystemSaturation + annotations: + description: 'System load per core at {{ $labels.instance }} has been above 2 for the last 15 minutes, is currently at {{ printf "%.2f" $value }}. + + This might indicate this instance resources saturation and can cause it becoming unresponsive. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemsaturation + summary: System saturated, load per core is very high. + expr: |- + node_load1{job="node-exporter"} + / count without (cpu, mode) (node_cpu_seconds_total{job="node-exporter", mode="idle"}) > 2 + for: 15m + labels: + severity: warning + - alert: NodeMemoryMajorPagesFaults + annotations: + description: 'Memory major pages are occurring at very high rate at {{ $labels.instance }}, 500 major page faults per second for the last 15 minutes, is currently at {{ printf "%.2f" $value }}. + + Please check that there is enough memory available at this instance. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememorymajorpagesfaults + summary: Memory major page faults are occurring at very high rate. + expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m]) > 500 + for: 15m + labels: + severity: warning + - alert: NodeMemoryHighUtilization + annotations: + description: 'Memory is filling up at {{ $labels.instance }}, has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememoryhighutilization + summary: Host is running out of memory. + expr: 100 - (node_memory_MemAvailable_bytes{job="node-exporter"} / node_memory_MemTotal_bytes{job="node-exporter"} * 100) > 90 + for: 15m + labels: + severity: warning + - alert: NodeDiskIOSaturation + annotations: + description: 'Disk IO queue (aqu-sq) is high on {{ $labels.device }} at {{ $labels.instance }}, has been above 10 for the last 30 minutes, is currently at {{ printf "%.2f" $value }}. + + This symptom might indicate disk saturation. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodediskiosaturation + summary: Disk IO queue is high. + expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m]) > 10 + for: 30m + labels: + severity: warning + - alert: NodeSystemdServiceFailed + annotations: + description: Systemd service {{ $labels.name }} has entered failed state at {{ $labels.instance }} + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemdservicefailed + summary: Systemd service has entered failed state. + expr: node_systemd_unit_state{job="node-exporter", state="failed"} == 1 + for: 5m + labels: + severity: warning + - alert: NodeSystemdServiceCrashlooping + annotations: + description: Systemd service {{ $labels.name }} has being restarted too many times at {{ $labels.instance }} for the last 15 minutes. Please check if service is crash looping. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemdservicecrashlooping + summary: Systemd service keeps restaring, possibly crash looping. + expr: increase(node_systemd_service_restart_total{job="node-exporter"}[5m]) > 2 + for: 15m + labels: + severity: warning + - alert: NodeBondingDegraded + annotations: + description: Bonding interface {{ $labels.master }} on {{ $labels.instance }} is in degraded state due to one or more slave failures. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodebondingdegraded + summary: Bonding interface is degraded + expr: (node_bonding_slaves - node_bonding_active) != 0 + for: 5m + labels: + severity: warning +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node-network.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-node-network + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: node-network + rules: + - alert: NodeNetworkInterfaceFlapping + annotations: + description: Network interface "{{ $labels.device }}" changing its up status often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }} + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/nodenetworkinterfaceflapping + summary: Network interface is often changing its status + expr: changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2 + for: 2m + labels: + severity: warning +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-node.rules + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: node.rules + rules: + - expr: |- + topk by (cluster, namespace, pod) (1, + max by (cluster, node, namespace, pod) ( + label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)") + )) + record: 'node_namespace_pod:kube_pod_info:' + - expr: |- + count by (cluster, node) ( + node_cpu_seconds_total{mode="idle",job="node-exporter"} + * on (cluster, namespace, pod) group_left(node) + topk by (cluster, namespace, pod) (1, node_namespace_pod:kube_pod_info:) + ) + record: node:node_num_cpu:sum + - expr: |- + sum( + node_memory_MemAvailable_bytes{job="node-exporter"} or + ( + node_memory_Buffers_bytes{job="node-exporter"} + + node_memory_Cached_bytes{job="node-exporter"} + + node_memory_MemFree_bytes{job="node-exporter"} + + node_memory_Slab_bytes{job="node-exporter"} + ) + ) by (cluster) + record: :node_memory_MemAvailable_bytes:sum + - expr: |- + avg by (cluster, node) ( + sum without (mode) ( + rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal",job="node-exporter"}[5m]) + ) + ) + record: node:node_cpu_utilization:ratio_rate5m + - expr: |- + avg by (cluster) ( + node:node_cpu_utilization:ratio_rate5m + ) + record: cluster:node_cpu:ratio_rate5m +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus-operator.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-prometheus-operator + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: prometheus-operator + rules: + - alert: PrometheusOperatorListErrors + annotations: + description: Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorlisterrors + summary: Errors while performing list operations in controller. + expr: (sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[10m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_total{job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[10m]))) > 0.4 + for: 15m + labels: + severity: warning + - alert: PrometheusOperatorWatchErrors + annotations: + description: Errors while performing watch operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorwatcherrors + summary: Errors while performing watch operations in controller. + expr: (sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[5m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_total{job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[5m]))) > 0.4 + for: 15m + labels: + severity: warning + - alert: PrometheusOperatorSyncFailed + annotations: + description: Controller {{ $labels.controller }} in {{ $labels.namespace }} namespace fails to reconcile {{ $value }} objects. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorsyncfailed + summary: Last controller reconciliation failed + expr: min_over_time(prometheus_operator_syncs{status="failed",job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[5m]) > 0 + for: 10m + labels: + severity: warning + - alert: PrometheusOperatorReconcileErrors + annotations: + description: '{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorreconcileerrors + summary: Errors while reconciling objects. + expr: (sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[5m]))) / (sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[5m]))) > 0.1 + for: 10m + labels: + severity: warning + - alert: PrometheusOperatorStatusUpdateErrors + annotations: + description: '{{ $value | humanizePercentage }} of status update operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorstatusupdateerrors + summary: Errors while updating objects status. + expr: (sum by (cluster,controller,namespace) (rate(prometheus_operator_status_update_errors_total{job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[5m]))) / (sum by (cluster,controller,namespace) (rate(prometheus_operator_status_update_operations_total{job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[5m]))) > 0.1 + for: 10m + labels: + severity: warning + - alert: PrometheusOperatorNodeLookupErrors + annotations: + description: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatornodelookuperrors + summary: Errors while reconciling Prometheus. + expr: rate(prometheus_operator_node_address_lookup_errors_total{job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[5m]) > 0.1 + for: 10m + labels: + severity: warning + - alert: PrometheusOperatorNotReady + annotations: + description: Prometheus operator in {{ $labels.namespace }} namespace isn't ready to reconcile {{ $labels.controller }} resources. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatornotready + summary: Prometheus operator not ready + expr: min by (cluster,controller,namespace) (max_over_time(prometheus_operator_ready{job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[5m]) == 0) + for: 5m + labels: + severity: warning + - alert: PrometheusOperatorRejectedResources + annotations: + description: Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorrejectedresources + summary: Resources rejected by Prometheus operator + expr: min_over_time(prometheus_operator_managed_resources{state="rejected",job="kube-prometheus-stack-1754-operator",namespace="prometheus"}[5m]) > 0 + for: 5m + labels: + severity: warning +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-prometheus-stack-1754-prometheus + namespace: prometheus + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + groups: + - name: prometheus + rules: + - alert: PrometheusBadConfig + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to reload its configuration. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusbadconfig + summary: Failed Prometheus configuration reload. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(prometheus_config_last_reload_successful{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) == 0 + for: 10m + labels: + severity: critical + - alert: PrometheusSDRefreshFailure + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to refresh SD with mechanism {{$labels.mechanism}}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheussdrefreshfailure + summary: Failed Prometheus SD refresh. + expr: increase(prometheus_sd_refresh_failures_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[10m]) > 0 + for: 20m + labels: + severity: warning + - alert: PrometheusKubernetesListWatchFailures + annotations: + description: Kubernetes service discovery of Prometheus {{$labels.namespace}}/{{$labels.pod}} is experiencing {{ printf "%.0f" $value }} failures with LIST/WATCH requests to the Kubernetes API in the last 5 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuskuberneteslistwatchfailures + summary: Requests in Kubernetes SD are failing. + expr: increase(prometheus_sd_kubernetes_failures_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusNotificationQueueRunningFull + annotations: + description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}} is running full. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotificationqueuerunningfull + summary: Prometheus alert notification queue predicted to run full in less than 30m. + expr: |- + # Without min_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + predict_linear(prometheus_notifications_queue_length{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m], 60 * 30) + > + min_over_time(prometheus_notifications_queue_capacity{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) + ) + for: 15m + labels: + severity: warning + - alert: PrometheusErrorSendingAlertsToSomeAlertmanagers + annotations: + description: '{{ printf "%.1f" $value }}% of alerts sent by Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}} were affected by errors.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstosomealertmanagers + summary: More than 1% of alerts sent by Prometheus to a specific Alertmanager were affected by errors. + expr: |- + ( + rate(prometheus_notifications_errors_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) + / + rate(prometheus_notifications_sent_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) + ) + * 100 + > 1 + for: 15m + labels: + severity: warning + - alert: PrometheusNotConnectedToAlertmanagers + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected to any Alertmanagers. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotconnectedtoalertmanagers + summary: Prometheus is not connected to any Alertmanagers. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(prometheus_notifications_alertmanagers_discovered{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) < 1 + for: 10m + labels: + severity: warning + - alert: PrometheusTSDBReloadsFailing + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} reload failures over the last 3h. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbreloadsfailing + summary: Prometheus has issues reloading blocks from disk. + expr: increase(prometheus_tsdb_reloads_failures_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[3h]) > 0 + for: 4h + labels: + severity: warning + - alert: PrometheusTSDBCompactionsFailing + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} compaction failures over the last 3h. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbcompactionsfailing + summary: Prometheus has issues compacting blocks. + expr: increase(prometheus_tsdb_compactions_failed_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[3h]) > 0 + for: 4h + labels: + severity: warning + - alert: PrometheusNotIngestingSamples + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting samples. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotingestingsamples + summary: Prometheus is not ingesting samples. + expr: |- + ( + sum without(type) (rate(prometheus_tsdb_head_samples_appended_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m])) <= 0 + and + ( + sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}) > 0 + or + sum without(rule_group) (prometheus_rule_group_rules{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}) > 0 + ) + ) + for: 10m + labels: + severity: warning + - alert: PrometheusDuplicateTimestamps + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with different values but duplicated timestamp. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusduplicatetimestamps + summary: Prometheus is dropping samples with duplicate timestamps. + expr: rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) > 0 + for: 10m + labels: + severity: warning + - alert: PrometheusOutOfOrderTimestamps + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with timestamps arriving out of order. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusoutofordertimestamps + summary: Prometheus drops samples with out-of-order timestamps. + expr: rate(prometheus_target_scrapes_sample_out_of_order_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) > 0 + for: 10m + labels: + severity: warning + - alert: PrometheusRemoteStorageFailures + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }} + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotestoragefailures + summary: Prometheus fails to send samples to remote storage. + expr: |- + ( + (rate(prometheus_remote_storage_failed_samples_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m])) + / + ( + (rate(prometheus_remote_storage_failed_samples_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m])) + + + (rate(prometheus_remote_storage_succeeded_samples_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) or rate(prometheus_remote_storage_samples_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m])) + ) + ) + * 100 + > 1 + for: 15m + labels: + severity: critical + - alert: PrometheusRemoteWriteBehind + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritebehind + summary: Prometheus remote write is behind. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) + - ignoring(remote_name, url) group_right + max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) + ) + > 120 + for: 15m + labels: + severity: critical + - alert: PrometheusRemoteWriteDesiredShards + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}` $labels.instance | query | first | value }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritedesiredshards + summary: Prometheus remote write desired shards calculation wants to run more than configured max shards. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + max_over_time(prometheus_remote_storage_shards_desired{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) + > + max_over_time(prometheus_remote_storage_shards_max{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) + ) + for: 15m + labels: + severity: warning + - alert: PrometheusRuleFailures + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to evaluate {{ printf "%.0f" $value }} rules in the last 5m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusrulefailures + summary: Prometheus is failing rule evaluations. + expr: increase(prometheus_rule_evaluation_failures_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) > 0 + for: 15m + labels: + severity: critical + - alert: PrometheusMissingRuleEvaluations + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{ printf "%.0f" $value }} rule group evaluations in the last 5m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusmissingruleevaluations + summary: Prometheus is missing rule evaluations due to slow rule group evaluation. + expr: increase(prometheus_rule_group_iterations_missed_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusTargetLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because the number of targets exceeded the configured target_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetlimithit + summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit. + expr: increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusLabelLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because some samples exceeded the configured label_limit, label_name_length_limit or label_value_length_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuslabellimithit + summary: Prometheus has dropped targets because some scrape configs have exceeded the labels limit. + expr: increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusScrapeBodySizeLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed {{ printf "%.0f" $value }} scrapes in the last 5m because some targets exceeded the configured body_size_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapebodysizelimithit + summary: Prometheus has dropped some targets that exceeded body size limit. + expr: increase(prometheus_target_scrapes_exceeded_body_size_limit_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusScrapeSampleLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed {{ printf "%.0f" $value }} scrapes in the last 5m because some targets exceeded the configured sample_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapesamplelimithit + summary: Prometheus has failed scrapes that have exceeded the configured sample limit. + expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusTargetSyncFailure + annotations: + description: '{{ printf "%.0f" $value }} targets in Prometheus {{$labels.namespace}}/{{$labels.pod}} have failed to sync because invalid configuration was supplied.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetsyncfailure + summary: Prometheus has failed to sync targets. + expr: increase(prometheus_target_sync_failed_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[30m]) > 0 + for: 5m + labels: + severity: critical + - alert: PrometheusHighQueryLoad + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} query API has less than 20% available capacity in its query engine for the last 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheushighqueryload + summary: Prometheus is reaching its maximum capacity serving concurrent requests. + expr: avg_over_time(prometheus_engine_queries{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) / max_over_time(prometheus_engine_queries_concurrent_max{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus"}[5m]) > 0.8 + for: 15m + labels: + severity: warning + - alert: PrometheusErrorSendingAlertsToAnyAlertmanager + annotations: + description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstoanyalertmanager + summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager. + expr: |- + min without (alertmanager) ( + rate(prometheus_notifications_errors_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus",alertmanager!~``}[5m]) + / + rate(prometheus_notifications_sent_total{job="kube-prometheus-stack-1754-prometheus",namespace="prometheus",alertmanager!~``}[5m]) + ) + * 100 + > 3 + for: 15m + labels: + severity: critical +--- +# Source: kube-prometheus-stack/charts/grafana/templates/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus + labels: + helm.sh/chart: grafana-9.3.0 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "12.1.0" +spec: + endpoints: + - port: http-web + scrapeTimeout: 30s + honorLabels: true + path: /metrics + scheme: http + jobLabel: "kube-prometheus-stack-1754164871" + selector: + matchLabels: + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + namespaceSelector: + matchNames: + - prometheus +--- +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754164871-kube-state-metrics + namespace: prometheus + labels: + helm.sh/chart: kube-state-metrics-6.1.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "2.16.0" + release: kube-prometheus-stack-1754164871 +spec: + jobLabel: app.kubernetes.io/name + selector: + matchLabels: + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + endpoints: + - port: http + honorLabels: true +--- +# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754164871-prometheus-node-exporter + namespace: prometheus + labels: + helm.sh/chart: prometheus-node-exporter-4.47.3 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "1.9.1" + release: kube-prometheus-stack-1754164871 +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + attachMetadata: + node: false + endpoints: + - port: http-metrics + scheme: http +--- +# Source: kube-prometheus-stack/templates/alertmanager/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754-alertmanager + namespace: prometheus + labels: + app: kube-prometheus-stack-alertmanager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + + selector: + matchLabels: + app: kube-prometheus-stack-alertmanager + release: "kube-prometheus-stack-1754164871" + self-monitor: "true" + namespaceSelector: + matchNames: + - "prometheus" + endpoints: + - port: http-web + enableHttp2: true + path: "/metrics" + - port: reloader-web + path: "/metrics" +--- +# Source: kube-prometheus-stack/templates/exporters/core-dns/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754-coredns + namespace: prometheus + labels: + app: kube-prometheus-stack-coredns + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app: kube-prometheus-stack-coredns + release: "kube-prometheus-stack-1754164871" + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token +--- +# Source: kube-prometheus-stack/templates/exporters/kube-api-server/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754-apiserver + namespace: prometheus + labels: + app: kube-prometheus-stack-apiserver + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + port: https + scheme: https + metricRelabelings: + - action: drop + regex: (etcd_request|apiserver_request_slo|apiserver_request_sli|apiserver_request)_duration_seconds_bucket;(0\.15|0\.2|0\.3|0\.35|0\.4|0\.45|0\.6|0\.7|0\.8|0\.9|1\.25|1\.5|1\.75|2|3|3\.5|4|4\.5|6|7|8|9|15|20|40|45|50)(\.0)? + sourceLabels: + - __name__ + - le + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + serverName: kubernetes + insecureSkipVerify: false + jobLabel: component + namespaceSelector: + matchNames: + - default + selector: + matchLabels: + component: apiserver + provider: kubernetes +--- +# Source: kube-prometheus-stack/templates/exporters/kube-controller-manager/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754-kube-controller-manager + namespace: prometheus + labels: + app: kube-prometheus-stack-kube-controller-manager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app: kube-prometheus-stack-kube-controller-manager + release: "kube-prometheus-stack-1754164871" + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true +--- +# Source: kube-prometheus-stack/templates/exporters/kube-etcd/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754-kube-etcd + namespace: prometheus + labels: + app: kube-prometheus-stack-kube-etcd + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app: kube-prometheus-stack-kube-etcd + release: "kube-prometheus-stack-1754164871" + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token +--- +# Source: kube-prometheus-stack/templates/exporters/kube-proxy/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754-kube-proxy + namespace: prometheus + labels: + app: kube-prometheus-stack-kube-proxy + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app: kube-prometheus-stack-kube-proxy + release: "kube-prometheus-stack-1754164871" + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token +--- +# Source: kube-prometheus-stack/templates/exporters/kube-scheduler/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754-kube-scheduler + namespace: prometheus + labels: + app: kube-prometheus-stack-kube-scheduler + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app: kube-prometheus-stack-kube-scheduler + release: "kube-prometheus-stack-1754164871" + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true +--- +# Source: kube-prometheus-stack/templates/exporters/kubelet/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754-kubelet + namespace: prometheus + labels: + app: kube-prometheus-stack-kubelet + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + + attachMetadata: + node: false + jobLabel: k8s-app + namespaceSelector: + matchNames: + - kube-system + selector: + matchLabels: + app.kubernetes.io/name: kubelet + k8s-app: kubelet + endpoints: + - port: https-metrics + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + honorLabels: true + honorTimestamps: true + metricRelabelings: + - action: drop + regex: (csi_operations|storage_operation_duration)_seconds_bucket;(0.25|2.5|15|25|120|600)(\.0)? + sourceLabels: + - __name__ + - le + relabelings: + - action: replace + sourceLabels: + - __metrics_path__ + targetLabel: metrics_path + - port: https-metrics + scheme: https + path: /metrics/cadvisor + interval: 10s + honorLabels: true + honorTimestamps: true + trackTimestampsStaleness: true + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + metricRelabelings: + - action: drop + regex: container_cpu_(cfs_throttled_seconds_total|load_average_10s|system_seconds_total|user_seconds_total) + sourceLabels: + - __name__ + - action: drop + regex: container_fs_(io_current|io_time_seconds_total|io_time_weighted_seconds_total|reads_merged_total|sector_reads_total|sector_writes_total|writes_merged_total) + sourceLabels: + - __name__ + - action: drop + regex: container_memory_(mapped_file|swap) + sourceLabels: + - __name__ + - action: drop + regex: container_(file_descriptors|tasks_state|threads_max) + sourceLabels: + - __name__ + - action: drop + regex: container_memory_failures_total;hierarchy + sourceLabels: + - __name__ + - scope + - action: drop + regex: container_network_.*;(cali|cilium|cni|lxc|nodelocaldns|tunl).* + sourceLabels: + - __name__ + - interface + - action: drop + regex: container_spec.* + sourceLabels: + - __name__ + - action: drop + regex: .+; + sourceLabels: + - id + - pod + relabelings: + - action: replace + sourceLabels: + - __metrics_path__ + targetLabel: metrics_path + - port: https-metrics + scheme: https + path: /metrics/probes + honorLabels: true + honorTimestamps: true + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + relabelings: + - action: replace + sourceLabels: + - __metrics_path__ + targetLabel: metrics_path +--- +# Source: kube-prometheus-stack/templates/prometheus-operator/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754-operator + namespace: prometheus + labels: + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + app: kube-prometheus-stack-operator + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/component: prometheus-operator +spec: + + endpoints: + - port: https + scheme: https + tlsConfig: + serverName: kube-prometheus-stack-1754-operator + ca: + secret: + name: kube-prometheus-stack-1754-admission + key: ca + optional: false + honorLabels: true + selector: + matchLabels: + app: kube-prometheus-stack-operator + release: "kube-prometheus-stack-1754164871" + namespaceSelector: + matchNames: + - "prometheus" +--- +# Source: kube-prometheus-stack/templates/prometheus/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-prometheus-stack-1754-prometheus + namespace: prometheus + labels: + app: kube-prometheus-stack-prometheus + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" +spec: + + selector: + matchLabels: + app: kube-prometheus-stack-prometheus + release: "kube-prometheus-stack-1754164871" + self-monitor: "true" + namespaceSelector: + matchNames: + - "prometheus" + endpoints: + - port: http-web + path: "/metrics" + - port: reloader-web + path: "/metrics" +--- +# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/validatingWebhookConfiguration.yaml +apiVersion: admissionregistration.k8s.io/v1 +kind: ValidatingWebhookConfiguration +metadata: + name: kube-prometheus-stack-1754-admission + annotations: + + labels: + app: kube-prometheus-stack-admission + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/version: "75.15.1" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-75.15.1 + release: "kube-prometheus-stack-1754164871" + heritage: "Helm" + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/component: prometheus-operator-webhook +webhooks: + - name: prometheusrulemutate.monitoring.coreos.com + failurePolicy: Ignore + rules: + - apiGroups: + - monitoring.coreos.com + apiVersions: + - "*" + resources: + - prometheusrules + operations: + - CREATE + - UPDATE + clientConfig: + service: + namespace: prometheus + name: kube-prometheus-stack-1754-operator + path: /admission-prometheusrules/validate + timeoutSeconds: 10 + admissionReviewVersions: ["v1", "v1beta1"] + sideEffects: None + diff --git a/docs/source/distributions/k8s/all-values.yaml b/docs/source/distributions/k8s/all-values.yaml new file mode 100644 index 000000000..a5d1bb029 --- /dev/null +++ b/docs/source/distributions/k8s/all-values.yaml @@ -0,0 +1,6 @@ +USER-SUPPLIED VALUES: +prometheus: + prometheusSpec: + serviceMonitorSelectorNilUsesHelmValues: false + service: + type: NodePort diff --git a/docs/source/distributions/k8s/apply.sh b/docs/source/distributions/k8s/apply.sh index 8f1852c9a..4d193b496 100755 --- a/docs/source/distributions/k8s/apply.sh +++ b/docs/source/distributions/k8s/apply.sh @@ -86,18 +86,6 @@ if [ "$USE_EBS" = "true" ]; then envsubst < ./chroma-k8s.yaml.template | kubectl apply -f - - # Create monitoring namespace - kubectl create namespace monitoring --dry-run=client -o yaml | kubectl apply -f - - - # Install Prometheus Operator CRDs - ./install-prometheus-operator.sh - - # Apply RBAC for Prometheus - kubectl apply -f ./prometheus-rbac.yaml - - # Apply monitoring resources after CRDs are installed - envsubst < ./monitoring-k8s.yaml.template | kubectl apply -f - - kubectl create configmap llama-stack-config --from-file=stack_run_config.yaml \ --dry-run=client -o yaml > stack-configmap.yaml @@ -116,16 +104,6 @@ else envsubst < ./postgres-k8s.yaml.template | sed 's/persistentVolumeClaim:/emptyDir: {}/g' | sed '/claimName:/d' | kubectl apply -f - envsubst < ./chroma-k8s.yaml.template | sed 's/persistentVolumeClaim:/emptyDir: {}/g' | sed '/claimName:/d' | kubectl apply -f - - # Create monitoring namespace - kubectl create namespace monitoring --dry-run=client -o yaml | kubectl apply -f - - - - # Apply RBAC for Prometheus - kubectl apply -f ./prometheus-rbac.yaml - - # Apply monitoring resources after CRDs are installed - envsubst < ./monitoring-k8s.yaml.template | kubectl apply -f - - kubectl create configmap llama-stack-config --from-file=stack_run_config.yaml \ --dry-run=client -o yaml > stack-configmap.yaml diff --git a/docs/source/distributions/k8s/install-prometheus.sh b/docs/source/distributions/k8s/install-prometheus.sh index 5ac40de0a..e5b0e9e95 100644 --- a/docs/source/distributions/k8s/install-prometheus.sh +++ b/docs/source/distributions/k8s/install-prometheus.sh @@ -35,4 +35,4 @@ helm install prometheus prometheus-community/kube-prometheus-stack \ echo "kube-prometheus-stack has been installed successfully!" echo "To access Grafana UI, run: kubectl port-forward -n monitoring svc/prometheus-grafana 3000:80" -echo "Default Grafana credentials - Username: admin, Password: prom-operator" \ No newline at end of file +echo "Default Grafana credentials - Username: admin, Password: prom-operator" diff --git a/docs/source/distributions/k8s/monitoring-k8s.yaml.template b/docs/source/distributions/k8s/monitoring-k8s.yaml.template deleted file mode 100644 index 1cd4059f1..000000000 --- a/docs/source/distributions/k8s/monitoring-k8s.yaml.template +++ /dev/null @@ -1,3164 +0,0 @@ ---- -apiVersion: v1 -kind: Namespace -metadata: - name: monitoring ---- -# Prometheus ConfigMap -apiVersion: v1 -kind: ConfigMap -metadata: - name: prometheus-config - namespace: monitoring -data: - prometheus.yml: | - global: - scrape_interval: 15s - evaluation_interval: 15s - - scrape_configs: - # NVIDIA DCGM exporter for GPU metrics - - job_name: 'dcgm' - static_configs: - - targets: ['dcgm-exporter:9400'] - - - job_name: 'kubernetes-pods' - kubernetes_sd_configs: - - role: pod - relabel_configs: - - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape] - action: keep - regex: true - - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path] - action: replace - target_label: __metrics_path__ - regex: (.+) - - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port] - action: replace - regex: ([^:]+)(?::\d+)?;(\d+) - replacement: $1:$2 - target_label: __address__ - - action: labelmap - regex: __meta_kubernetes_pod_label_(.+) - - source_labels: [__meta_kubernetes_namespace] - action: replace - target_label: kubernetes_namespace - - source_labels: [__meta_kubernetes_pod_name] - action: replace - target_label: kubernetes_pod_name - - # Specific job for vLLM pods - - job_name: 'vllm-pods' - kubernetes_sd_configs: - - role: pod - relabel_configs: - - source_labels: [__meta_kubernetes_pod_label_app] - regex: vllm - action: keep - - source_labels: [__meta_kubernetes_pod_container_port_name] - regex: http - action: keep - - source_labels: [__meta_kubernetes_namespace] - action: replace - target_label: kubernetes_namespace - - source_labels: [__meta_kubernetes_pod_name] - action: replace - target_label: kubernetes_pod_name - - # Specific job for NIM pods - - job_name: 'nim-pods' - kubernetes_sd_configs: - - role: pod - relabel_configs: - - source_labels: [__meta_kubernetes_pod_label_nim_type] - regex: llama-nim - action: keep - - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path] - action: replace - target_label: __metrics_path__ - regex: (.+) - - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port] - action: replace - regex: ([^:]+)(?::\d+)?;(\d+) - replacement: $1:$2 - target_label: __address__ - - source_labels: [__meta_kubernetes_namespace] - action: replace - target_label: kubernetes_namespace - - source_labels: [__meta_kubernetes_pod_name] - action: replace - target_label: kubernetes_pod_name - - source_labels: [__meta_kubernetes_pod_label_app] - action: replace - target_label: app - - # Direct scrape for NIM service - - job_name: 'nim-service' - static_configs: - - targets: ['llm-nim-code:8000'] - metrics_path: /v1/metrics - scrape_interval: 5s - - # Specific job for Ollama pods - - job_name: 'ollama-pods' - kubernetes_sd_configs: - - role: pod - relabel_configs: - - source_labels: [__meta_kubernetes_pod_label_app_kubernetes_io_name] - regex: ollama-safety - action: keep - - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path] - action: replace - target_label: __metrics_path__ - regex: (.+) - - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port] - action: replace - regex: ([^:]+)(?::\d+)?;(\d+) - replacement: $1:$2 - target_label: __address__ - - source_labels: [__meta_kubernetes_namespace] - action: replace - target_label: kubernetes_namespace - - source_labels: [__meta_kubernetes_pod_name] - action: replace - target_label: kubernetes_pod_name ---- -# Prometheus Deployment -apiVersion: apps/v1 -kind: Deployment -metadata: - name: prometheus - namespace: monitoring - labels: - app: prometheus -spec: - replicas: 1 - selector: - matchLabels: - app: prometheus - template: - metadata: - labels: - app: prometheus - spec: - serviceAccountName: prometheus - containers: - - name: prometheus - image: prom/prometheus:v2.45.0 - args: - - "--config.file=/etc/prometheus/prometheus.yml" - - "--storage.tsdb.path=/prometheus" - - "--web.console.libraries=/etc/prometheus/console_libraries" - - "--web.console.templates=/etc/prometheus/consoles" - - "--web.enable-lifecycle" - ports: - - containerPort: 9090 - name: http - volumeMounts: - - name: prometheus-config - mountPath: /etc/prometheus/ - - name: prometheus-storage - mountPath: /prometheus - volumes: - - name: prometheus-config - configMap: - name: prometheus-config - - name: prometheus-storage - emptyDir: {} ---- -# Prometheus Service -apiVersion: v1 -kind: Service -metadata: - name: prometheus - namespace: monitoring - annotations: - prometheus.io/scrape: 'true' - prometheus.io/port: '9090' -spec: - selector: - app: prometheus - ports: - - port: 9090 - targetPort: 9090 - name: http - type: NodePort # Changed from ClusterIP to NodePort to make it accessible outside the cluster ---- -# Grafana ConfigMap for datasources -apiVersion: v1 -kind: ConfigMap -metadata: - name: grafana-datasources - namespace: monitoring -data: - prometheus.yaml: | - apiVersion: 1 - datasources: - - name: Prometheus - type: prometheus - url: http://prometheus:9090 - access: proxy - isDefault: true ---- -# Grafana ConfigMap for dashboards provider -apiVersion: v1 -kind: ConfigMap -metadata: - name: grafana-dashboards-provider - namespace: monitoring -data: - dashboards.yaml: | - apiVersion: 1 - providers: - - name: 'default' - orgId: 1 - folder: '' - type: file - disableDeletion: false - editable: true - options: - path: /var/lib/grafana/dashboards ---- -# Grafana ConfigMap for dashboards -apiVersion: v1 -kind: ConfigMap -metadata: - name: grafana-dashboards - namespace: monitoring -data: - nim-dashboard.json: | - { - "annotations": { - "list": [ - { - "builtIn": 1, - "datasource": "-- Grafana --", - "enable": true, - "hide": true, - "iconColor": "rgba(0, 211, 255, 1)", - "name": "Annotations & Alerts", - "type": "dashboard" - } - ] - }, - "editable": true, - "gnetId": null, - "graphTooltip": 0, - "id": 2, - "links": [], - "panels": [ - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 0 - }, - "hiddenSeries": false, - "id": 1, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "DCGM_FI_DEV_GPU_UTIL{instance=\"dcgm-exporter:9400\", pod=~\"(llm-nim-code|vllm).*\"}", - "refId": "A", - "legendFormat": "GPU {{gpu}} - {{pod}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "NIM GPU Utilization", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "percent", - "label": null, - "logBase": 1, - "max": "100", - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 0 - }, - "hiddenSeries": false, - "id": 2, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "DCGM_FI_DEV_FB_USED{instance=\"dcgm-exporter:9400\", pod=~\"(llm-nim-code|vllm).*\"} / 1024 / 1024 / 1024", - "refId": "A", - "legendFormat": "GPU {{gpu}} - {{pod}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "NIM GPU Memory Used (GB)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "gbytes", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 8 - }, - "hiddenSeries": false, - "id": 3, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "DCGM_FI_DEV_POWER_USAGE{instance=\"dcgm-exporter:9400\", pod=~\"(llm-nim-code|vllm).*\"}", - "refId": "A", - "legendFormat": "GPU {{gpu}} - {{pod}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "NIM GPU Power Usage (W)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "watt", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 8 - }, - "hiddenSeries": false, - "id": 4, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "DCGM_FI_DEV_GPU_TEMP{instance=\"dcgm-exporter:9400\", pod=~\"(llm-nim-code|vllm).*\"}", - "refId": "A", - "legendFormat": "GPU {{gpu}} - {{pod}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "NIM GPU Temperature (°C)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "celsius", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 16 - }, - "hiddenSeries": false, - "id": 5, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "rate(nim_requests_total{pod=~\"llm-nim-code.*\"}[1m])", - "refId": "A", - "legendFormat": "{{pod}} - {{endpoint}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "NIM Request Rate", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "reqps", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 16 - }, - "hiddenSeries": false, - "id": 6, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "histogram_quantile(0.95, sum(rate(nim_request_duration_seconds_bucket{pod=~\"llm-nim-code.*\"}[5m])) by (le, endpoint))", - "refId": "A", - "legendFormat": "p95 - {{endpoint}}" - }, - { - "expr": "histogram_quantile(0.50, sum(rate(nim_request_duration_seconds_bucket{pod=~\"llm-nim-code.*\"}[5m])) by (le, endpoint))", - "refId": "B", - "legendFormat": "p50 - {{endpoint}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "NIM Request Latency", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "s", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 24 - }, - "hiddenSeries": false, - "id": 7, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "nim_active_requests{pod=~\"llm-nim-code.*\"}", - "refId": "A", - "legendFormat": "{{pod}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "NIM Active Requests", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 24 - }, - "hiddenSeries": false, - "id": 8, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "nim_tokens_per_second{pod=~\"llm-nim-code.*\"}", - "refId": "A", - "legendFormat": "{{pod}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "NIM Tokens Per Second", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - } - ], - "schemaVersion": 22, - "style": "dark", - "tags": [], - "templating": { - "list": [] - }, - "time": { - "from": "now-6h", - "to": "now" - }, - "timepicker": { - "refresh_intervals": [ - "5s", - "10s", - "30s", - "1m", - "5m", - "15m", - "30m", - "1h", - "2h", - "1d" - ] - }, - "timezone": "", - "title": "NVIDIA NIM Monitoring", - "uid": "nim-dashboard", - "version": 1 - } - ollama-dashboard.json: | - { - "annotations": { - "list": [ - { - "builtIn": 1, - "datasource": "-- Grafana --", - "enable": true, - "hide": true, - "iconColor": "rgba(0, 211, 255, 1)", - "name": "Annotations & Alerts", - "type": "dashboard" - } - ] - }, - "editable": true, - "gnetId": null, - "graphTooltip": 0, - "id": 3, - "links": [], - "panels": [ - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 0 - }, - "hiddenSeries": false, - "id": 1, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "rate(ollama_requests_total{kubernetes_pod_name=~\"ollama-safety.*\"}[1m])", - "refId": "A", - "legendFormat": "{{kubernetes_pod_name}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Ollama Request Rate", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "reqps", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 0 - }, - "hiddenSeries": false, - "id": 2, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "histogram_quantile(0.95, sum(rate(ollama_request_duration_seconds_bucket{kubernetes_pod_name=~\"ollama-safety.*\"}[5m])) by (le))", - "refId": "A", - "legendFormat": "p95" - }, - { - "expr": "histogram_quantile(0.50, sum(rate(ollama_request_duration_seconds_bucket{kubernetes_pod_name=~\"ollama-safety.*\"}[5m])) by (le))", - "refId": "B", - "legendFormat": "p50" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Ollama Request Latency", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "s", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 8 - }, - "hiddenSeries": false, - "id": 3, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "ollama_active_requests{kubernetes_pod_name=~\"ollama-safety.*\"}", - "refId": "A", - "legendFormat": "{{kubernetes_pod_name}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Ollama Active Requests", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 8 - }, - "hiddenSeries": false, - "id": 4, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "ollama_tokens_per_second{kubernetes_pod_name=~\"ollama-safety.*\"}", - "refId": "A", - "legendFormat": "{{kubernetes_pod_name}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Ollama Tokens Per Second", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 16 - }, - "hiddenSeries": false, - "id": 5, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "sum by(kubernetes_pod_name) (container_memory_usage_bytes{pod=~\"ollama-safety.*\"})", - "refId": "A", - "legendFormat": "{{kubernetes_pod_name}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Ollama Memory Usage", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "bytes", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 16 - }, - "hiddenSeries": false, - "id": 6, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "sum by(kubernetes_pod_name) (rate(container_cpu_usage_seconds_total{pod=~\"ollama-safety.*\"}[5m]))", - "refId": "A", - "legendFormat": "{{kubernetes_pod_name}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Ollama CPU Usage", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 24 - }, - "hiddenSeries": false, - "id": 7, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "ollama_gpu_memory_used_bytes{kubernetes_pod_name=~\"ollama-safety.*\"}", - "refId": "A", - "legendFormat": "Used - {{kubernetes_pod_name}}" - }, - { - "expr": "ollama_gpu_memory_total_bytes{kubernetes_pod_name=~\"ollama-safety.*\"}", - "refId": "B", - "legendFormat": "Total - {{kubernetes_pod_name}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Ollama GPU Memory", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "bytes", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 24 - }, - "hiddenSeries": false, - "id": 8, - "legend": { - "avg": false, - "current": true, - "max": true, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "ollama_gpu_utilization{kubernetes_pod_name=~\"ollama-safety.*\"}", - "refId": "A", - "legendFormat": "{{kubernetes_pod_name}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Ollama GPU Utilization", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "percent", - "label": null, - "logBase": 1, - "max": "100", - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - } - ], - "schemaVersion": 22, - "style": "dark", - "tags": [], - "templating": { - "list": [] - }, - "time": { - "from": "now-6h", - "to": "now" - }, - "timepicker": { - "refresh_intervals": [ - "5s", - "10s", - "30s", - "1m", - "5m", - "15m", - "30m", - "1h", - "2h", - "1d" - ] - }, - "timezone": "", - "title": "Ollama Monitoring", - "uid": "ollama-dashboard", - "version": 1 - } - k8s-pods-dashboard.json: | - { - "annotations": { - "list": [ - { - "builtIn": 1, - "datasource": "-- Grafana --", - "enable": true, - "hide": true, - "iconColor": "rgba(0, 211, 255, 1)", - "name": "Annotations & Alerts", - "type": "dashboard" - } - ] - }, - "editable": true, - "gnetId": null, - "graphTooltip": 0, - "id": 1, - "links": [], - "panels": [ - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 16 - }, - "hiddenSeries": false, - "id": 11, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "gpu_cache_usage_perc{model_name=~\".+\"} * 100", - "refId": "A" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "GPU KV-Cache Usage (%)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "percent", - "label": null, - "logBase": 1, - "max": "100", - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 16 - }, - "hiddenSeries": false, - "id": 12, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "num_requests_running{model_name=~\".+\"}", - "refId": "A", - "legendFormat": "Running - {{model_name}}" - }, - { - "expr": "num_requests_waiting{model_name=~\".+\"}", - "refId": "B", - "legendFormat": "Waiting - {{model_name}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Request Queue", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 24 - }, - "hiddenSeries": false, - "id": 13, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "histogram_quantile(0.95, sum(rate(time_to_first_token_seconds_bucket{model_name=~\".+\"}[5m])) by (le, model_name))", - "refId": "A", - "legendFormat": "p95 - {{model_name}}" - }, - { - "expr": "histogram_quantile(0.50, sum(rate(time_to_first_token_seconds_bucket{model_name=~\".+\"}[5m])) by (le, model_name))", - "refId": "B", - "legendFormat": "p50 - {{model_name}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Time to First Token (seconds)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "s", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 24 - }, - "hiddenSeries": false, - "id": 14, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "histogram_quantile(0.95, sum(rate(time_per_output_token_seconds_bucket{model_name=~\".+\"}[5m])) by (le, model_name))", - "refId": "A", - "legendFormat": "p95 - {{model_name}}" - }, - { - "expr": "histogram_quantile(0.50, sum(rate(time_per_output_token_seconds_bucket{model_name=~\".+\"}[5m])) by (le, model_name))", - "refId": "B", - "legendFormat": "p50 - {{model_name}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Time per Output Token (seconds)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "s", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 0 - }, - "hiddenSeries": false, - "id": 8, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "DCGM_FI_DEV_GPU_UTIL{instance=\"dcgm-exporter:9400\"}", - "refId": "A", - "legendFormat": "GPU {{gpu}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "GPU Utilization", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "percent", - "label": null, - "logBase": 1, - "max": "100", - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 0 - }, - "hiddenSeries": false, - "id": 9, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "DCGM_FI_DEV_FB_USED{instance=\"dcgm-exporter:9400\"} / (DCGM_FI_DEV_FB_USED{instance=\"dcgm-exporter:9400\"} + DCGM_FI_DEV_FB_FREE{instance=\"dcgm-exporter:9400\"}) * 100", - "refId": "A", - "legendFormat": "GPU {{gpu}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "GPU Memory Utilization", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "percent", - "label": null, - "logBase": 1, - "max": "100", - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 8 - }, - "hiddenSeries": false, - "id": 10, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "DCGM_FI_DEV_POWER_USAGE{instance=\"dcgm-exporter:9400\"}", - "refId": "A", - "legendFormat": "GPU {{gpu}}" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "GPU Power Usage (Watts)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "celsius", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 0 - }, - "hiddenSeries": false, - "id": 2, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{pod=~\"vllm.*|llama-nim.*\"}[5m]))", - "refId": "A" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "CPU Usage", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 0 - }, - "hiddenSeries": false, - "id": 3, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "sum by(pod) (container_memory_usage_bytes{pod=~\"vllm.*|llama-nim.*\"})", - "refId": "A" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Memory Usage", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "bytes", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 8 - }, - "hiddenSeries": false, - "id": 4, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "sum by(pod) (rate(container_network_receive_bytes_total{pod=~\"vllm.*|llama-nim.*\"}[5m]))", - "refId": "A" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Network Receive", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "bytes", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 8 - }, - "hiddenSeries": false, - "id": 5, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{pod=~\"vllm.*|llama-nim.*\"}[5m]))", - "refId": "A" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Network Transmit", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "bytes", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 16 - }, - "hiddenSeries": false, - "id": 6, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "sum by(pod) (rate(container_fs_reads_total{pod=~\"vllm.*|llama-nim.*\"}[5m]))", - "refId": "A" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Disk Reads", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "Prometheus", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 16 - }, - "hiddenSeries": false, - "id": 7, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "dataLinks": [] - }, - "percentage": false, - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "sum by(pod) (rate(container_fs_writes_total{pod=~\"vllm.*|llama-nim.*\"}[5m]))", - "refId": "A" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Disk Writes", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - } - ], - "schemaVersion": 22, - "style": "dark", - "tags": [], - "templating": { - "list": [] - }, - "time": { - "from": "now-6h", - "to": "now" - }, - "timepicker": { - "refresh_intervals": [ - "5s", - "10s", - "30s", - "1m", - "5m", - "15m", - "30m", - "1h", - "2h", - "1d" - ] - }, - "timezone": "", - "title": "Llama Stack Monitoring", - "uid": "llama-stack", - "version": 1 - } ---- -# Grafana Deployment -apiVersion: apps/v1 -kind: Deployment -metadata: - name: grafana - namespace: monitoring - labels: - app: grafana -spec: - replicas: 1 - selector: - matchLabels: - app: grafana - template: - metadata: - labels: - app: grafana - spec: - containers: - - name: grafana - image: grafana/grafana:10.0.3 - ports: - - containerPort: 3000 - name: http - volumeMounts: - - name: grafana-storage - mountPath: /var/lib/grafana - - name: grafana-datasources - mountPath: /etc/grafana/provisioning/datasources - - name: grafana-dashboards-provider - mountPath: /etc/grafana/provisioning/dashboards - - name: grafana-dashboards - mountPath: /var/lib/grafana/dashboards - env: - - name: GF_SECURITY_ADMIN_USER - value: admin - - name: GF_SECURITY_ADMIN_PASSWORD - value: admin # In production, use a secret - - name: GF_USERS_ALLOW_SIGN_UP - value: "false" - volumes: - - name: grafana-storage - emptyDir: {} - - name: grafana-datasources - configMap: - name: grafana-datasources - - name: grafana-dashboards-provider - configMap: - name: grafana-dashboards-provider - - name: grafana-dashboards - configMap: - name: grafana-dashboards ---- -# Grafana Service -apiVersion: v1 -kind: Service -metadata: - name: grafana - namespace: monitoring -spec: - selector: - app: grafana - ports: - - port: 3000 - targetPort: 3000 - name: http - type: ClusterIP ---- -# Service Monitor for Prometheus Operator (if using it) -apiVersion: monitoring.coreos.com/v1 -kind: ServiceMonitor -metadata: - name: vllm-monitor - namespace: monitoring - labels: - release: prometheus -spec: - selector: - matchLabels: - app: vllm - namespaceSelector: - matchNames: - - default - endpoints: - - port: http - interval: 15s ---- -apiVersion: monitoring.coreos.com/v1 -kind: ServiceMonitor -metadata: - name: nim-monitor - namespace: monitoring - labels: - release: prometheus -spec: - selector: - matchLabels: - nim-type: llama-nim - namespaceSelector: - matchNames: - - default - endpoints: - - port: http-openai - interval: 15s ---- -# Ingress for Grafana and Prometheus (if needed) -apiVersion: networking.k8s.io/v1 -kind: Ingress -metadata: - name: monitoring-ingress - namespace: monitoring - annotations: - nginx.ingress.kubernetes.io/rewrite-target: / -spec: - rules: - - host: grafana.local - http: - paths: - - path: / - pathType: Prefix - backend: - service: - name: grafana - port: - number: 3000 - - host: prometheus.local - http: - paths: - - path: / - pathType: Prefix - backend: - service: - name: prometheus - port: - number: 9090 ---- -# NVIDIA DCGM Exporter DaemonSet for GPU metrics -apiVersion: apps/v1 -kind: DaemonSet -metadata: - name: dcgm-exporter - namespace: monitoring - labels: - app: dcgm-exporter -spec: - selector: - matchLabels: - app: dcgm-exporter - template: - metadata: - labels: - app: dcgm-exporter - spec: - containers: - - name: dcgm-exporter - image: nvidia/dcgm-exporter:3.2.5-3.1.7-ubuntu20.04 - securityContext: - runAsNonRoot: false - runAsUser: 0 - ports: - - containerPort: 9400 - name: metrics - args: - - -f - - /etc/dcgm-exporter/dcp-metrics-included.csv - volumeMounts: - - name: dcgm-config - mountPath: /etc/dcgm-exporter - volumes: - - name: dcgm-config - configMap: - name: dcgm-config - nodeSelector: - kubernetes.io/os: linux - nvidia.com/gpu.present: "true" - tolerations: - - key: nvidia.com/gpu - operator: Exists - effect: NoSchedule ---- -# DCGM Exporter ConfigMap for metrics configuration -apiVersion: v1 -kind: ConfigMap -metadata: - name: dcgm-config - namespace: monitoring -data: - dcp-metrics-included.csv: | - # Format: - # DCGM_FI_DEV_, , - DCGM_FI_DEV_GPU_UTIL, GPU utilization, % - DCGM_FI_DEV_MEM_COPY_UTIL, Memory utilization, % - DCGM_FI_DEV_FB_FREE, Framebuffer memory free, MiB - DCGM_FI_DEV_FB_USED, Framebuffer memory used, MiB - DCGM_FI_DEV_FB_TOTAL, Framebuffer memory total, MiB - DCGM_FI_DEV_GPU_TEMP, GPU temperature, C - DCGM_FI_DEV_POWER_USAGE, Power usage, W - DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION, Total energy consumption, mJ - DCGM_FI_DEV_PCIE_REPLAY_COUNTER, PCIe replay counter, count - DCGM_FI_DEV_PCIE_TX_THROUGHPUT, PCIe transmit throughput, KiB/s - DCGM_FI_DEV_PCIE_RX_THROUGHPUT, PCIe receive throughput, KiB/s - DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL, NVLink bandwidth total, KiB/s - DCGM_FI_DEV_VGPU_LICENSE_STATUS, vGPU license status, N/A - DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS, Uncorrectable remapped rows, count - DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS, Correctable remapped rows, count - DCGM_FI_DEV_ROW_REMAP_FAILURE, Row remap failure, count - DCGM_FI_DEV_XID_ERRORS, XID errors, count - DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_TOTAL, NVLink CRC flit error count total, count - DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_TOTAL, NVLink CRC data error count total, count - DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_TOTAL, NVLink replay error count total, count - DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_TOTAL, NVLink recovery error count total, count - DCGM_FI_DEV_RETIRED_PAGES_SBE, Retired pages SBE, count - DCGM_FI_DEV_RETIRED_PAGES_DBE, Retired pages DBE, count - DCGM_FI_DEV_RETIRED_PAGES_PENDING, Retired pages pending, count - DCGM_FI_DEV_GRAPHICS_PIDS, Graphics processes, count - DCGM_FI_DEV_COMPUTE_PIDS, Compute processes, count ---- -# NVIDIA DCGM Exporter Service -apiVersion: v1 -kind: Service -metadata: - name: dcgm-exporter - namespace: monitoring - labels: - app: dcgm-exporter - annotations: - prometheus.io/scrape: 'true' - prometheus.io/port: '9400' -spec: - selector: - app: dcgm-exporter - ports: - - port: 9400 - targetPort: 9400 - name: metrics - type: ClusterIP diff --git a/docs/source/distributions/k8s/prometheus-rbac.yaml b/docs/source/distributions/k8s/prometheus-rbac.yaml deleted file mode 100644 index 703eb3e5b..000000000 --- a/docs/source/distributions/k8s/prometheus-rbac.yaml +++ /dev/null @@ -1,41 +0,0 @@ ---- -apiVersion: v1 -kind: ServiceAccount -metadata: - name: prometheus - namespace: monitoring ---- -apiVersion: rbac.authorization.k8s.io/v1 -kind: ClusterRole -metadata: - name: prometheus -rules: -- apiGroups: [""] - resources: - - nodes - - nodes/proxy - - services - - endpoints - - pods - verbs: ["get", "list", "watch"] -- apiGroups: - - extensions - - networking.k8s.io - resources: - - ingresses - verbs: ["get", "list", "watch"] -- nonResourceURLs: ["/metrics"] - verbs: ["get"] ---- -apiVersion: rbac.authorization.k8s.io/v1 -kind: ClusterRoleBinding -metadata: - name: prometheus -roleRef: - apiGroup: rbac.authorization.k8s.io - kind: ClusterRole - name: prometheus -subjects: -- kind: ServiceAccount - name: prometheus - namespace: monitoring diff --git a/docs/source/distributions/k8s/svc-and-pods.yaml b/docs/source/distributions/k8s/svc-and-pods.yaml new file mode 100644 index 000000000..51ca62fa1 --- /dev/null +++ b/docs/source/distributions/k8s/svc-and-pods.yaml @@ -0,0 +1,2274 @@ +apiVersion: v1 +items: +- apiVersion: v1 + kind: Service + metadata: + creationTimestamp: "2025-08-02T20:01:52Z" + labels: + managed-by: prometheus-operator + operated-alertmanager: "true" + name: alertmanager-operated + namespace: prometheus + ownerReferences: + - apiVersion: monitoring.coreos.com/v1 + kind: Alertmanager + name: kube-prometheus-stack-1754-alertmanager + uid: 37e64ef7-78b0-485a-9c86-e4e83188d868 + resourceVersion: "93640374" + uid: 9a4a4644-e7fd-40b5-b14b-fb0055e37cee + spec: + clusterIP: None + clusterIPs: + - None + internalTrafficPolicy: Cluster + ipFamilies: + - IPv4 + ipFamilyPolicy: SingleStack + ports: + - name: http-web + port: 9093 + protocol: TCP + targetPort: http-web + - name: tcp-mesh + port: 9094 + protocol: TCP + targetPort: 9094 + - name: udp-mesh + port: 9094 + protocol: UDP + targetPort: 9094 + publishNotReadyAddresses: true + selector: + app.kubernetes.io/name: alertmanager + sessionAffinity: None + type: ClusterIP + status: + loadBalancer: {} +- apiVersion: v1 + kind: Service + metadata: + annotations: + meta.helm.sh/release-name: kube-prometheus-stack-1754164871 + meta.helm.sh/release-namespace: prometheus + creationTimestamp: "2025-08-02T20:01:49Z" + labels: + app: kube-prometheus-stack-alertmanager + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/part-of: kube-prometheus-stack + app.kubernetes.io/version: 75.15.1 + chart: kube-prometheus-stack-75.15.1 + heritage: Helm + release: kube-prometheus-stack-1754164871 + self-monitor: "true" + name: kube-prometheus-stack-1754-alertmanager + namespace: prometheus + resourceVersion: "93640183" + uid: 552a7228-3b1d-4dd8-abd7-f491f365a295 + spec: + clusterIP: 10.100.154.228 + clusterIPs: + - 10.100.154.228 + internalTrafficPolicy: Cluster + ipFamilies: + - IPv4 + ipFamilyPolicy: SingleStack + ports: + - name: http-web + port: 9093 + protocol: TCP + targetPort: 9093 + - appProtocol: http + name: reloader-web + port: 8080 + protocol: TCP + targetPort: reloader-web + selector: + alertmanager: kube-prometheus-stack-1754-alertmanager + app.kubernetes.io/name: alertmanager + sessionAffinity: None + type: ClusterIP + status: + loadBalancer: {} +- apiVersion: v1 + kind: Service + metadata: + annotations: + meta.helm.sh/release-name: kube-prometheus-stack-1754164871 + meta.helm.sh/release-namespace: prometheus + creationTimestamp: "2025-08-02T20:01:49Z" + labels: + app: kube-prometheus-stack-operator + app.kubernetes.io/component: prometheus-operator + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/part-of: kube-prometheus-stack + app.kubernetes.io/version: 75.15.1 + chart: kube-prometheus-stack-75.15.1 + heritage: Helm + release: kube-prometheus-stack-1754164871 + name: kube-prometheus-stack-1754-operator + namespace: prometheus + resourceVersion: "93640195" + uid: 240740e2-b4d2-4a14-a52d-7f73a93256c0 + spec: + clusterIP: 10.100.175.188 + clusterIPs: + - 10.100.175.188 + internalTrafficPolicy: Cluster + ipFamilies: + - IPv4 + ipFamilyPolicy: SingleStack + ports: + - name: https + port: 443 + protocol: TCP + targetPort: https + selector: + app: kube-prometheus-stack-operator + release: kube-prometheus-stack-1754164871 + sessionAffinity: None + type: ClusterIP + status: + loadBalancer: {} +- apiVersion: v1 + kind: Service + metadata: + annotations: + meta.helm.sh/release-name: kube-prometheus-stack-1754164871 + meta.helm.sh/release-namespace: prometheus + creationTimestamp: "2025-08-02T20:01:49Z" + labels: + app: kube-prometheus-stack-prometheus + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/part-of: kube-prometheus-stack + app.kubernetes.io/version: 75.15.1 + chart: kube-prometheus-stack-75.15.1 + heritage: Helm + release: kube-prometheus-stack-1754164871 + self-monitor: "true" + name: kube-prometheus-stack-1754-prometheus + namespace: prometheus + resourceVersion: "93640192" + uid: ce5f1fd7-e1a7-4656-b01b-1abf881246bd + spec: + clusterIP: 10.100.64.119 + clusterIPs: + - 10.100.64.119 + externalTrafficPolicy: Cluster + internalTrafficPolicy: Cluster + ipFamilies: + - IPv4 + ipFamilyPolicy: SingleStack + ports: + - name: http-web + nodePort: 30090 + port: 9090 + protocol: TCP + targetPort: 9090 + - appProtocol: http + name: reloader-web + nodePort: 30588 + port: 8080 + protocol: TCP + targetPort: reloader-web + selector: + app.kubernetes.io/name: prometheus + operator.prometheus.io/name: kube-prometheus-stack-1754-prometheus + sessionAffinity: None + type: NodePort + status: + loadBalancer: {} +- apiVersion: v1 + kind: Service + metadata: + annotations: + meta.helm.sh/release-name: kube-prometheus-stack-1754164871 + meta.helm.sh/release-namespace: prometheus + creationTimestamp: "2025-08-02T20:01:49Z" + labels: + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/name: grafana + app.kubernetes.io/version: 12.1.0 + helm.sh/chart: grafana-9.3.0 + name: kube-prometheus-stack-1754164871-grafana + namespace: prometheus + resourceVersion: "93643729" + uid: 49a69113-710e-4750-aa03-7c72e1306cf8 + spec: + clusterIP: 10.100.18.230 + clusterIPs: + - 10.100.18.230 + externalTrafficPolicy: Cluster + internalTrafficPolicy: Cluster + ipFamilies: + - IPv4 + ipFamilyPolicy: SingleStack + ports: + - name: http-web + nodePort: 31509 + port: 80 + protocol: TCP + targetPort: 3000 + selector: + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/name: grafana + sessionAffinity: None + type: NodePort + status: + loadBalancer: {} +- apiVersion: v1 + kind: Service + metadata: + annotations: + meta.helm.sh/release-name: kube-prometheus-stack-1754164871 + meta.helm.sh/release-namespace: prometheus + creationTimestamp: "2025-08-02T20:01:49Z" + labels: + app.kubernetes.io/component: metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/version: 2.16.0 + helm.sh/chart: kube-state-metrics-6.1.0 + release: kube-prometheus-stack-1754164871 + name: kube-prometheus-stack-1754164871-kube-state-metrics + namespace: prometheus + resourceVersion: "93640202" + uid: 3fcd1cf8-7218-4624-bcde-563ef0b4c809 + spec: + clusterIP: 10.100.158.39 + clusterIPs: + - 10.100.158.39 + internalTrafficPolicy: Cluster + ipFamilies: + - IPv4 + ipFamilyPolicy: SingleStack + ports: + - name: http + port: 8080 + protocol: TCP + targetPort: 8080 + selector: + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/name: kube-state-metrics + sessionAffinity: None + type: ClusterIP + status: + loadBalancer: {} +- apiVersion: v1 + kind: Service + metadata: + annotations: + meta.helm.sh/release-name: kube-prometheus-stack-1754164871 + meta.helm.sh/release-namespace: prometheus + prometheus.io/scrape: "true" + creationTimestamp: "2025-08-02T20:01:49Z" + labels: + app.kubernetes.io/component: metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/version: 1.9.1 + helm.sh/chart: prometheus-node-exporter-4.47.3 + jobLabel: node-exporter + release: kube-prometheus-stack-1754164871 + name: kube-prometheus-stack-1754164871-prometheus-node-exporter + namespace: prometheus + resourceVersion: "93640189" + uid: 36ceaa10-3544-4d2a-92bb-9d839a0a0dbc + spec: + clusterIP: 10.100.153.18 + clusterIPs: + - 10.100.153.18 + internalTrafficPolicy: Cluster + ipFamilies: + - IPv4 + ipFamilyPolicy: SingleStack + ports: + - name: http-metrics + port: 9100 + protocol: TCP + targetPort: 9100 + selector: + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/name: prometheus-node-exporter + sessionAffinity: None + type: ClusterIP + status: + loadBalancer: {} +- apiVersion: v1 + kind: Service + metadata: + creationTimestamp: "2025-08-02T20:01:52Z" + labels: + managed-by: prometheus-operator + operated-prometheus: "true" + name: prometheus-operated + namespace: prometheus + ownerReferences: + - apiVersion: monitoring.coreos.com/v1 + kind: Prometheus + name: kube-prometheus-stack-1754-prometheus + uid: f76b5a30-c66c-4d0b-b4ec-0854154752ba + resourceVersion: "93640390" + uid: c98da91f-e91c-454c-b8be-ac5471bd94a0 + spec: + clusterIP: None + clusterIPs: + - None + internalTrafficPolicy: Cluster + ipFamilies: + - IPv4 + ipFamilyPolicy: SingleStack + ports: + - name: http-web + port: 9090 + protocol: TCP + targetPort: http-web + selector: + app.kubernetes.io/name: prometheus + sessionAffinity: None + type: ClusterIP + status: + loadBalancer: {} +- apiVersion: v1 + kind: Pod + metadata: + annotations: + kubectl.kubernetes.io/default-container: alertmanager + creationTimestamp: "2025-08-02T20:01:52Z" + generateName: alertmanager-kube-prometheus-stack-1754-alertmanager- + labels: + alertmanager: kube-prometheus-stack-1754-alertmanager + app.kubernetes.io/instance: kube-prometheus-stack-1754-alertmanager + app.kubernetes.io/managed-by: prometheus-operator + app.kubernetes.io/name: alertmanager + app.kubernetes.io/version: 0.28.1 + apps.kubernetes.io/pod-index: "0" + controller-revision-hash: alertmanager-kube-prometheus-stack-1754-alertmanager-7677c479d + statefulset.kubernetes.io/pod-name: alertmanager-kube-prometheus-stack-1754-alertmanager-0 + name: alertmanager-kube-prometheus-stack-1754-alertmanager-0 + namespace: prometheus + ownerReferences: + - apiVersion: apps/v1 + blockOwnerDeletion: true + controller: true + kind: StatefulSet + name: alertmanager-kube-prometheus-stack-1754-alertmanager + uid: 5f535039-e58c-49d0-972f-e1c916e59fe2 + resourceVersion: "93640559" + uid: 87515b5e-8797-423e-ad3a-475082c2f928 + spec: + affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchExpressions: + - key: app.kubernetes.io/name + operator: In + values: + - alertmanager + - key: alertmanager + operator: In + values: + - kube-prometheus-stack-1754-alertmanager + topologyKey: kubernetes.io/hostname + weight: 100 + automountServiceAccountToken: true + containers: + - args: + - --config.file=/etc/alertmanager/config_out/alertmanager.env.yaml + - --storage.path=/alertmanager + - --data.retention=120h + - --cluster.listen-address= + - --web.listen-address=:9093 + - --web.external-url=http://kube-prometheus-stack-1754-alertmanager.prometheus:9093 + - --web.route-prefix=/ + - --cluster.label=prometheus/kube-prometheus-stack-1754-alertmanager + - --cluster.peer=alertmanager-kube-prometheus-stack-1754-alertmanager-0.alertmanager-operated:9094 + - --cluster.reconnect-timeout=5m + - --web.config.file=/etc/alertmanager/web_config/web-config.yaml + env: + - name: POD_IP + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: status.podIP + image: quay.io/prometheus/alertmanager:v0.28.1 + imagePullPolicy: IfNotPresent + livenessProbe: + failureThreshold: 10 + httpGet: + path: /-/healthy + port: http-web + scheme: HTTP + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 3 + name: alertmanager + ports: + - containerPort: 9093 + name: http-web + protocol: TCP + - containerPort: 9094 + name: mesh-tcp + protocol: TCP + - containerPort: 9094 + name: mesh-udp + protocol: UDP + readinessProbe: + failureThreshold: 10 + httpGet: + path: /-/ready + port: http-web + scheme: HTTP + initialDelaySeconds: 3 + periodSeconds: 5 + successThreshold: 1 + timeoutSeconds: 3 + resources: + requests: + memory: 200Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: FallbackToLogsOnError + volumeMounts: + - mountPath: /etc/alertmanager/config + name: config-volume + - mountPath: /etc/alertmanager/config_out + name: config-out + readOnly: true + - mountPath: /etc/alertmanager/certs + name: tls-assets + readOnly: true + - mountPath: /alertmanager + name: alertmanager-kube-prometheus-stack-1754-alertmanager-db + - mountPath: /etc/alertmanager/web_config/web-config.yaml + name: web-config + readOnly: true + subPath: web-config.yaml + - mountPath: /etc/alertmanager/cluster_tls_config/cluster-tls-config.yaml + name: cluster-tls-config + readOnly: true + subPath: cluster-tls-config.yaml + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-nl55p + readOnly: true + - args: + - --listen-address=:8080 + - --web-config-file=/etc/alertmanager/web_config/web-config.yaml + - --reload-url=http://127.0.0.1:9093/-/reload + - --config-file=/etc/alertmanager/config/alertmanager.yaml.gz + - --config-envsubst-file=/etc/alertmanager/config_out/alertmanager.env.yaml + - --watched-dir=/etc/alertmanager/config + command: + - /bin/prometheus-config-reloader + env: + - name: POD_NAME + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: metadata.name + - name: SHARD + value: "-1" + image: quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0 + imagePullPolicy: IfNotPresent + name: config-reloader + ports: + - containerPort: 8080 + name: reloader-web + protocol: TCP + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: FallbackToLogsOnError + volumeMounts: + - mountPath: /etc/alertmanager/config + name: config-volume + readOnly: true + - mountPath: /etc/alertmanager/config_out + name: config-out + - mountPath: /etc/alertmanager/web_config/web-config.yaml + name: web-config + readOnly: true + subPath: web-config.yaml + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-nl55p + readOnly: true + dnsPolicy: ClusterFirst + enableServiceLinks: true + hostname: alertmanager-kube-prometheus-stack-1754-alertmanager-0 + initContainers: + - args: + - --watch-interval=0 + - --listen-address=:8081 + - --config-file=/etc/alertmanager/config/alertmanager.yaml.gz + - --config-envsubst-file=/etc/alertmanager/config_out/alertmanager.env.yaml + - --watched-dir=/etc/alertmanager/config + command: + - /bin/prometheus-config-reloader + env: + - name: POD_NAME + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: metadata.name + - name: SHARD + value: "-1" + image: quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0 + imagePullPolicy: IfNotPresent + name: init-config-reloader + ports: + - containerPort: 8081 + name: reloader-web + protocol: TCP + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: FallbackToLogsOnError + volumeMounts: + - mountPath: /etc/alertmanager/config + name: config-volume + readOnly: true + - mountPath: /etc/alertmanager/config_out + name: config-out + - mountPath: /etc/alertmanager/web_config/web-config.yaml + name: web-config + readOnly: true + subPath: web-config.yaml + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-nl55p + readOnly: true + nodeName: ip-172-33-32-41.us-west-2.compute.internal + preemptionPolicy: PreemptLowerPriority + priority: 0 + restartPolicy: Always + schedulerName: default-scheduler + securityContext: + fsGroup: 2000 + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + seccompProfile: + type: RuntimeDefault + serviceAccount: kube-prometheus-stack-1754-alertmanager + serviceAccountName: kube-prometheus-stack-1754-alertmanager + subdomain: alertmanager-operated + terminationGracePeriodSeconds: 120 + tolerations: + - effect: NoExecute + key: node.kubernetes.io/not-ready + operator: Exists + tolerationSeconds: 300 + - effect: NoExecute + key: node.kubernetes.io/unreachable + operator: Exists + tolerationSeconds: 300 + volumes: + - name: config-volume + secret: + defaultMode: 420 + secretName: alertmanager-kube-prometheus-stack-1754-alertmanager-generated + - name: tls-assets + projected: + defaultMode: 420 + sources: + - secret: + name: alertmanager-kube-prometheus-stack-1754-alertmanager-tls-assets-0 + - emptyDir: + medium: Memory + name: config-out + - name: web-config + secret: + defaultMode: 420 + secretName: alertmanager-kube-prometheus-stack-1754-alertmanager-web-config + - name: cluster-tls-config + secret: + defaultMode: 420 + secretName: alertmanager-kube-prometheus-stack-1754-alertmanager-cluster-tls-config + - emptyDir: {} + name: alertmanager-kube-prometheus-stack-1754-alertmanager-db + - name: kube-api-access-nl55p + projected: + defaultMode: 420 + sources: + - serviceAccountToken: + expirationSeconds: 3607 + path: token + - configMap: + items: + - key: ca.crt + path: ca.crt + name: kube-root-ca.crt + - downwardAPI: + items: + - fieldRef: + apiVersion: v1 + fieldPath: metadata.namespace + path: namespace + status: + conditions: + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:54Z" + status: "True" + type: PodReadyToStartContainers + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:56Z" + status: "True" + type: Initialized + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:02:02Z" + status: "True" + type: Ready + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:02:02Z" + status: "True" + type: ContainersReady + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:52Z" + status: "True" + type: PodScheduled + containerStatuses: + - containerID: containerd://194f0a60e4b5062f6a7cf9a06906132d0b0edb5971121ac2374ffd9e4ab189d9 + image: quay.io/prometheus/alertmanager:v0.28.1 + imageID: quay.io/prometheus/alertmanager@sha256:27c475db5fb156cab31d5c18a4251ac7ed567746a2483ff264516437a39b15ba + lastState: {} + name: alertmanager + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:01:58Z" + volumeMounts: + - mountPath: /etc/alertmanager/config + name: config-volume + - mountPath: /etc/alertmanager/config_out + name: config-out + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /etc/alertmanager/certs + name: tls-assets + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /alertmanager + name: alertmanager-kube-prometheus-stack-1754-alertmanager-db + - mountPath: /etc/alertmanager/web_config/web-config.yaml + name: web-config + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /etc/alertmanager/cluster_tls_config/cluster-tls-config.yaml + name: cluster-tls-config + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-nl55p + readOnly: true + recursiveReadOnly: Disabled + - containerID: containerd://c2bb73168093a0fcd50da24d316874aa1190fcc36f21f61581cd404dc1c3b79f + image: quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0 + imageID: quay.io/prometheus-operator/prometheus-config-reloader@sha256:78aec597d87aa2b4ba947ab9190538dae93a58a67b8e930aefea1086534b02ef + lastState: {} + name: config-reloader + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:01:58Z" + volumeMounts: + - mountPath: /etc/alertmanager/config + name: config-volume + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /etc/alertmanager/config_out + name: config-out + - mountPath: /etc/alertmanager/web_config/web-config.yaml + name: web-config + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-nl55p + readOnly: true + recursiveReadOnly: Disabled + hostIP: 172.33.32.41 + hostIPs: + - ip: 172.33.32.41 + initContainerStatuses: + - containerID: containerd://f8cac5cdbb6a72d8c8a85888059863eb716d42c3a090588042418e233f67d027 + image: quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0 + imageID: quay.io/prometheus-operator/prometheus-config-reloader@sha256:78aec597d87aa2b4ba947ab9190538dae93a58a67b8e930aefea1086534b02ef + lastState: {} + name: init-config-reloader + ready: true + restartCount: 0 + started: false + state: + terminated: + containerID: containerd://f8cac5cdbb6a72d8c8a85888059863eb716d42c3a090588042418e233f67d027 + exitCode: 0 + finishedAt: "2025-08-02T20:01:54Z" + reason: Completed + startedAt: "2025-08-02T20:01:54Z" + volumeMounts: + - mountPath: /etc/alertmanager/config + name: config-volume + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /etc/alertmanager/config_out + name: config-out + - mountPath: /etc/alertmanager/web_config/web-config.yaml + name: web-config + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-nl55p + readOnly: true + recursiveReadOnly: Disabled + phase: Running + podIP: 172.33.46.59 + podIPs: + - ip: 172.33.46.59 + qosClass: Burstable + startTime: "2025-08-02T20:01:52Z" +- apiVersion: v1 + kind: Pod + metadata: + creationTimestamp: "2025-08-02T20:01:49Z" + generateName: kube-prometheus-stack-1754-operator-57d8448ffc- + labels: + app: kube-prometheus-stack-operator + app.kubernetes.io/component: prometheus-operator + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator + app.kubernetes.io/part-of: kube-prometheus-stack + app.kubernetes.io/version: 75.15.1 + chart: kube-prometheus-stack-75.15.1 + heritage: Helm + pod-template-hash: 57d8448ffc + release: kube-prometheus-stack-1754164871 + name: kube-prometheus-stack-1754-operator-57d8448ffc-zkxrs + namespace: prometheus + ownerReferences: + - apiVersion: apps/v1 + blockOwnerDeletion: true + controller: true + kind: ReplicaSet + name: kube-prometheus-stack-1754-operator-57d8448ffc + uid: f323c763-7775-4cb7-af35-996f6dbe58c5 + resourceVersion: "93640436" + uid: 7920b221-bd8e-4b25-984a-c4fe4ffff94d + spec: + automountServiceAccountToken: true + containers: + - args: + - --kubelet-service=kube-system/kube-prometheus-stack-1754-kubelet + - --kubelet-endpoints=true + - --kubelet-endpointslice=false + - --localhost=127.0.0.1 + - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0 + - --config-reloader-cpu-request=0 + - --config-reloader-cpu-limit=0 + - --config-reloader-memory-request=0 + - --config-reloader-memory-limit=0 + - --thanos-default-base-image=quay.io/thanos/thanos:v0.39.2 + - --secret-field-selector=type!=kubernetes.io/dockercfg,type!=kubernetes.io/service-account-token,type!=helm.sh/release.v1 + - --web.enable-tls=true + - --web.cert-file=/cert/cert + - --web.key-file=/cert/key + - --web.listen-address=:10250 + - --web.tls-min-version=VersionTLS13 + env: + - name: GOGC + value: "30" + image: quay.io/prometheus-operator/prometheus-operator:v0.83.0 + imagePullPolicy: IfNotPresent + livenessProbe: + failureThreshold: 3 + httpGet: + path: /healthz + port: https + scheme: HTTPS + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + name: kube-prometheus-stack + ports: + - containerPort: 10250 + name: https + protocol: TCP + readinessProbe: + failureThreshold: 3 + httpGet: + path: /healthz + port: https + scheme: HTTPS + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: File + volumeMounts: + - mountPath: /cert + name: tls-secret + readOnly: true + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-7qbvh + readOnly: true + dnsPolicy: ClusterFirst + enableServiceLinks: true + nodeName: ip-172-33-32-41.us-west-2.compute.internal + preemptionPolicy: PreemptLowerPriority + priority: 0 + restartPolicy: Always + schedulerName: default-scheduler + securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + seccompProfile: + type: RuntimeDefault + serviceAccount: kube-prometheus-stack-1754-operator + serviceAccountName: kube-prometheus-stack-1754-operator + terminationGracePeriodSeconds: 30 + tolerations: + - effect: NoExecute + key: node.kubernetes.io/not-ready + operator: Exists + tolerationSeconds: 300 + - effect: NoExecute + key: node.kubernetes.io/unreachable + operator: Exists + tolerationSeconds: 300 + volumes: + - name: tls-secret + secret: + defaultMode: 420 + secretName: kube-prometheus-stack-1754-admission + - name: kube-api-access-7qbvh + projected: + defaultMode: 420 + sources: + - serviceAccountToken: + expirationSeconds: 3607 + path: token + - configMap: + items: + - key: ca.crt + path: ca.crt + name: kube-root-ca.crt + - downwardAPI: + items: + - fieldRef: + apiVersion: v1 + fieldPath: metadata.namespace + path: namespace + status: + conditions: + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:52Z" + status: "True" + type: PodReadyToStartContainers + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:49Z" + status: "True" + type: Initialized + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:53Z" + status: "True" + type: Ready + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:53Z" + status: "True" + type: ContainersReady + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:49Z" + status: "True" + type: PodScheduled + containerStatuses: + - containerID: containerd://072cc3d39cda99ab1807a732bb2524dddefb0f8f1386f0aebbffe5a4ec9a1283 + image: quay.io/prometheus-operator/prometheus-operator:v0.83.0 + imageID: quay.io/prometheus-operator/prometheus-operator@sha256:b6a89b8ec08f4cca759b2d579e8545f97ffb897973fcd68148c153f2e936c8b3 + lastState: {} + name: kube-prometheus-stack + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:01:51Z" + volumeMounts: + - mountPath: /cert + name: tls-secret + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-7qbvh + readOnly: true + recursiveReadOnly: Disabled + hostIP: 172.33.32.41 + hostIPs: + - ip: 172.33.32.41 + phase: Running + podIP: 172.33.54.157 + podIPs: + - ip: 172.33.54.157 + qosClass: BestEffort + startTime: "2025-08-02T20:01:49Z" +- apiVersion: v1 + kind: Pod + metadata: + annotations: + checksum/config: 0e9cbd0ea8e24e32f7dfca5bab17a2ba05652642f0a09a4882833ae88e4cc4a3 + checksum/sc-dashboard-provider-config: e70bf6a851099d385178a76de9757bb0bef8299da6d8443602590e44f05fdf24 + checksum/secret: 032056e9c62bbe9d1daa41ee49cd3d9524c076f51ca4c65adadf4ef08ef28712 + kubectl.kubernetes.io/default-container: grafana + creationTimestamp: "2025-08-02T20:01:49Z" + generateName: kube-prometheus-stack-1754164871-grafana-85445fd75f- + labels: + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/name: grafana + app.kubernetes.io/version: 12.1.0 + helm.sh/chart: grafana-9.3.0 + pod-template-hash: 85445fd75f + name: kube-prometheus-stack-1754164871-grafana-85445fd75f-4sc65 + namespace: prometheus + ownerReferences: + - apiVersion: apps/v1 + blockOwnerDeletion: true + controller: true + kind: ReplicaSet + name: kube-prometheus-stack-1754164871-grafana-85445fd75f + uid: 8dd3307e-8b75-47c7-ac66-e03eb22764f5 + resourceVersion: "93640642" + uid: c49e9c23-10b3-4c45-b6de-a9d388d3022a + spec: + automountServiceAccountToken: true + containers: + - env: + - name: METHOD + value: WATCH + - name: LABEL + value: grafana_dashboard + - name: LABEL_VALUE + value: "1" + - name: FOLDER + value: /tmp/dashboards + - name: RESOURCE + value: both + - name: NAMESPACE + value: ALL + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + key: admin-user + name: kube-prometheus-stack-1754164871-grafana + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + key: admin-password + name: kube-prometheus-stack-1754164871-grafana + - name: REQ_URL + value: http://localhost:3000/api/admin/provisioning/dashboards/reload + - name: REQ_METHOD + value: POST + image: quay.io/kiwigrid/k8s-sidecar:1.30.3 + imagePullPolicy: IfNotPresent + name: grafana-sc-dashboard + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: File + volumeMounts: + - mountPath: /tmp/dashboards + name: sc-dashboard-volume + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-cdhhf + readOnly: true + - env: + - name: METHOD + value: WATCH + - name: LABEL + value: grafana_datasource + - name: LABEL_VALUE + value: "1" + - name: FOLDER + value: /etc/grafana/provisioning/datasources + - name: RESOURCE + value: both + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + key: admin-user + name: kube-prometheus-stack-1754164871-grafana + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + key: admin-password + name: kube-prometheus-stack-1754164871-grafana + - name: REQ_URL + value: http://localhost:3000/api/admin/provisioning/datasources/reload + - name: REQ_METHOD + value: POST + image: quay.io/kiwigrid/k8s-sidecar:1.30.3 + imagePullPolicy: IfNotPresent + name: grafana-sc-datasources + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: File + volumeMounts: + - mountPath: /etc/grafana/provisioning/datasources + name: sc-datasources-volume + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-cdhhf + readOnly: true + - env: + - name: POD_IP + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: status.podIP + - name: GF_SECURITY_ADMIN_USER + valueFrom: + secretKeyRef: + key: admin-user + name: kube-prometheus-stack-1754164871-grafana + - name: GF_SECURITY_ADMIN_PASSWORD + valueFrom: + secretKeyRef: + key: admin-password + name: kube-prometheus-stack-1754164871-grafana + - name: GF_PATHS_DATA + value: /var/lib/grafana/ + - name: GF_PATHS_LOGS + value: /var/log/grafana + - name: GF_PATHS_PLUGINS + value: /var/lib/grafana/plugins + - name: GF_PATHS_PROVISIONING + value: /etc/grafana/provisioning + image: docker.io/grafana/grafana:12.1.0 + imagePullPolicy: IfNotPresent + livenessProbe: + failureThreshold: 10 + httpGet: + path: /api/health + port: 3000 + scheme: HTTP + initialDelaySeconds: 60 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 30 + name: grafana + ports: + - containerPort: 3000 + name: grafana + protocol: TCP + - containerPort: 9094 + name: gossip-tcp + protocol: TCP + - containerPort: 9094 + name: gossip-udp + protocol: UDP + - containerPort: 6060 + name: profiling + protocol: TCP + readinessProbe: + failureThreshold: 3 + httpGet: + path: /api/health + port: 3000 + scheme: HTTP + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: File + volumeMounts: + - mountPath: /etc/grafana/grafana.ini + name: config + subPath: grafana.ini + - mountPath: /var/lib/grafana + name: storage + - mountPath: /tmp/dashboards + name: sc-dashboard-volume + - mountPath: /etc/grafana/provisioning/dashboards/sc-dashboardproviders.yaml + name: sc-dashboard-provider + subPath: provider.yaml + - mountPath: /etc/grafana/provisioning/datasources + name: sc-datasources-volume + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-cdhhf + readOnly: true + dnsPolicy: ClusterFirst + enableServiceLinks: true + nodeName: ip-172-33-32-41.us-west-2.compute.internal + preemptionPolicy: PreemptLowerPriority + priority: 0 + restartPolicy: Always + schedulerName: default-scheduler + securityContext: + fsGroup: 472 + runAsGroup: 472 + runAsNonRoot: true + runAsUser: 472 + serviceAccount: kube-prometheus-stack-1754164871-grafana + serviceAccountName: kube-prometheus-stack-1754164871-grafana + shareProcessNamespace: false + terminationGracePeriodSeconds: 30 + tolerations: + - effect: NoExecute + key: node.kubernetes.io/not-ready + operator: Exists + tolerationSeconds: 300 + - effect: NoExecute + key: node.kubernetes.io/unreachable + operator: Exists + tolerationSeconds: 300 + volumes: + - configMap: + defaultMode: 420 + name: kube-prometheus-stack-1754164871-grafana + name: config + - emptyDir: {} + name: storage + - emptyDir: {} + name: sc-dashboard-volume + - configMap: + defaultMode: 420 + name: kube-prometheus-stack-1754164871-grafana-config-dashboards + name: sc-dashboard-provider + - emptyDir: {} + name: sc-datasources-volume + - name: kube-api-access-cdhhf + projected: + defaultMode: 420 + sources: + - serviceAccountToken: + expirationSeconds: 3607 + path: token + - configMap: + items: + - key: ca.crt + path: ca.crt + name: kube-root-ca.crt + - downwardAPI: + items: + - fieldRef: + apiVersion: v1 + fieldPath: metadata.namespace + path: namespace + status: + conditions: + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:02:02Z" + status: "True" + type: PodReadyToStartContainers + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:49Z" + status: "True" + type: Initialized + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:02:09Z" + status: "True" + type: Ready + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:02:09Z" + status: "True" + type: ContainersReady + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:49Z" + status: "True" + type: PodScheduled + containerStatuses: + - containerID: containerd://114d989a3b87c0a9005a04b7661adf5ba4be8392d2dd2571d00e5c3450c38d6f + image: docker.io/grafana/grafana:12.1.0 + imageID: docker.io/grafana/grafana@sha256:6ac590e7cabc2fbe8d7b8fc1ce9c9f0582177b334e0df9c927ebd9670469440f + lastState: {} + name: grafana + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:02:02Z" + volumeMounts: + - mountPath: /etc/grafana/grafana.ini + name: config + - mountPath: /var/lib/grafana + name: storage + - mountPath: /tmp/dashboards + name: sc-dashboard-volume + - mountPath: /etc/grafana/provisioning/dashboards/sc-dashboardproviders.yaml + name: sc-dashboard-provider + - mountPath: /etc/grafana/provisioning/datasources + name: sc-datasources-volume + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-cdhhf + readOnly: true + recursiveReadOnly: Disabled + - containerID: containerd://e640a53015faae291d56c699e4f0ec4862fba0a0e950eca4fa9ae7ec11253882 + image: quay.io/kiwigrid/k8s-sidecar:1.30.3 + imageID: quay.io/kiwigrid/k8s-sidecar@sha256:49dcce269568b1645b0050f296da787c99119647965229919a136614123f0627 + lastState: {} + name: grafana-sc-dashboard + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:01:52Z" + volumeMounts: + - mountPath: /tmp/dashboards + name: sc-dashboard-volume + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-cdhhf + readOnly: true + recursiveReadOnly: Disabled + - containerID: containerd://a56f9ccb98959cb6b8918592a1a7025d6711b7940fff48b5461a401812cbe124 + image: quay.io/kiwigrid/k8s-sidecar:1.30.3 + imageID: quay.io/kiwigrid/k8s-sidecar@sha256:49dcce269568b1645b0050f296da787c99119647965229919a136614123f0627 + lastState: {} + name: grafana-sc-datasources + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:01:52Z" + volumeMounts: + - mountPath: /etc/grafana/provisioning/datasources + name: sc-datasources-volume + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-cdhhf + readOnly: true + recursiveReadOnly: Disabled + hostIP: 172.33.32.41 + hostIPs: + - ip: 172.33.32.41 + phase: Running + podIP: 172.33.42.38 + podIPs: + - ip: 172.33.42.38 + qosClass: BestEffort + startTime: "2025-08-02T20:01:49Z" +- apiVersion: v1 + kind: Pod + metadata: + creationTimestamp: "2025-08-02T20:01:49Z" + generateName: kube-prometheus-stack-1754164871-kube-state-metrics-6cbcf68db6- + labels: + app.kubernetes.io/component: metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/version: 2.16.0 + helm.sh/chart: kube-state-metrics-6.1.0 + pod-template-hash: 6cbcf68db6 + release: kube-prometheus-stack-1754164871 + name: kube-prometheus-stack-1754164871-kube-state-metrics-6cbcf6r26h2 + namespace: prometheus + ownerReferences: + - apiVersion: apps/v1 + blockOwnerDeletion: true + controller: true + kind: ReplicaSet + name: kube-prometheus-stack-1754164871-kube-state-metrics-6cbcf68db6 + uid: 9608401d-ae24-4d58-9241-78edbe7db9c5 + resourceVersion: "93640531" + uid: 6e217ae5-4616-4431-97dc-3636cd49d37a + spec: + automountServiceAccountToken: true + containers: + - args: + - --port=8080 + - --resources=certificatesigningrequests,configmaps,cronjobs,daemonsets,deployments,endpoints,horizontalpodautoscalers,ingresses,jobs,leases,limitranges,mutatingwebhookconfigurations,namespaces,networkpolicies,nodes,persistentvolumeclaims,persistentvolumes,poddisruptionbudgets,pods,replicasets,replicationcontrollers,resourcequotas,secrets,services,statefulsets,storageclasses,validatingwebhookconfigurations,volumeattachments + image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.16.0 + imagePullPolicy: IfNotPresent + livenessProbe: + failureThreshold: 3 + httpGet: + path: /livez + port: 8080 + scheme: HTTP + initialDelaySeconds: 5 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 5 + name: kube-state-metrics + ports: + - containerPort: 8080 + name: http + protocol: TCP + readinessProbe: + failureThreshold: 3 + httpGet: + path: /readyz + port: 8081 + scheme: HTTP + initialDelaySeconds: 5 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 5 + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: File + volumeMounts: + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-4htkb + readOnly: true + dnsPolicy: ClusterFirst + enableServiceLinks: true + nodeName: ip-172-33-32-41.us-west-2.compute.internal + preemptionPolicy: PreemptLowerPriority + priority: 0 + restartPolicy: Always + schedulerName: default-scheduler + securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + seccompProfile: + type: RuntimeDefault + serviceAccount: kube-prometheus-stack-1754164871-kube-state-metrics + serviceAccountName: kube-prometheus-stack-1754164871-kube-state-metrics + terminationGracePeriodSeconds: 30 + tolerations: + - effect: NoExecute + key: node.kubernetes.io/not-ready + operator: Exists + tolerationSeconds: 300 + - effect: NoExecute + key: node.kubernetes.io/unreachable + operator: Exists + tolerationSeconds: 300 + volumes: + - name: kube-api-access-4htkb + projected: + defaultMode: 420 + sources: + - serviceAccountToken: + expirationSeconds: 3607 + path: token + - configMap: + items: + - key: ca.crt + path: ca.crt + name: kube-root-ca.crt + - downwardAPI: + items: + - fieldRef: + apiVersion: v1 + fieldPath: metadata.namespace + path: namespace + status: + conditions: + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:51Z" + status: "True" + type: PodReadyToStartContainers + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:49Z" + status: "True" + type: Initialized + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:59Z" + status: "True" + type: Ready + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:59Z" + status: "True" + type: ContainersReady + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:49Z" + status: "True" + type: PodScheduled + containerStatuses: + - containerID: containerd://9b193660e0e30060da4ef2c1df59c02f7d8a26ddbdd4754d2f70c002b162ddca + image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.16.0 + imageID: registry.k8s.io/kube-state-metrics/kube-state-metrics@sha256:e750cd4b43f782e3106537026c2995cac85d921aedea334e1d16caad7877c360 + lastState: {} + name: kube-state-metrics + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:01:50Z" + volumeMounts: + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-4htkb + readOnly: true + recursiveReadOnly: Disabled + hostIP: 172.33.32.41 + hostIPs: + - ip: 172.33.32.41 + phase: Running + podIP: 172.33.53.196 + podIPs: + - ip: 172.33.53.196 + qosClass: BestEffort + startTime: "2025-08-02T20:01:49Z" +- apiVersion: v1 + kind: Pod + metadata: + annotations: + cluster-autoscaler.kubernetes.io/safe-to-evict: "true" + creationTimestamp: "2025-08-02T20:01:49Z" + generateName: kube-prometheus-stack-1754164871-prometheus-node-exporter- + labels: + app.kubernetes.io/component: metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/version: 1.9.1 + controller-revision-hash: 8587f5b7cd + helm.sh/chart: prometheus-node-exporter-4.47.3 + jobLabel: node-exporter + pod-template-generation: "1" + release: kube-prometheus-stack-1754164871 + name: kube-prometheus-stack-1754164871-prometheus-node-exporter-6cr5d + namespace: prometheus + ownerReferences: + - apiVersion: apps/v1 + blockOwnerDeletion: true + controller: true + kind: DaemonSet + name: kube-prometheus-stack-1754164871-prometheus-node-exporter + uid: cc472f6b-fe45-47cb-a915-52e316494b41 + resourceVersion: "93640385" + uid: a815da5b-4963-4286-8d07-8eb975a37f1d + spec: + affinity: + nodeAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + nodeSelectorTerms: + - matchFields: + - key: metadata.name + operator: In + values: + - ip-172-33-17-181.us-west-2.compute.internal + automountServiceAccountToken: false + containers: + - args: + - --path.procfs=/host/proc + - --path.sysfs=/host/sys + - --path.rootfs=/host/root + - --path.udev.data=/host/root/run/udev/data + - --web.listen-address=[$(HOST_IP)]:9100 + - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/) + - --collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs|erofs)$ + env: + - name: HOST_IP + value: 0.0.0.0 + image: quay.io/prometheus/node-exporter:v1.9.1 + imagePullPolicy: IfNotPresent + livenessProbe: + failureThreshold: 3 + httpGet: + path: / + port: http-metrics + scheme: HTTP + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + name: node-exporter + ports: + - containerPort: 9100 + hostPort: 9100 + name: http-metrics + protocol: TCP + readinessProbe: + failureThreshold: 3 + httpGet: + path: / + port: http-metrics + scheme: HTTP + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + resources: {} + securityContext: + readOnlyRootFilesystem: true + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: File + volumeMounts: + - mountPath: /host/proc + name: proc + readOnly: true + - mountPath: /host/sys + name: sys + readOnly: true + - mountPath: /host/root + mountPropagation: HostToContainer + name: root + readOnly: true + dnsPolicy: ClusterFirst + enableServiceLinks: true + hostNetwork: true + hostPID: true + nodeName: ip-172-33-17-181.us-west-2.compute.internal + nodeSelector: + kubernetes.io/os: linux + preemptionPolicy: PreemptLowerPriority + priority: 0 + restartPolicy: Always + schedulerName: default-scheduler + securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + serviceAccount: kube-prometheus-stack-1754164871-prometheus-node-exporter + serviceAccountName: kube-prometheus-stack-1754164871-prometheus-node-exporter + terminationGracePeriodSeconds: 30 + tolerations: + - effect: NoSchedule + operator: Exists + - effect: NoExecute + key: node.kubernetes.io/not-ready + operator: Exists + - effect: NoExecute + key: node.kubernetes.io/unreachable + operator: Exists + - effect: NoSchedule + key: node.kubernetes.io/disk-pressure + operator: Exists + - effect: NoSchedule + key: node.kubernetes.io/memory-pressure + operator: Exists + - effect: NoSchedule + key: node.kubernetes.io/pid-pressure + operator: Exists + - effect: NoSchedule + key: node.kubernetes.io/unschedulable + operator: Exists + - effect: NoSchedule + key: node.kubernetes.io/network-unavailable + operator: Exists + volumes: + - hostPath: + path: /proc + type: "" + name: proc + - hostPath: + path: /sys + type: "" + name: sys + - hostPath: + path: / + type: "" + name: root + status: + conditions: + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:52Z" + status: "True" + type: PodReadyToStartContainers + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:49Z" + status: "True" + type: Initialized + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:52Z" + status: "True" + type: Ready + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:52Z" + status: "True" + type: ContainersReady + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:49Z" + status: "True" + type: PodScheduled + containerStatuses: + - containerID: containerd://e2168bde6ec19ec96668a460597bf7ffe51e3a8c731f93b6d9e1cfc5dc139f70 + image: quay.io/prometheus/node-exporter:v1.9.1 + imageID: quay.io/prometheus/node-exporter@sha256:d00a542e409ee618a4edc67da14dd48c5da66726bbd5537ab2af9c1dfc442c8a + lastState: {} + name: node-exporter + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:01:51Z" + volumeMounts: + - mountPath: /host/proc + name: proc + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /host/sys + name: sys + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /host/root + name: root + readOnly: true + recursiveReadOnly: Disabled + hostIP: 172.33.17.181 + hostIPs: + - ip: 172.33.17.181 + phase: Running + podIP: 172.33.17.181 + podIPs: + - ip: 172.33.17.181 + qosClass: BestEffort + startTime: "2025-08-02T20:01:49Z" +- apiVersion: v1 + kind: Pod + metadata: + annotations: + cluster-autoscaler.kubernetes.io/safe-to-evict: "true" + creationTimestamp: "2025-08-02T20:01:49Z" + generateName: kube-prometheus-stack-1754164871-prometheus-node-exporter- + labels: + app.kubernetes.io/component: metrics + app.kubernetes.io/instance: kube-prometheus-stack-1754164871 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/version: 1.9.1 + controller-revision-hash: 8587f5b7cd + helm.sh/chart: prometheus-node-exporter-4.47.3 + jobLabel: node-exporter + pod-template-generation: "1" + release: kube-prometheus-stack-1754164871 + name: kube-prometheus-stack-1754164871-prometheus-node-exporter-zhfng + namespace: prometheus + ownerReferences: + - apiVersion: apps/v1 + blockOwnerDeletion: true + controller: true + kind: DaemonSet + name: kube-prometheus-stack-1754164871-prometheus-node-exporter + uid: cc472f6b-fe45-47cb-a915-52e316494b41 + resourceVersion: "93640352" + uid: e52dc924-4e66-4571-ae7c-1f36b4ec2472 + spec: + affinity: + nodeAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + nodeSelectorTerms: + - matchFields: + - key: metadata.name + operator: In + values: + - ip-172-33-32-41.us-west-2.compute.internal + automountServiceAccountToken: false + containers: + - args: + - --path.procfs=/host/proc + - --path.sysfs=/host/sys + - --path.rootfs=/host/root + - --path.udev.data=/host/root/run/udev/data + - --web.listen-address=[$(HOST_IP)]:9100 + - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/) + - --collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs|erofs)$ + env: + - name: HOST_IP + value: 0.0.0.0 + image: quay.io/prometheus/node-exporter:v1.9.1 + imagePullPolicy: IfNotPresent + livenessProbe: + failureThreshold: 3 + httpGet: + path: / + port: http-metrics + scheme: HTTP + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + name: node-exporter + ports: + - containerPort: 9100 + hostPort: 9100 + name: http-metrics + protocol: TCP + readinessProbe: + failureThreshold: 3 + httpGet: + path: / + port: http-metrics + scheme: HTTP + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + resources: {} + securityContext: + readOnlyRootFilesystem: true + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: File + volumeMounts: + - mountPath: /host/proc + name: proc + readOnly: true + - mountPath: /host/sys + name: sys + readOnly: true + - mountPath: /host/root + mountPropagation: HostToContainer + name: root + readOnly: true + dnsPolicy: ClusterFirst + enableServiceLinks: true + hostNetwork: true + hostPID: true + nodeName: ip-172-33-32-41.us-west-2.compute.internal + nodeSelector: + kubernetes.io/os: linux + preemptionPolicy: PreemptLowerPriority + priority: 0 + restartPolicy: Always + schedulerName: default-scheduler + securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + serviceAccount: kube-prometheus-stack-1754164871-prometheus-node-exporter + serviceAccountName: kube-prometheus-stack-1754164871-prometheus-node-exporter + terminationGracePeriodSeconds: 30 + tolerations: + - effect: NoSchedule + operator: Exists + - effect: NoExecute + key: node.kubernetes.io/not-ready + operator: Exists + - effect: NoExecute + key: node.kubernetes.io/unreachable + operator: Exists + - effect: NoSchedule + key: node.kubernetes.io/disk-pressure + operator: Exists + - effect: NoSchedule + key: node.kubernetes.io/memory-pressure + operator: Exists + - effect: NoSchedule + key: node.kubernetes.io/pid-pressure + operator: Exists + - effect: NoSchedule + key: node.kubernetes.io/unschedulable + operator: Exists + - effect: NoSchedule + key: node.kubernetes.io/network-unavailable + operator: Exists + volumes: + - hostPath: + path: /proc + type: "" + name: proc + - hostPath: + path: /sys + type: "" + name: sys + - hostPath: + path: / + type: "" + name: root + status: + conditions: + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:51Z" + status: "True" + type: PodReadyToStartContainers + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:49Z" + status: "True" + type: Initialized + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:51Z" + status: "True" + type: Ready + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:51Z" + status: "True" + type: ContainersReady + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:49Z" + status: "True" + type: PodScheduled + containerStatuses: + - containerID: containerd://36a36f636e0fb083d4a9b6d049b19e36cbe9d835b6cc41ff2e999a9264e04171 + image: quay.io/prometheus/node-exporter:v1.9.1 + imageID: quay.io/prometheus/node-exporter@sha256:d00a542e409ee618a4edc67da14dd48c5da66726bbd5537ab2af9c1dfc442c8a + lastState: {} + name: node-exporter + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:01:51Z" + volumeMounts: + - mountPath: /host/proc + name: proc + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /host/sys + name: sys + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /host/root + name: root + readOnly: true + recursiveReadOnly: Disabled + hostIP: 172.33.32.41 + hostIPs: + - ip: 172.33.32.41 + phase: Running + podIP: 172.33.32.41 + podIPs: + - ip: 172.33.32.41 + qosClass: BestEffort + startTime: "2025-08-02T20:01:49Z" +- apiVersion: v1 + kind: Pod + metadata: + annotations: + kubectl.kubernetes.io/default-container: prometheus + creationTimestamp: "2025-08-02T20:01:52Z" + generateName: prometheus-kube-prometheus-stack-1754-prometheus- + labels: + app.kubernetes.io/instance: kube-prometheus-stack-1754-prometheus + app.kubernetes.io/managed-by: prometheus-operator + app.kubernetes.io/name: prometheus + app.kubernetes.io/version: 3.5.0 + apps.kubernetes.io/pod-index: "0" + controller-revision-hash: prometheus-kube-prometheus-stack-1754-prometheus-7bbd956f4 + operator.prometheus.io/name: kube-prometheus-stack-1754-prometheus + operator.prometheus.io/shard: "0" + prometheus: kube-prometheus-stack-1754-prometheus + statefulset.kubernetes.io/pod-name: prometheus-kube-prometheus-stack-1754-prometheus-0 + name: prometheus-kube-prometheus-stack-1754-prometheus-0 + namespace: prometheus + ownerReferences: + - apiVersion: apps/v1 + blockOwnerDeletion: true + controller: true + kind: StatefulSet + name: prometheus-kube-prometheus-stack-1754-prometheus + uid: 74140836-f846-474c-9bab-88205c90d209 + resourceVersion: "93640627" + uid: 6028f975-aa14-4fc8-962a-5fef7ad4ff09 + spec: + affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchExpressions: + - key: app.kubernetes.io/name + operator: In + values: + - prometheus + - key: app.kubernetes.io/instance + operator: In + values: + - kube-prometheus-stack-1754-prometheus + topologyKey: kubernetes.io/hostname + weight: 100 + automountServiceAccountToken: true + containers: + - args: + - --config.file=/etc/prometheus/config_out/prometheus.env.yaml + - --web.enable-lifecycle + - --web.external-url=http://kube-prometheus-stack-1754-prometheus.prometheus:9090 + - --web.route-prefix=/ + - --storage.tsdb.retention.time=10d + - --storage.tsdb.path=/prometheus + - --storage.tsdb.wal-compression + - --web.config.file=/etc/prometheus/web_config/web-config.yaml + image: quay.io/prometheus/prometheus:v3.5.0 + imagePullPolicy: IfNotPresent + livenessProbe: + failureThreshold: 6 + httpGet: + path: /-/healthy + port: http-web + scheme: HTTP + periodSeconds: 5 + successThreshold: 1 + timeoutSeconds: 3 + name: prometheus + ports: + - containerPort: 9090 + name: http-web + protocol: TCP + readinessProbe: + failureThreshold: 3 + httpGet: + path: /-/ready + port: http-web + scheme: HTTP + periodSeconds: 5 + successThreshold: 1 + timeoutSeconds: 3 + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /-/ready + port: http-web + scheme: HTTP + periodSeconds: 15 + successThreshold: 1 + timeoutSeconds: 3 + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: FallbackToLogsOnError + volumeMounts: + - mountPath: /etc/prometheus/config_out + name: config-out + readOnly: true + - mountPath: /etc/prometheus/certs + name: tls-assets + readOnly: true + - mountPath: /prometheus + name: prometheus-kube-prometheus-stack-1754-prometheus-db + - mountPath: /etc/prometheus/rules/prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + name: prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + - mountPath: /etc/prometheus/web_config/web-config.yaml + name: web-config + readOnly: true + subPath: web-config.yaml + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-h97gt + readOnly: true + - args: + - --listen-address=:8080 + - --reload-url=http://127.0.0.1:9090/-/reload + - --config-file=/etc/prometheus/config/prometheus.yaml.gz + - --config-envsubst-file=/etc/prometheus/config_out/prometheus.env.yaml + - --watched-dir=/etc/prometheus/rules/prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + command: + - /bin/prometheus-config-reloader + env: + - name: POD_NAME + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: metadata.name + - name: SHARD + value: "0" + image: quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0 + imagePullPolicy: IfNotPresent + name: config-reloader + ports: + - containerPort: 8080 + name: reloader-web + protocol: TCP + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: FallbackToLogsOnError + volumeMounts: + - mountPath: /etc/prometheus/config + name: config + - mountPath: /etc/prometheus/config_out + name: config-out + - mountPath: /etc/prometheus/rules/prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + name: prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-h97gt + readOnly: true + dnsPolicy: ClusterFirst + enableServiceLinks: true + hostname: prometheus-kube-prometheus-stack-1754-prometheus-0 + initContainers: + - args: + - --watch-interval=0 + - --listen-address=:8081 + - --config-file=/etc/prometheus/config/prometheus.yaml.gz + - --config-envsubst-file=/etc/prometheus/config_out/prometheus.env.yaml + - --watched-dir=/etc/prometheus/rules/prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + command: + - /bin/prometheus-config-reloader + env: + - name: POD_NAME + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: metadata.name + - name: SHARD + value: "0" + image: quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0 + imagePullPolicy: IfNotPresent + name: init-config-reloader + ports: + - containerPort: 8081 + name: reloader-web + protocol: TCP + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: FallbackToLogsOnError + volumeMounts: + - mountPath: /etc/prometheus/config + name: config + - mountPath: /etc/prometheus/config_out + name: config-out + - mountPath: /etc/prometheus/rules/prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + name: prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-h97gt + readOnly: true + nodeName: ip-172-33-32-41.us-west-2.compute.internal + preemptionPolicy: PreemptLowerPriority + priority: 0 + restartPolicy: Always + schedulerName: default-scheduler + securityContext: + fsGroup: 2000 + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + seccompProfile: + type: RuntimeDefault + serviceAccount: kube-prometheus-stack-1754-prometheus + serviceAccountName: kube-prometheus-stack-1754-prometheus + shareProcessNamespace: false + subdomain: prometheus-operated + terminationGracePeriodSeconds: 600 + tolerations: + - effect: NoExecute + key: node.kubernetes.io/not-ready + operator: Exists + tolerationSeconds: 300 + - effect: NoExecute + key: node.kubernetes.io/unreachable + operator: Exists + tolerationSeconds: 300 + volumes: + - name: config + secret: + defaultMode: 420 + secretName: prometheus-kube-prometheus-stack-1754-prometheus + - name: tls-assets + projected: + defaultMode: 420 + sources: + - secret: + name: prometheus-kube-prometheus-stack-1754-prometheus-tls-assets-0 + - emptyDir: + medium: Memory + name: config-out + - configMap: + defaultMode: 420 + name: prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + name: prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + - name: web-config + secret: + defaultMode: 420 + secretName: prometheus-kube-prometheus-stack-1754-prometheus-web-config + - emptyDir: {} + name: prometheus-kube-prometheus-stack-1754-prometheus-db + - name: kube-api-access-h97gt + projected: + defaultMode: 420 + sources: + - serviceAccountToken: + expirationSeconds: 3607 + path: token + - configMap: + items: + - key: ca.crt + path: ca.crt + name: kube-root-ca.crt + - downwardAPI: + items: + - fieldRef: + apiVersion: v1 + fieldPath: metadata.namespace + path: namespace + status: + conditions: + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:54Z" + status: "True" + type: PodReadyToStartContainers + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:56Z" + status: "True" + type: Initialized + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:02:08Z" + status: "True" + type: Ready + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:02:08Z" + status: "True" + type: ContainersReady + - lastProbeTime: null + lastTransitionTime: "2025-08-02T20:01:52Z" + status: "True" + type: PodScheduled + containerStatuses: + - containerID: containerd://2d67bd8a01943ce3b45197a534c606a8a5e0eafc1f5bcb831b8afb11e9ed6e88 + image: quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0 + imageID: quay.io/prometheus-operator/prometheus-config-reloader@sha256:78aec597d87aa2b4ba947ab9190538dae93a58a67b8e930aefea1086534b02ef + lastState: {} + name: config-reloader + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:02:02Z" + volumeMounts: + - mountPath: /etc/prometheus/config + name: config + - mountPath: /etc/prometheus/config_out + name: config-out + - mountPath: /etc/prometheus/rules/prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + name: prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-h97gt + readOnly: true + recursiveReadOnly: Disabled + - containerID: containerd://f32c9431e3d0bb65fd309f5ec217348d5be0648bc9d8191e0336022e27d056a6 + image: quay.io/prometheus/prometheus:v3.5.0 + imageID: quay.io/prometheus/prometheus@sha256:63805ebb8d2b3920190daf1cb14a60871b16fd38bed42b857a3182bc621f4996 + lastState: {} + name: prometheus + ready: true + restartCount: 0 + started: true + state: + running: + startedAt: "2025-08-02T20:02:02Z" + volumeMounts: + - mountPath: /etc/prometheus/config_out + name: config-out + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /etc/prometheus/certs + name: tls-assets + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /prometheus + name: prometheus-kube-prometheus-stack-1754-prometheus-db + - mountPath: /etc/prometheus/rules/prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + name: prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + - mountPath: /etc/prometheus/web_config/web-config.yaml + name: web-config + readOnly: true + recursiveReadOnly: Disabled + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-h97gt + readOnly: true + recursiveReadOnly: Disabled + hostIP: 172.33.32.41 + hostIPs: + - ip: 172.33.32.41 + initContainerStatuses: + - containerID: containerd://eb6e6b2578ed43a0861c4515d3bf4aa9b7d67fbb5b20b449ed5f07626b63cd1b + image: quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0 + imageID: quay.io/prometheus-operator/prometheus-config-reloader@sha256:78aec597d87aa2b4ba947ab9190538dae93a58a67b8e930aefea1086534b02ef + lastState: {} + name: init-config-reloader + ready: true + restartCount: 0 + started: false + state: + terminated: + containerID: containerd://eb6e6b2578ed43a0861c4515d3bf4aa9b7d67fbb5b20b449ed5f07626b63cd1b + exitCode: 0 + finishedAt: "2025-08-02T20:01:54Z" + reason: Completed + startedAt: "2025-08-02T20:01:54Z" + volumeMounts: + - mountPath: /etc/prometheus/config + name: config + - mountPath: /etc/prometheus/config_out + name: config-out + - mountPath: /etc/prometheus/rules/prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + name: prometheus-kube-prometheus-stack-1754-prometheus-rulefiles-0 + - mountPath: /var/run/secrets/kubernetes.io/serviceaccount + name: kube-api-access-h97gt + readOnly: true + recursiveReadOnly: Disabled + phase: Running + podIP: 172.33.51.237 + podIPs: + - ip: 172.33.51.237 + qosClass: BestEffort + startTime: "2025-08-02T20:01:52Z" +kind: List +metadata: + resourceVersion: ""