livrare lot 2

backend/observability/otel-collector/otel-collector.yaml

@@ -0,0 +1,77 @@
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+
+processors:
+  batch:
+    timeout: 1s
+    send_batch_size: 1024
+
+  memory_limiter:
+    check_interval: 5s
+    limit_mib: 512
+
+  resource:
+    attributes:
+      - key: cluster
+        value: didi-prod
+        action: insert
+      - key: environment
+        value: production
+        action: insert
+
+  tail_sampling:
+    decision_wait: 10s
+    num_traces: 100
+    expected_new_traces_per_sec: 10
+    policies:
+      - name: errors-policy
+        type: status_code
+        status_code: { status_codes: [ERROR] }
+      - name: slow-traces-policy
+        type: latency
+        latency: { threshold_ms: 1000 }
+      - name: random-sampling
+        type: probabilistic
+        probabilistic: { sampling_percentage: 10 }
+
+exporters:
+  # Jaeger receives via OTLP natively
+  otlp/jaeger:
+    endpoint: didi-jaeger:4317
+    tls:
+      insecure: true
+
+  # Prometheus exporter for service metrics derived from spans
+  prometheus:
+    endpoint: 0.0.0.0:8889
+    namespace: otel
+    const_labels:
+      cluster: didi-prod
+
+  # Log to stdout for debugging (disable in prod)
+  debug:
+    verbosity: basic
+
+extensions:
+  health_check:
+    endpoint: 0.0.0.0:13133
+
+service:
+  extensions: [health_check]
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [memory_limiter, resource, tail_sampling, batch]
+      exporters: [otlp/jaeger]
+    metrics:
+      receivers: [otlp]
+      processors: [memory_limiter, resource, batch]
+      exporters: [prometheus]
+  telemetry:
+    metrics:
+      address: 0.0.0.0:8888