bakery-ia/infrastructure/kubernetes/base/components/monitoring/otel-collector.yaml

---
apiVersion: v1
kind: ConfigMap
metadata:
  name: otel-collector-config
  namespace: monitoring
data:
  otel-collector-config.yaml: |
    extensions:
      health_check:
        endpoint: 0.0.0.0:13133

    receivers:
      otlp:
        protocols:
          grpc:
            endpoint: 0.0.0.0:4317
          http:
            endpoint: 0.0.0.0:4318

    processors:
      batch:
        timeout: 10s
        send_batch_size: 1024

      # Memory limiter to prevent OOM
      memory_limiter:
        check_interval: 1s
        limit_mib: 512
        spike_limit_mib: 128

    exporters:
      # Export metrics to Prometheus
      prometheus:
        endpoint: "0.0.0.0:8889"
        namespace: otelcol
        const_labels:
          source: otel-collector

      # Export to SigNoz
      otlp/signoz:
        endpoint: "signoz-query-service.monitoring.svc.cluster.local:8080"
        tls:
          insecure: true

      # Logging exporter for debugging traces and logs
      logging:
        loglevel: info
        sampling_initial: 5
        sampling_thereafter: 200

    service:
      extensions: [health_check]
      pipelines:
        # Traces pipeline: receive -> process -> export to SigNoz
        traces:
          receivers: [otlp]
          processors: [memory_limiter, batch]
          exporters: [otlp/signoz, logging]

        # Metrics pipeline: receive -> process -> export to both Prometheus and SigNoz
        metrics:
          receivers: [otlp]
          processors: [memory_limiter, batch]
          exporters: [prometheus, otlp/signoz]

        # Logs pipeline: receive -> process -> export to SigNoz
        logs:
          receivers: [otlp]
          processors: [memory_limiter, batch]
          exporters: [otlp/signoz, logging]

---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: otel-collector
  namespace: monitoring
  labels:
    app: otel-collector
spec:
  replicas: 1
  selector:
    matchLabels:
      app: otel-collector
  template:
    metadata:
      labels:
        app: otel-collector
    spec:
      containers:
      - name: otel-collector
        image: otel/opentelemetry-collector-contrib:0.91.0
        args:
        - --config=/conf/otel-collector-config.yaml
        ports:
        - containerPort: 4317
          protocol: TCP
          name: otlp-grpc
        - containerPort: 4318
          protocol: TCP
          name: otlp-http
        - containerPort: 8889
          protocol: TCP
          name: prometheus
        - containerPort: 13133
          protocol: TCP
          name: health-check
        volumeMounts:
        - name: otel-collector-config
          mountPath: /conf
        resources:
          requests:
            memory: "256Mi"
            cpu: "100m"
          limits:
            memory: "512Mi"
            cpu: "500m"
        livenessProbe:
          httpGet:
            path: /
            port: 13133
          initialDelaySeconds: 30
          periodSeconds: 10
        readinessProbe:
          httpGet:
            path: /
            port: 13133
          initialDelaySeconds: 5
          periodSeconds: 5
      volumes:
      - name: otel-collector-config
        configMap:
          name: otel-collector-config
          items:
          - key: otel-collector-config.yaml
            path: otel-collector-config.yaml

---
apiVersion: v1
kind: Service
metadata:
  name: otel-collector
  namespace: monitoring
  labels:
    app: otel-collector
  annotations:
    prometheus.io/scrape: "true"
    prometheus.io/port: "8889"
    prometheus.io/path: "/metrics"
spec:
  type: ClusterIP
  ports:
  - port: 4317
    targetPort: 4317
    protocol: TCP
    name: otlp-grpc
  - port: 4318
    targetPort: 4318
    protocol: TCP
    name: otlp-http
  - port: 8889
    targetPort: 8889
    protocol: TCP
    name: prometheus
  selector:
    app: otel-collector