apiVersion: opentelemetry.io/v1beta1
kind: OpenTelemetryCollector
metadata:
  name: collector-with-ta-prometheus-cr
spec:
  serviceAccount: opentelemetry-targetallocator-sa
  priorityClassName: edge-p4-operability-services
  image: us-east1-docker.pkg.dev/ret-edge-pltf-infra/thirdparty/otel/opentelemetry-collector-contrib@sha256:ff3b385fc8a4bc7709e2bd8b4024259b649f78732aecc874a963250b5a5c3dd4 #TBD: Fix bzl path automation
  resources:
    requests:
      cpu: 25m
      memory: 128Mi
  config:
    service:
      pipelines:
        metrics:
          exporters:
          - googlemanagedprometheus
          processors:
          - attributes
          - resource
          - groupbyattrs
          - resourcedetection
          - memory_limiter
          - batch
          receivers:
          - prometheus
      telemetry:
        logs:
          encoding: "json"
          level: "WARN"
    exporters:
      googlemanagedprometheus:
        metric:
          prefix: prometheus.googleapis.com
          compression: gzip
    processors:
      attributes:
        actions:
        - value: ${cluster_hash}
          action: upsert
          key: cluster_hash
        - value: ${cluster_uuid}
          action: upsert
          key: cluster_name
        - value: ${cluster_provider}
          action: upsert
          key: cluster_type
      batch:
        # batch metrics before sending to reduce API usage
        send_batch_max_size: 0
        send_batch_size: 10000
        timeout: 10s
      groupbyattrs:
        keys:
        - cluster
        - location
        - project_id
        - namespace
      memory_limiter:
        # drop metrics if memory usage gets too high
        check_interval: 5s
        limit_mib: 4096
      resource:
        attributes:
        - value: ${cluster_uuid}
          action: upsert
          key: cluster
        - value: ${gcp_region}-${gcp_zone}
          action: upsert
          key: location
        - value: ${gcp_project_id}
          action: upsert
          key: project_id
      resourcedetection:
        detectors:
        - gcp
        override: false
        timeout: 5s
    receivers:
      prometheus:
        config:
          scrape_configs:
          - job_name: otel-collector
            scrape_interval: 60s
            static_configs:
            - targets:
              - 0.0.0.0:8888
        report_extra_scrape_metrics: true
        target_allocator:
          collector_id: "$${POD_NAME}"
          endpoint: http://collector-with-ta-prometheus-cr-targetallocator
          interval: 60s
  managementState: managed
  mode: statefulset
  podDisruptionBudget:
    minAvailable: 1
  targetAllocator:
    serviceAccount: opentelemetry-targetallocator-sa
    image: us-east1-docker.pkg.dev/ret-edge-pltf-infra/thirdparty/ghcr.io/open-telemetry/opentelemetry-operator/target-allocator@sha256:c490ab98f73f683d11af86ac2b0c69be89bc787abfcb38525f870a7d377173da #TBD: Fix bzl path automation
    resources:
      requests:
        cpu: 10m
        memory: 10Mi
    enabled: true
    observability:
      metrics:
        enableMetrics: true
    prometheusCR:
      enabled: true
      podMonitorSelector: {}
      scrapeInterval: 1m0s
      serviceMonitorSelector: {}
  upgradeStrategy: automatic