extensions:
  health_check:
    endpoint: 0.0.0.0:13133
  file_storage:
    directory: /var/lib/otelcol/queue

receivers:
  otlp:
    protocols:
      grpc:
        endpoint: 0.0.0.0:4317
      http:
        endpoint: 0.0.0.0:4318
  prometheus:
    config:
      scrape_configs:
        - job_name: otel-collector
          scrape_interval: 30s
          static_configs:
            - targets: ["127.0.0.1:8888"]
              labels:
                service_name: otel-collector
        - job_name: redis-safety
          scrape_interval: 30s
          static_configs:
            - targets: ["redis-exporter:9121"]
              labels:
                service_name: redis
        - job_name: nginx
          scrape_interval: 30s
          static_configs:
            - targets: ["nginx-exporter:9113"]
              labels:
                service_name: nginx
  hostmetrics:
    root_path: /hostfs
    collection_interval: 30s
    scrapers:
      cpu:
      disk:
      filesystem:
        exclude_mount_points:
          mount_points:
            - /hostfs/(dev|proc|sys|run)($|/)
          match_type: regexp
      load:
      memory:
      network:
      paging:
      processes:

processors:
  memory_limiter:
    check_interval: 1s
    limit_mib: 384
    spike_limit_mib: 96
  resource/vm2:
    attributes:
      - {key: service.namespace, value: han-chat, action: upsert}
      - {key: deployment.environment, value: "${env:APP_ENV}", action: upsert}
      - {key: service.version, value: "${env:RELEASE_VERSION}", action: upsert}
  attributes/redact:
    actions:
      - {key: http.request.header.authorization, action: delete}
      - {key: http.request.header.cookie, action: delete}
      - {key: url.query, action: delete}
      - {key: url.full, action: delete}
      - {key: http.target, action: delete}
      - {key: http.request.body, action: delete}
      - {key: http.response.body, action: delete}
      - {key: db.statement, action: delete}
      - {key: db.query.text, action: delete}
      - {key: enduser.id, action: delete}
      - {key: user.phone, action: delete}
      - {key: user.email, action: delete}
      - {key: messaging.message.body, action: delete}
      - {key: aws.s3.key, action: delete}
      - {key: s3.object.key, action: delete}
  filter/noise:
    error_mode: ignore
    traces:
      span:
        - 'attributes["http.route"] == "/health/live"'
        - 'attributes["http.route"] == "/nginx-health/live"'
    logs:
      log_record:
        - 'severity_number < SEVERITY_NUMBER_INFO'
  tail_sampling:
    decision_wait: 10s
    num_traces: 10000
    expected_new_traces_per_sec: 50
    policies:
      - name: errors
        type: status_code
        status_code:
          status_codes: [ERROR]
      - name: slow
        type: latency
        latency:
          threshold_ms: 1000
      - name: baseline
        type: probabilistic
        probabilistic:
          sampling_percentage: 10
  batch:
    timeout: 5s
    send_batch_size: 1024
    send_batch_max_size: 2048

exporters:
  otlp/remote:
    endpoint: "${env:OTEL_REMOTE_ENDPOINT}"
    tls:
      insecure: "${env:OTEL_REMOTE_TLS_INSECURE}"
    sending_queue:
      enabled: true
      storage: file_storage
      queue_size: 10000
    retry_on_failure:
      enabled: true
      initial_interval: 5s
      max_interval: 30s
      max_elapsed_time: 0s

service:
  extensions: [health_check, file_storage]
  pipelines:
    traces:
      receivers: [otlp]
      processors: [memory_limiter, resource/vm2, attributes/redact, filter/noise, tail_sampling, batch]
      exporters: [otlp/remote]
    metrics:
      receivers: [otlp, prometheus, hostmetrics]
      processors: [memory_limiter, resource/vm2, attributes/redact, batch]
      exporters: [otlp/remote]
    logs:
      receivers: [otlp]
      processors: [memory_limiter, resource/vm2, attributes/redact, filter/noise, batch]
      exporters: [otlp/remote]
  telemetry:
    metrics:
      address: 0.0.0.0:8888