observability/opentelemetry-collector/manifests/collector.yaml

# OpenTelemetry Collector with Target Allocator
# Managed by OpenTelemetry Operator
#
# Architecture:
# - DaemonSet mode: one collector per node for log collection
# - Target Allocator: distributes scrape targets across collectors
# - Filelog receiver for container logs
# - Prometheus receiver with Target Allocator for metrics
# - Exports to: Tempo (traces), Prometheus (metrics), Loki (logs)
apiVersion: opentelemetry.io/v1beta1
kind: OpenTelemetryCollector
metadata:
  name: otel-collector
  namespace: opentelemetry
spec:
  mode: daemonset
  image: otel/opentelemetry-collector-contrib:0.113.0
  serviceAccount: otel-collector

  # Target Allocator disabled - metrics collected by Prometheus directly
  # OTel handles logs (filelog) and traces (otlp) only

  resources:
    requests:
      cpu: 50m
      memory: 256Mi
    limits:
      memory: 512Mi

  tolerations:
    - key: node-role.kubernetes.io/control-plane
      operator: Exists
      effect: NoSchedule

  volumeMounts:
    - name: varlogpods
      mountPath: /var/log/pods
      readOnly: true
    - name: varlibdockercontainers
      mountPath: /var/lib/docker/containers
      readOnly: true

  volumes:
    - name: varlogpods
      hostPath:
        path: /var/log/pods
    - name: varlibdockercontainers
      hostPath:
        path: /var/lib/docker/containers

  ports:
    - name: otlp-grpc
      port: 4317
      protocol: TCP
      targetPort: 4317
    - name: otlp-http
      port: 4318
      protocol: TCP
      targetPort: 4318
    - name: metrics
      port: 8888
      protocol: TCP
      targetPort: 8888

  env:
    - name: K8S_NODE_NAME
      valueFrom:
        fieldRef:
          fieldPath: spec.nodeName
    - name: K8S_POD_NAME
      valueFrom:
        fieldRef:
          fieldPath: metadata.name
    - name: K8S_POD_IP
      valueFrom:
        fieldRef:
          fieldPath: status.podIP

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

      # Filelog receiver for container logs
      filelog:
        include:
          - /var/log/pods/*/*/*.log
        exclude:
          - /var/log/pods/opentelemetry_otel-collector*/*/*.log
        start_at: end
        include_file_path: true
        include_file_name: false
        operators:
          - type: router
            id: get-format
            routes:
              - output: parser-docker
                expr: 'body matches "^\\{"'
              - output: parser-containerd
                expr: 'body matches "^[^ Z]+Z"'
            default: parser-containerd

          - type: json_parser
            id: parser-docker
            output: extract-metadata-from-filepath
            timestamp:
              parse_from: attributes.time
              layout: '%Y-%m-%dT%H:%M:%S.%LZ'

          - type: regex_parser
            id: parser-containerd
            regex: '^(?P<time>[^ ^Z]+Z) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
            output: extract-metadata-from-filepath
            timestamp:
              parse_from: attributes.time
              layout: '%Y-%m-%dT%H:%M:%S.%LZ'

          - type: regex_parser
            id: extract-metadata-from-filepath
            regex: '^.*\/(?P<namespace>[^_]+)_(?P<pod_name>[^_]+)_(?P<uid>[a-f0-9-]+)\/(?P<container_name>[^\/]+)\/.*$'
            parse_from: attributes["log.file.path"]

          - type: move
            from: attributes.namespace
            to: resource["k8s.namespace.name"]
          - type: move
            from: attributes.pod_name
            to: resource["k8s.pod.name"]
          - type: move
            from: attributes.container_name
            to: resource["k8s.container.name"]
          - type: move
            from: attributes.uid
            to: resource["k8s.pod.uid"]
          - type: move
            from: attributes.stream
            to: attributes["log.iostream"]
          - type: move
            from: attributes.log
            to: body

      # Prometheus receiver - self metrics only
      prometheus:
        config:
          scrape_configs:
            - job_name: otel-collector
              scrape_interval: 60s
              static_configs:
                - targets: ['${env:K8S_POD_IP}:8888']

    processors:
      batch:
        timeout: 10s
        send_batch_size: 1024
        send_batch_max_size: 2048

      memory_limiter:
        check_interval: 5s
        limit_mib: 400
        spike_limit_mib: 100

      k8sattributes:
        extract:
          metadata:
            - k8s.namespace.name
            - k8s.deployment.name
            - k8s.pod.name
            - k8s.node.name
        passthrough: false
        pod_association:
          - sources:
              - from: resource_attribute
                name: k8s.pod.ip
          - sources:
              - from: resource_attribute
                name: k8s.pod.uid
          - sources:
              - from: connection

      resourcedetection:
        detectors: [env, system]
        timeout: 5s
        override: false

    exporters:
      otlp/tempo:
        endpoint: tempo.tempo.svc.cluster.local:4317
        tls:
          insecure: true

      prometheusremotewrite:
        endpoint: http://prometheus-kube-prometheus-prometheus.prometheus.svc:9090/api/v1/write
        tls:
          insecure: true
        external_labels:
          otel_collector: ${env:K8S_POD_NAME}

      loki:
        endpoint: http://loki.loki.svc.cluster.local:3100/loki/api/v1/push
        default_labels_enabled:
          exporter: true
          level: true

      debug:
        verbosity: basic

    extensions:
      health_check:
        endpoint: 0.0.0.0:13133

    service:
      extensions: [health_check]
      pipelines:
        traces:
          receivers: [otlp]
          processors: [memory_limiter, k8sattributes, resourcedetection, batch]
          exporters: [otlp/tempo]

        metrics:
          receivers: [otlp, prometheus]
          processors: [memory_limiter, k8sattributes, resourcedetection, batch]
          exporters: [prometheusremotewrite]

        logs:
          receivers: [otlp, filelog]
          processors: [memory_limiter, k8sattributes, resourcedetection, batch]
          exporters: [loki]