deploy/otel/col/values.yaml

# Default values for opentelemetry-collector.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.

nameOverride: ""
fullnameOverride: ""

# Valid values are "daemonset", "deployment", and "statefulset".
mode: "daemonset"

presets:
  logsCollection:
    enabled: false
    includeCollectorLogs: false
    # Enabling this writes checkpoints in /var/lib/otelcol/ host directory.
    # Note this changes collector's user to root, so that it can write to host directory.
    storeCheckpoints: false
  # Configures the collector to collect host metrics.
  # Adds the hostmetrics receiver to the metrics pipeline
  # and adds the necessary volumes and volume mounts.
  # Best used with mode = daemonset.
  hostMetrics:
    enabled: false
  # Configures the Kubernetes Processor to add Kubernetes metadata.
  # Adds the k8sattributes processor to all the pipelines
  # and adds the necessary rules to ClusteRole.
  # Best used with mode = daemonset.
  kubernetesAttributes:
    enabled: true
  # Configures the Kubernetes Cluster Receiver to collect cluster-level metrics.
  # Adds the k8s_cluster receiver to the metrics pipeline
  # and adds the necessary rules to ClusteRole.
  # Best used with mode = deployment or statefulset.
  clusterMetrics:
    enabled: false
  # Configures the collector to collect Kubelet metrics.
  # Adds the kubeletstats receiver to the metrics pipeline
  # and adds the necessary rules to ClusteRole.
  # Best used with mode = daemonset.
  kubeletMetrics:
    enabled: false

configMap:
  # Specifies whether a configMap should be created (true by default)
  create: true

# Base collector configuration.
# Supports templating. To escape existing instances of {{ }}, use {{` <original content> `}}.
# For example, {{ REDACTED_EMAIL }} becomes {{` {{ REDACTED_EMAIL }} `}}.
config:
  exporters:
    loki:
      endpoint: http://loki-loki-distributed-gateway.observe.svc.cluster.local:80/loki/api/v1/push
    otlphttp/deepflow:
     traces_endpoint: "http://deepflow-agent.deepflow/api/v1/otel/trace"
     tls:
       insecure: true
     retry_on_failure:
       enabled: true
    otlphttp/uptrace:
      #endpoint: http://39.106.74.84:34318
      endpoint: http://uptrace.observe.svc.cluster.local:14318
      tls:
        insecure: true
      headers:
        # uptrace-dsn: 'http://project2_secret_token@39.106.74.84:34318/2'
        uptrace-dsn: 'http://project2_secret_token@uptrace.observe.svc.cluster.local:14318/2'
    
    debug:
      verbosity: detailed
    otlp:
      endpoint: "tempo-distributor.observe.svc.cluster.local:4317"
      tls:
        insecure: true
    prometheus:
      endpoint: "0.0.0.0:8889"
    clickhouse:
      endpoint: "tcp://clickhouse-headless.observe.svc.cluster.local:9000?dial_timeout=10s&compress=lz4"
      database: otel
      username: default
      password: "cecf@cestong.com"
      ttl: 240h
      #logs_table: otel_logs
      #traces_table: otel_traces
      #metrics_table: otel_metrics
      timeout: 5s
      retry_on_failure:
        enabled: true
        initial_interval: 5s
        max_interval: 30s
        max_elapsed_time: 300s
    kafka/proto:
        brokers:
          - kafka-headless.observe.svc.cluster.local:9092
        protocol_version: 2.0.0
        encoding: otlp_proto
        topic: otelproto
        timeout: 5s
        retry_on_failure: 
          enabled: true
          initial_interval: 5s
          max_interval: 30s
          max_elapsed_time: 120s
        producer:
          max_message_bytes: 1000000
          required_acks: 1
          compression: lz4
        sending_queue:
          enabled: false
    kafka:
        brokers:
          - kafka-headless.observe.svc.cluster.local:9092
          #- kafka-broker.ob.svc.cluster.local:9092
        protocol_version: 2.0.0
        encoding: otlp_json
        topic: otel
        timeout: 5s
        retry_on_failure: 
          enabled: true
          initial_interval: 5s
          max_interval: 30s
          max_elapsed_time: 120s
        producer:
          max_message_bytes: 1000000
          required_acks: 1
          compression: lz4
          flush_max_messages: 5000
        sending_queue:
          enabled: false
  extensions:
    health_check:
      endpoint: "0.0.0.0:13133"

  processors:
    filter/ottl:
      error_mode: ignore
      logs:
        log_record:
          - 'severity_number < SEVERITY_NUMBER_WARN'
    #transform:
    #  error_mode: ignore
    #  log_statements:
    #    - context: log
    #      statements:
    #      - set(severity_number, SEVERITY_NUMBER_INFO) where IsString(body) and IsMatch(body, "(\\s|\\[)INFO(\\s|\\])")
    #      - set(severity_number, SEVERITY_NUMBER_WARN) where IsString(body) and IsMatch(body, "(\\s|\\[)WARN(\\s|\\])")
    #      - set(severity_number, SEVERITY_NUMBER_ERROR) where IsString(body) and IsMatch(body, "(\\s|\\[)ERROR(\\s|\\])")
    #      - set(severity_number, SEVERITY_NUMBER_INFO) where severity_number == SEVERITY_NUMBER_UNSPECIFIED
    attributes:
      actions:
        - action: insert
          key: loki.attribute.labels
          value: log.iostream
 
    resource:
      attributes:
        - action: insert
          key: loki.resource.labels
          value: k8s.container.name, k8s.container.restart_count, k8s.deployment.name, k8s.namespace.name, k8s.pod.name, k8s.node.name, k8s.daemonset.name, service.name, k8s.pod.uid
    batch: 
      send_batch_max_size: 1000
      send_batch_size: 500
      timeout: 5s
    # If set to null, will be overridden with values based on k8s resource limits
    memory_limiter:
      check_interval: 1s
      limit_percentage: 80
      spike_limit_percentage: 30
  receivers:
    kafka:
      brokers: kafka-headless.observe.svc.cluster.local:9092
      protocol_version: 2.0.0
      topic: otel_agent
      encoding: otlp_proto
    otlp:
      protocols:
        grpc:
          endpoint: ${MY_POD_IP}:4317
        http:
          endpoint: ${MY_POD_IP}:4318
    prometheus:
      config:
        scrape_configs:
          - job_name: opentelemetry-collector
            scrape_interval: 10s
            static_configs:
              - targets:
                  - ${MY_POD_IP}:8888
  service:
    telemetry:
      metrics:
        address: ${MY_POD_IP}:8888
      logs:
        level: "info"
    extensions:
      - health_check
    pipelines:
      metrics:
        receivers:
          - otlp
          - prometheus
        processors: 
          - memory_limiter
        exporters:
          - prometheus
            #- clickhouse
      logs:
        exporters:
          - clickhouse
        processors:
          #- filter/ottl
          - memory_limiter
          - batch
        receivers:
          - otlp
      traces:
        exporters:
          - kafka/proto
        processors:
          - memory_limiter
            #- batch
        receivers:
          - otlp
          - kafka

image:
  repository: otel/opentelemetry-collector-contrib
  #repository: reg.cestong.com.cn/cecf/obcol
  pullPolicy: Always
  tag: "0.108.0"
  digest: ""
imagePullSecrets: []

# OpenTelemetry Collector executable
command:
  name: ""
  extraArgs: []

serviceAccount:
  # Specifies whether a service account should be created
  create: true
  # Annotations to add to the service account
  annotations: {}
  # The name of the service account to use.
  # If not set and create is true, a name is generated using the fullname template
  name: ""

clusterRole:
  # Specifies whether a clusterRole should be created
  # Some presets also trigger the creation of a cluster role and cluster role binding.
  # If using one of those presets, this field is no-op.
  create: false
  # Annotations to add to the clusterRole
  # Can be used in combination with presets that create a cluster role.
  annotations: {}
  # The name of the clusterRole to use.
  # If not set a name is generated using the fullname template
  # Can be used in combination with presets that create a cluster role.
  name: ""
  # A set of rules as documented here : https://kubernetes.io/docs/reference/access-authn-authz/rbac/
  # Can be used in combination with presets that create a cluster role to add additional rules.
  rules: []
  # - apiGroups:
  #   - ''
  #   resources:
  #   - 'pods'
  #   - 'nodes'
  #   verbs:
  #   - 'get'
  #   - 'list'
  #   - 'watch'

  clusterRoleBinding:
    annotations: {}
    name: ""

podSecurityContext: {}
securityContext: {}

nodeSelector: {}
tolerations: []
affinity: {}
topologySpreadConstraints: {}

priorityClassName: ""

extraEnvs: []
extraVolumes: []
extraVolumeMounts: []

ports:
  health:
    enabled: true
    containerPort: 13133
    servicePort: 13133
    protocol: TCP
  otlp:
    enabled: true
    containerPort: 4317
    servicePort: 4317
    #hostPort: 4317
    protocol: TCP
    nodePort: 30317
    appProtocol: grpc
  otlp-http:
    enabled: true
    containerPort: 4318
    servicePort: 4318
    #hostPort: 4318
    # nodePort: 30318
    protocol: TCP
  prome:
    enabled: true
    containerPort: 8889
    servicePort: 8889
    protocol: TCP
  metrics:
    enabled: true
    containerPort: 8888
    servicePort: 8888
    protocol: TCP

# Resource limits & requests. Update according to your own use case as these values might be too low for a typical deployment.
resources:
  limits:
    cpu: 4
    memory: 4096Mi

podAnnotations:
  prometheus.io/scrape: "true"
  prometheus.io/path: /metrics
  prometheus.io/port: "8889"

podLabels: {}

# Host networking requested for this pod. Use the host's network namespace.
hostNetwork: false

# Pod DNS policy ClusterFirst, ClusterFirstWithHostNet, None, Default, None
dnsPolicy: ""

# only used with deployment mode
replicaCount: 1

# only used with deployment mode
revisionHistoryLimit: 10

annotations: {}

# List of extra sidecars to add
extraContainers: []
# extraContainers:
#   - name: test
#     command:
#       - cp
#     args:
#       - /bin/sleep
#       - /test/sleep
#     image: busybox:latest
#     volumeMounts:
#       - name: test
#         mountPath: /test

# List of init container specs, e.g. for copying a binary to be executed as a lifecycle hook.
# Another usage of init containers is e.g. initializing filesystem permissions to the OTLP Collector user `10001` in case you are using persistence and the volume is producing a permission denied error for the OTLP Collector container.
initContainers: []
lifecycleHooks: {}
service:
  type: NodePort
  annotations: {}

ingress:
  enabled: true
  annotations:
    nginx.ingress.kubernetes.io/cors-allow-origin: "http://otel-demo.cestong.com.cn,http://localhost:3000,http://localhost:1234,http://localhost:5678,http://observe-front.cestong.com.cn"
    nginx.ingress.kubernetes.io/enable-cors: "true"
    nginx.ingress.kubernetes.io/cors-allow-headers: "*"
    nginx.ingress.kubernetes.io/cors-allow-methods: "*"
    nginx.ingress.kubernetes.io/cors-allow-credentials: "true"

  ingressClassName: nginx
  hosts:
    - host: otel-collector.cestong.com.cn
      paths:
        - path: /
          pathType: Prefix
          port: 4318
  additionalIngresses: []
podMonitor:
  enabled: false
  metricsEndpoints:
    - port: metrics
      # interval: 15s

  # additional labels for the PodMonitor
  extraLabels: {}
  #   release: kube-prometheus-stack

serviceMonitor:
  # The service monitor by default scrapes the metrics port.
  # The metrics port needs to be enabled as well.
  enabled: false
  metricsEndpoints:
    - port: metrics
      # interval: 15s

  # additional labels for the ServiceMonitor
  extraLabels: {}
  #  release: kube-prometheus-stack

# PodDisruptionBudget is used only if deployment enabled
podDisruptionBudget:
  enabled: false
#   minAvailable: 2
#   maxUnavailable: 1

# autoscaling is used only if deployment enabled
autoscaling:
  enabled: false
  minReplicas: 1
  maxReplicas: 10
  targetCPUUtilizationPercentage: 80
  # targetMemoryUtilizationPercentage: 80

rollout:
  rollingUpdate: {}
  # When 'mode: daemonset', maxSurge cannot be used when hostPort is set for any of the ports
  # maxSurge: 25%
  # maxUnavailable: 0
  strategy: RollingUpdate

prometheusRule:
  enabled: false
  groups: []
  # Create default rules for monitoring the collector
  defaultRules:
    enabled: false

  # additional labels for the PrometheusRule
  extraLabels: {}

statefulset:
  # volumeClaimTemplates for a statefulset
  volumeClaimTemplates: []
  podManagementPolicy: "Parallel"