phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix telemetry to work on reinstantiating new lib cli (#761)

Browse source 
# What does this PR do?

Since we maintain global state in our telemetry pipeline,
reinstantiating lib cli will cause us to add duplicate span processors
causing sqlite to lock out because of constraint violations since we now
have two span processor writing to sqlite. This PR changes the telemetry
adapter for otel to only instantiate the provider once and add the span
processsors only once.

Also fixes an issue llama stack build


## Test Plan

tested with notebook at
https://colab.research.google.com/drive/1ck7hXQxRl6UvT-ijNRZ-gMZxH1G3cN2d#scrollTo=9496f75c
This commit is contained in:
Dinesh Yeduguru 2025-01-14 11:31:50 -08:00 • committed by GitHub
parent 194d12b304
commit a174938fbd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 30 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

53
llama_stack/providers/inline/telemetry/meta_reference/telemetry.py
View file

@ -30,13 +30,10 @@ from llama_stack.apis.telemetry import (
Trace,
UnstructuredLogEvent,
)
from llama_stack.distribution.datatypes import Api
from llama_stack.providers.inline.telemetry.meta_reference.console_span_processor import (
ConsoleSpanProcessor,
)
from llama_stack.providers.inline.telemetry.meta_reference.sqlite_span_processor import (
SQLiteSpanProcessor,
)
@ -52,6 +49,7 @@ _GLOBAL_STORAGE = {
"up_down_counters": {},
}
_global_lock = threading.Lock()
_TRACER_PROVIDER = None
def string_to_trace_id(s: str) -> int:
@ -80,31 +78,34 @@ class TelemetryAdapter(TelemetryDatasetMixin, Telemetry):
}
)
provider = TracerProvider(resource=resource)
trace.set_tracer_provider(provider)
if TelemetrySink.OTEL in self.config.sinks:
otlp_exporter = OTLPSpanExporter(
endpoint=self.config.otel_endpoint,
)
span_processor = BatchSpanProcessor(otlp_exporter)
trace.get_tracer_provider().add_span_processor(span_processor)
metric_reader = PeriodicExportingMetricReader(
OTLPMetricExporter(
global _TRACER_PROVIDER
if _TRACER_PROVIDER is None:
provider = TracerProvider(resource=resource)
trace.set_tracer_provider(provider)
_TRACER_PROVIDER = provider
if TelemetrySink.OTEL in self.config.sinks:
otlp_exporter = OTLPSpanExporter(
endpoint=self.config.otel_endpoint,
)
)
metric_provider = MeterProvider(
resource=resource, metric_readers=[metric_reader]
)
metrics.set_meter_provider(metric_provider)
self.meter = metrics.get_meter(__name__)
if TelemetrySink.SQLITE in self.config.sinks:
trace.get_tracer_provider().add_span_processor(
SQLiteSpanProcessor(self.config.sqlite_db_path)
)
self.trace_store = SQLiteTraceStore(self.config.sqlite_db_path)
if TelemetrySink.CONSOLE in self.config.sinks:
trace.get_tracer_provider().add_span_processor(ConsoleSpanProcessor())
span_processor = BatchSpanProcessor(otlp_exporter)
trace.get_tracer_provider().add_span_processor(span_processor)
metric_reader = PeriodicExportingMetricReader(
OTLPMetricExporter(
endpoint=self.config.otel_endpoint,
)
)
metric_provider = MeterProvider(
resource=resource, metric_readers=[metric_reader]
)
metrics.set_meter_provider(metric_provider)
self.meter = metrics.get_meter(__name__)
if TelemetrySink.SQLITE in self.config.sinks:
trace.get_tracer_provider().add_span_processor(
SQLiteSpanProcessor(self.config.sqlite_db_path)
)
self.trace_store = SQLiteTraceStore(self.config.sqlite_db_path)
if TelemetrySink.CONSOLE in self.config.sinks:
trace.get_tracer_provider().add_span_processor(ConsoleSpanProcessor())
self._lock = _global_lock
async def initialize(self) -> None: