Skip to content

The only tool you need to know what is happening and how to fix it.

2.2 KB
Raw Blame
# Traceway cluster agent, as values for the upstream OpenTelemetry Collector chart.
#
#   helm upgrade --install traceway-cluster-agent \
#     open-telemetry/opentelemetry-collector \
#     --namespace traceway \
#     --values cluster-agent-values.yaml
#
# Reports cluster state metrics and Kubernetes events. Keep it at one replica:
# a second copy would report every cluster metric twice.
mode: deployment
replicaCount: 1

image:
  repository: otel/opentelemetry-collector-contrib

presets:
  clusterMetrics:
    enabled: true
  kubernetesEvents:
    enabled: true

extraEnvs:
  - name: TRACEWAY_TOKEN
    valueFrom:
      secretKeyRef:
        name: traceway-token
        key: token
  - name: TRACEWAY_ENDPOINT
    valueFrom:
      configMapKeyRef:
        name: traceway-settings
        key: TRACEWAY_ENDPOINT
  - name: TRACEWAY_CLUSTER_NAME
    valueFrom:
      configMapKeyRef:
        name: traceway-settings
        key: TRACEWAY_CLUSTER_NAME

config:
  receivers:
    k8s_cluster:
      collection_interval: 30s
      node_conditions_to_report: [Ready, MemoryPressure, DiskPressure, PIDPressure]
      allocatable_types_to_report: [cpu, memory, storage, ephemeral-storage]

  processors:
    resource/cluster:
      attributes:
        - key: k8s.cluster.name
          value: ${env:TRACEWAY_CLUSTER_NAME}
          action: upsert
        # Cluster-wide series belong to no node, so they report under the
        # cluster's own name rather than any instance.
        - key: service.name
          value: ${env:TRACEWAY_CLUSTER_NAME}
          action: upsert

  exporters:
    otlphttp/traceway:
      endpoint: ${env:TRACEWAY_ENDPOINT}
      headers:
        Authorization: Bearer ${env:TRACEWAY_TOKEN}
      compression: gzip
      retry_on_failure:
        enabled: true

  service:
    pipelines:
      traces: null
      metrics:
        receivers: [k8s_cluster]
        processors: [memory_limiter, resource/cluster, batch]
        exporters: [otlphttp/traceway]
      logs:
        receivers: [k8sobjects]
        processors: [memory_limiter, resource/cluster, batch]
        exporters: [otlphttp/traceway]

resources:
  requests:
    cpu: 100m
    memory: 200Mi
  limits:
    memory: 500Mi