Remove local uwsgi instrumentation and local development tempo and agent

dev/README.md

@@ -70,7 +70,6 @@ The possible profiles values are:
 - `rabbitmq`
 - `postgres`
 - `mysql`
-- `tracing`
 
 The default is `engine,oncall_ui,redis,grafana`. This runs:
 
@@ -174,13 +173,6 @@ export DRONE_TOKEN=<Your DRONE_TOKEN>
 drone sign --save grafana/oncall .drone.yml
 ```
 
-## Tracing setup
-
-Run these steps to enable tracing in your local deployment
-
-1. Add `tracing` to COMPOSE_PROFILES variable (more in [`COMPOSE_PROFILES`](#compose_profiles))
-2. Start the application and check tracing spans at [Grafana Explore Tab](http://localhost:3000/explore), datasource Tempo
-
 ## Troubleshooting
 
 ### ld: library not found for -lssl

dev/conf/agent.yaml

@@ -1,16 +0,0 @@
-server:
-  log_level: debug
-
-traces:
-  configs:
-  - name: default
-    receivers:
-      otlp:
-        protocols:
-          grpc:
-    remote_write:
-      - endpoint: tempo:4317
-        insecure: true
-    batch:
-      timeout: 5s
-      send_batch_size: 100

dev/conf/grafana-datasources.yaml

@@ -1,30 +0,0 @@
-apiVersion: 1
-
-datasources:
-- name: Prometheus
-  type: prometheus
-  uid: prometheus
-  access: proxy
-  orgId: 1
-  url: http://prometheus:9090
-  basicAuth: false
-  isDefault: false
-  version: 1
-  editable: false
-  jsonData:
-    httpMethod: GET
-- name: Tempo
-  type: tempo
-  access: proxy
-  orgId: 1
-  url: http://tempo:3200
-  basicAuth: false
-  isDefault: true
-  version: 1
-  editable: false
-  apiVersion: 1
-  uid: tempo
-  jsonData:
-    httpMethod: GET
-    serviceMap:
-      datasourceUid: prometheus

dev/conf/tempo-local.yaml

@@ -1,62 +0,0 @@
-search_enabled: true
-metrics_generator_enabled: true
-
-server:
-  http_listen_port: 3200
-
-distributor:
-  receivers:                           # this configuration will listen on all ports and protocols that tempo is capable of.
-    jaeger:                            # the receives all come from the OpenTelemetry collector.  more configuration information can
-      protocols:                       # be found there: https://github.com/open-telemetry/opentelemetry-collector/tree/main/receiver
-        thrift_http:                   #
-        grpc:                          # for a production deployment you should only enable the receivers you need!
-        thrift_binary:
-        thrift_compact:
-    zipkin:
-    otlp:
-      protocols:
-        http:
-        grpc:
-    opencensus:
-
-ingester:
-  trace_idle_period: 10s               # the length of time after a trace has not received spans to consider it complete and flush it
-  max_block_bytes: 1_000_000           # cut the head block when it hits this size or ...
-  max_block_duration: 5m               #   this much time passes
-
-compactor:
-  compaction:
-    compaction_window: 1h              # blocks in this time window will be compacted together
-    max_block_bytes: 100_000_000       # maximum size of compacted blocks
-    block_retention: 1h
-    compacted_block_retention: 10m
-
-metrics_generator:
-  registry:
-    external_labels:
-      source: tempo
-      cluster: docker-compose
-  storage:
-    path: /tmp/tempo/generator/wal
-    remote_write:
-      - url: http://prometheus:9090/api/v1/write
-        send_exemplars: true
-
-storage:
-  trace:
-    backend: local                     # backend configuration to use
-    block:
-      bloom_filter_false_positive: .05 # bloom filter false positive rate.  lower values create larger filters but fewer false positives
-      index_downsample_bytes: 1000     # number of bytes per index record
-      encoding: zstd                   # block encoding/compression.  options: none, gzip, lz4-64k, lz4-256k, lz4-1M, lz4, snappy, zstd, s2
-    wal:
-      path: /tmp/tempo/wal             # where to store the the wal locally
-      encoding: snappy                 # wal encoding/compression.  options: none, gzip, lz4-64k, lz4-256k, lz4-1M, lz4, snappy, zstd, s2
-    local:
-      path: /tmp/tempo/blocks
-    pool:
-      max_workers: 100                 # worker pool determines the number of parallel requests to the object store backend
-      queue_depth: 10000
-
-overrides:
-  metrics_generator_processors: [service-graphs, span-metrics]

docker-compose-developer.yml

@@ -25,9 +25,6 @@ x-env-vars: &oncall-env-vars
   BROKER_TYPE: ${BROKER_TYPE}
   GRAFANA_API_URL: http://localhost:3000
   GOOGLE_APPLICATION_CREDENTIALS: /etc/app/gcp_service_account.json
-  OTEL_TRACING_ENABLED: True
-  OTEL_SERVICE_NAME: oncall
-  OTEL_EXPORTER_OTLP_ENDPOINT: http://localhost:4317
 
 # basically this is needed because the oncall backend containers have been configured to communicate w/ grafana via
 # http://localhost:3000 (GRAFANA_API_URL). This URL is used in two scenarios:
@@ -298,7 +295,6 @@ services:
     volumes:
       - grafanadata_dev:/var/lib/grafana
       - ./grafana-plugin:/var/lib/grafana/plugins/grafana-plugin
-      - ./dev/conf/grafana-datasources.yaml:/etc/grafana/provisioning/datasources/datasources.yaml
     depends_on:
       postgres:
         condition: service_healthy
@@ -306,34 +302,6 @@ services:
         condition: service_healthy
     profiles:
       - grafana
-
-  agent:
-    image: grafana/agent:v0.27.1
-    volumes:
-      - ./dev/conf/agent.yaml:/etc/agent.yaml
-    entrypoint:
-      - /bin/agent
-      - -config.file=/etc/agent.yaml
-    ports:
-      - "4317:4317"
-    profiles:
-      - tracing
-
-  tempo:
-    image: grafana/tempo:latest
-    command: [ "-config.file=/etc/tempo.yaml" ]
-    volumes:
-      - ./dev/conf/tempo-local.yaml:/etc/tempo.yaml
-      - tempodata_dev:/tmp/tempo
-    ports:
-      - "14268"  # jaeger ingest
-      - "3200"   # tempo
-      - "4317"  # otlp grpc
-      - "4318"  # otlp http
-      - "9411"   # zipkin
-    profiles:
-      - tracing
-
 volumes:
   redisdata_dev:
     labels: *oncall-labels
@@ -345,8 +313,6 @@ volumes:
     labels: *oncall-labels
   mysqldata_dev:
     labels: *oncall-labels
-  tempodata_dev:
-    labels: *oncall-labels
 
 networks:
   default:

engine/engine/wsgi.py

@@ -17,7 +17,6 @@ from opentelemetry.instrumentation.pymysql import PyMySQLInstrumentor
 from opentelemetry.instrumentation.wsgi import OpenTelemetryMiddleware
 from opentelemetry.sdk.trace import TracerProvider
 from opentelemetry.sdk.trace.export import BatchSpanProcessor
-from uwsgidecorators import postfork
 from whitenoise import WhiteNoise
 
 os.environ.setdefault("DJANGO_SETTINGS_MODULE", "settings.prod")
@@ -26,11 +25,18 @@ application = get_wsgi_application()
 application = WhiteNoise(application)
 
 if settings.OTEL_TRACING_ENABLED and settings.OTEL_EXPORTER_OTLP_ENDPOINT:
-    application = OpenTelemetryMiddleware(application)
+    try:
+        from uwsgidecorators import postfork
 
-    @postfork
-    def init_tracing():
-        trace.set_tracer_provider(TracerProvider())
-        span_processor = BatchSpanProcessor(OTLPSpanExporter())
-        trace.get_tracer_provider().add_span_processor(span_processor)
-        PyMySQLInstrumentor().instrument()
+        application = OpenTelemetryMiddleware(application)
+
+        @postfork
+        def init_tracing():
+            trace.set_tracer_provider(TracerProvider())
+            span_processor = BatchSpanProcessor(OTLPSpanExporter())
+            trace.get_tracer_provider().add_span_processor(span_processor)
+            PyMySQLInstrumentor().instrument()
+
+    except ModuleNotFoundError:
+        # Only works under uwsgi web server environment
+        pass

engine/requirements.txt

@@ -45,4 +45,3 @@ opentelemetry-instrumentation-celery==0.36b0
 opentelemetry-instrumentation-pymysql==0.36b0
 opentelemetry-instrumentation-wsgi==0.36b0
 opentelemetry-exporter-otlp-proto-grpc==1.15.0
-uwsgidecorators==1.1.0