deploy/helm/edot-collector/kube-stack/managed_otlp/values.yaml

# For installation and configuration options, refer to the [installation instructions](https://github.com/elastic/opentelemetry/blob/main/docs/kubernetes/operator/README.md)

# For advanced configuration options, refer to the [official OpenTelemetry Helm chart](https://github.com/open-telemetry/opentelemetry-helm-charts/blob/main/charts/opentelemetry-kube-stack/values.yaml)
# This file has been tested together with opentelemetry-kube-stack helm chart version: 0.3.3
opentelemetry-operator:
  manager:
    extraArgs:
      - --enable-go-instrumentation
  admissionWebhooks:
    certManager:
      enabled: false # For production environments, it is [recommended to use cert-manager for better security and scalability](https://github.com/open-telemetry/opentelemetry-helm-charts/tree/main/charts/opentelemetry-operator#tls-certificate-requirement).
    autoGenerateCert:
      enabled: true # Enable/disable automatic certificate generation. Set to false if manually managing certificates.
      recreate: true # Force certificate regeneration on updates. Only applicable if autoGenerateCert.enabled is true.
crds:
  create: true # Install the OpenTelemetry Operator CRDs.
defaultCRConfig:
  image:
    repository: "docker.elastic.co/elastic-agent/elastic-agent"
    tag: "9.1.0"
  targetAllocator:
    enabled: false # Enable/disable the Operator's Target allocator.
    # Refer to: https://github.com/open-telemetry/opentelemetry-operator/tree/main/cmd/otel-allocator
clusterRole:
  rules:
    - apiGroups: [""]
      resources: ["configmaps"]
      verbs: ["get"]
# `clusterName` specifies the name of the Kubernetes cluster. It sets the 'k8s.cluster.name' field.
# Cluster Name is automatically detected for EKS/GKE/AKS. Add the below value in environments where cluster name cannot be detected.
# clusterName: myClusterName
collectors:
  #  Cluster is a K8s deployment EDOT collector focused on gathering telemetry
  #  at the cluster level (Kubernetes Events and cluster metrics).
  cluster:
    fullnameOverride: "opentelemetry-kube-stack-cluster-stats"
    env:
      - name: ELASTIC_AGENT_OTEL
        value: '"true"'
    config:
      exporters:
        # [Debug exporter](https://github.com/open-telemetry/opentelemetry-collector/blob/main/exporter/debugexporter/README.md)
        debug:
          verbosity: basic # Options: basic, detailed. Choose verbosity level for debug logs.
          # [Elasticsearch exporter](https://github.com/open-telemetry/opentelemetry-collector-contrib/blob/main/exporter/elasticsearchexporter/README.md)
        otlp/gateway:
          endpoint: "http://opentelemetry-kube-stack-gateway-collector:4317"
          tls:
            insecure: true
      processors:
        # [Resource Detection Processor](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/processor/resourcedetectionprocessor)
        resourcedetection/eks:
          detectors: [env, eks] # Detects resources from environment variables and EKS (Elastic Kubernetes Service).
          timeout: 15s
          override: true
          eks:
            resource_attributes:
              k8s.cluster.name:
                enabled: true
        resourcedetection/gcp:
          detectors: [env, gcp] # Detects resources from environment variables and GCP (Google Cloud Platform).
          timeout: 2s
          override: true
        resourcedetection/aks:
          detectors: [env, aks] # Detects resources from environment variables and AKS (Azure Kubernetes Service).
          timeout: 2s
          override: true
          aks:
            resource_attributes:
              k8s.cluster.name:
                enabled: true
        # [Resource Processor](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/processor/resourceprocessor)
        resource/k8s: # Resource attributes tailored for services within Kubernetes.
          attributes:
            - key: service.name # Set the service.name resource attribute based on the well-known app.kubernetes.io/name label
              from_attribute: app.label.name
              action: insert
            - key: service.name # Set the service.name resource attribute based on the k8s.container.name attribute
              from_attribute: k8s.container.name
              action: insert
            - key: app.label.name # Delete app.label.name attribute previously used for service.name
              action: delete
            - key: service.version # Set the service.version resource attribute based on the well-known app.kubernetes.io/version label
              from_attribute: app.label.version
              action: insert
            - key: app.label.version # Delete app.label.version attribute previously used for service.version
              action: delete
        resource/hostname:
          attributes:
            - key: host.name
              from_attribute: k8s.node.name
              action: upsert
        # [K8s Attributes Processor](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/processor/k8sattributesprocessor)
        k8sattributes:
          passthrough: false # Annotates resources with the pod IP and does not try to extract any other metadata.
          pod_association:
            # Below association takes a look at the k8s.pod.ip and k8s.pod.uid resource attributes or connection's context, and tries to match it with the pod having the same attribute.
            - sources:
                - from: resource_attribute
                  name: k8s.pod.ip
            - sources:
                - from: resource_attribute
                  name: k8s.pod.uid
            - sources:
                - from: connection
          extract:
            metadata:
              - "k8s.namespace.name"
              - "k8s.deployment.name"
              - "k8s.replicaset.name"
              - "k8s.statefulset.name"
              - "k8s.daemonset.name"
              - "k8s.cronjob.name"
              - "k8s.job.name"
              - "k8s.node.name"
              - "k8s.pod.name"
              - "k8s.pod.ip"
              - "k8s.pod.uid"
              - "k8s.pod.start_time"
            labels:
              - tag_name: app.label.name
                key: app.kubernetes.io/name
                from: pod
              - tag_name: app.label.version
                key: app.kubernetes.io/version
                from: pod
      receivers:
        # [K8s Objects Receiver](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/k8sobjectsreceiver)
        k8sobjects:
          objects:
            - name: events
              mode: "watch"
              group: "events.k8s.io"
              exclude_watch_type:
                - "DELETED"
        # [K8s Cluster Receiver](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/k8sclusterreceiver)
        k8s_cluster:
          auth_type: serviceAccount # Determines how to authenticate to the K8s API server. This can be one of none (for no auth), serviceAccount (to use the standard service account token provided to the agent pod), or kubeConfig to use credentials from ~/.kube/config.
          node_conditions_to_report:
            - Ready
            - MemoryPressure
          allocatable_types_to_report:
            - cpu
            - memory
          metrics:
            k8s.pod.status_reason:
              enabled: true
          resource_attributes:
            k8s.kubelet.version:
              enabled: true
            os.description:
              enabled: true
            os.type:
              enabled: true
            k8s.container.status.last_terminated_reason:
              enabled: true
      # [Service Section](https://opentelemetry.io/docs/collector/configuration/#service)
      service:
        pipelines:
          metrics:
            exporters:
              - debug
              - otlp/gateway
            processors:
              - k8sattributes
              - resourcedetection/eks
              - resourcedetection/gcp
              - resourcedetection/aks
              - resource/k8s
              - resource/hostname
            receivers:
              - k8s_cluster
          logs:
            receivers:
              - k8sobjects
            processors:
              - resourcedetection/eks
              - resourcedetection/gcp
              - resourcedetection/aks
              - resource/hostname
            exporters:
              - debug
              - otlp/gateway
  #  Daemon is a K8s daemonset EDOT collector focused on gathering telemetry at
  #  node level and exposing an OTLP endpoint for data ingestion.
  #  Auto-instrumentation SDKs will use this endpoint.
  daemon:
    fullnameOverride: "opentelemetry-kube-stack-daemon"
    env:
      # Work around for open /mounts error: https://github.com/open-telemetry/opentelemetry-collector-contrib/issues/35990
      - name: HOST_PROC_MOUNTINFO
        value: ""
      - name: ELASTIC_AGENT_OTEL
        value: '"true"'
    presets:
      logsCollection:
        enabled: true # Enable/disable the collection of node's logs.
        storeCheckpoints: true # Store checkpoints for log collection, allowing for resumption from the last processed log.
    hostNetwork: true # Use the host's network namespace. This allows the daemon to access the network interfaces of the host directly.
    securityContext: # Run the daemon as the root user and group for proper metrics collection.
      runAsUser: 0
      runAsGroup: 0
    scrape_configs_file: "" # [Prometheus metrics](https://github.com/open-telemetry/opentelemetry-helm-charts/tree/main/charts/opentelemetry-kube-stack#scrape_configs_file-details)
    config:
      exporters:
        # [Debug exporter](https://github.com/open-telemetry/opentelemetry-collector/blob/main/exporter/debugexporter/README.md)
        debug:
          verbosity: basic
        otlp/gateway:
          endpoint: "http://opentelemetry-kube-stack-gateway-collector-headless:4317"
          tls:
            insecure: true
      processors:
        # [Batch Processor](https://github.com/open-telemetry/opentelemetry-collector/tree/main/processor/batchprocessor)
        batch: {}
        batch/metrics:
          # explicitly set send_batch_max_size to 0, as splitting metrics requests may cause version_conflict_engine_exception in TSDB
          send_batch_max_size: 0
          timeout: 1s
        # [Resource Detection Processor](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/processor/resourcedetectionprocessor)
        resourcedetection/eks:
          detectors: [env, eks] # Detects resources from environment variables and EKS (Elastic Kubernetes Service).
          timeout: 15s
          override: true
          eks:
            resource_attributes:
              k8s.cluster.name:
                enabled: true
        resourcedetection/gcp:
          detectors: [env, gcp] # Detects resources from environment variables and GCP (Google Cloud Platform).
          timeout: 2s
          override: true
        resourcedetection/aks:
          detectors: [env, aks] # Detects resources from environment variables and AKS (Azure Kubernetes Service).
          timeout: 2s
          override: true
          aks:
            resource_attributes:
              k8s.cluster.name:
                enabled: true
        resource/hostname:
          attributes:
            - key: host.name
              from_attribute: k8s.node.name
              action: upsert
        resourcedetection/system:
          detectors: ["system", "ec2"] # Detects resources from the system and EC2 instances.
          system:
            hostname_sources: ["os"]
            resource_attributes:
              host.name:
                enabled: true
              host.id:
                enabled: false
              host.arch:
                enabled: true
              host.ip:
                enabled: true
              host.mac:
                enabled: true
              host.cpu.vendor.id:
                enabled: true
              host.cpu.family:
                enabled: true
              host.cpu.model.id:
                enabled: true
              host.cpu.model.name:
                enabled: true
              host.cpu.stepping:
                enabled: true
              host.cpu.cache.l2.size:
                enabled: true
              os.description:
                enabled: true
              os.type:
                enabled: true
          ec2:
            resource_attributes:
              host.name:
                enabled: false
              host.id:
                enabled: true
        # [Resource Processor](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/processor/resourceprocessor)
        resource/k8s: # Resource attributes tailored for services within Kubernetes.
          attributes:
            - key: service.name # Set the service.name resource attribute based on the well-known app.kubernetes.io/name label
              from_attribute: app.label.name
              action: insert
            - key: service.name # Set the service.name resource attribute based on the k8s.container.name attribute
              from_attribute: k8s.container.name
              action: insert
            - key: app.label.name # Delete app.label.name attribute previously used for service.name
              action: delete
            - key: service.version # Set the service.version resource attribute based on the well-known app.kubernetes.io/version label
              from_attribute: app.label.version
              action: insert
            - key: app.label.version # Delete app.label.version attribute previously used for service.version
              action: delete
        resource/cloud:
          attributes:
            - key: cloud.instance.id
              from_attribute: host.id
              action: insert
        # [K8s Attributes Processor](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/processor/k8sattributesprocessor)
        k8sattributes:
          filter:
            # Only retrieve pods running on the same node as the collector
            node_from_env_var: OTEL_K8S_NODE_NAME
          passthrough: false
          pod_association:
            # Below association takes a look at the k8s.pod.ip and k8s.pod.uid resource attributes or connection's context, and tries to match it with the pod having the same attribute.
            - sources:
                - from: resource_attribute
                  name: k8s.pod.ip
            - sources:
                - from: resource_attribute
                  name: k8s.pod.uid
            - sources:
                - from: connection
          extract:
            metadata:
              - "k8s.namespace.name"
              - "k8s.deployment.name"
              - "k8s.replicaset.name"
              - "k8s.statefulset.name"
              - "k8s.daemonset.name"
              - "k8s.cronjob.name"
              - "k8s.job.name"
              - "k8s.node.name"
              - "k8s.pod.name"
              - "k8s.pod.ip"
              - "k8s.pod.uid"
              - "k8s.pod.start_time"
            labels:
              - tag_name: app.label.name
                key: app.kubernetes.io/name
                from: pod
              - tag_name: app.label.version
                key: app.kubernetes.io/version
                from: pod
      receivers:
        # [OTLP Receiver](https://github.com/open-telemetry/opentelemetry-collector/tree/main/receiver/otlpreceiver)
        otlp:
          protocols:
            grpc:
              endpoint: 0.0.0.0:4317
            http:
              endpoint: 0.0.0.0:4318
        # [File Log Receiver](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/filelogreceiver)
        filelog:
          retry_on_failure:
            enabled: true
          start_at: end
          exclude:
            # exlude collector logs
            - /var/log/pods/*opentelemetry-kube-stack*/*/*.log
          include:
            - /var/log/pods/*/*/*.log
          include_file_name: false
          include_file_path: true
          operators:
            - id: container-parser # Extract container's metadata
              type: container
        # [Hostmetrics Receiver](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/hostmetricsreceiver)
        hostmetrics:
          collection_interval: 10s
          root_path: /hostfs # Mounted node's root file system
          scrapers:
            cpu:
              metrics:
                system.cpu.utilization:
                  enabled: true
                system.cpu.logical.count:
                  enabled: true
            memory:
              metrics:
                system.memory.utilization:
                  enabled: true
            # process scraper is disabled for now: https://github.com/open-telemetry/opentelemetry-collector-contrib/issues/39423
            #process:
            #  mute_process_exe_error: true
            #  mute_process_io_error: true
            #  mute_process_user_error: true
            #  metrics:
            #    process.threads:
            #      enabled: true
            #    process.open_file_descriptors:
            #      enabled: true
            #    process.memory.utilization:
            #      enabled: true
            #    process.disk.operations:
            #      enabled: true
            network: {}
            processes: {}
            load: {}
            disk: {}
            filesystem:
              exclude_mount_points:
                mount_points:
                  - /dev/*
                  - /proc/*
                  - /sys/*
                  - /run/k3s/containerd/*
                  - /var/lib/docker/*
                  - /var/lib/kubelet/*
                  - /snap/*
                match_type: regexp
              exclude_fs_types:
                fs_types:
                  - autofs
                  - binfmt_misc
                  - bpf
                  - cgroup2
                  - configfs
                  - debugfs
                  - devpts
                  - devtmpfs
                  - fusectl
                  - hugetlbfs
                  - iso9660
                  - mqueue
                  - nsfs
                  - overlay
                  - proc
                  - procfs
                  - pstore
                  - rpc_pipefs
                  - securityfs
                  - selinuxfs
                  - squashfs
                  - sysfs
                  - tracefs
                match_type: strict
        # [Kubelet Stats Receiver](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/kubeletstatsreceiver)
        kubeletstats:
          auth_type: serviceAccount # Authentication mechanism with the Kubelet endpoint, refer to: https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/kubeletstatsreceiver#configuration
          collection_interval: 20s
          endpoint: ${env:OTEL_K8S_NODE_NAME}:10250
          node: "${env:OTEL_K8S_NODE_NAME}"
          # Required to work for all CSPs without an issue
          insecure_skip_verify: true
          k8s_api_config:
            auth_type: serviceAccount
          metrics:
            k8s.pod.memory.node.utilization:
              enabled: true
            k8s.pod.cpu.node.utilization:
              enabled: true
            k8s.container.cpu_limit_utilization:
              enabled: true
            k8s.pod.cpu_limit_utilization:
              enabled: true
            k8s.container.cpu_request_utilization:
              enabled: true
            k8s.container.memory_limit_utilization:
              enabled: true
            k8s.pod.memory_limit_utilization:
              enabled: true
            k8s.container.memory_request_utilization:
              enabled: true
            k8s.node.uptime:
              enabled: true
            k8s.node.cpu.usage:
              enabled: true
            k8s.pod.cpu.usage:
              enabled: true
          extra_metadata_labels:
            - container.id
      # [Service Section](https://opentelemetry.io/docs/collector/configuration/#service)
      service:
        pipelines:
          logs/node:
            receivers:
              - filelog
            processors:
              - batch
              - k8sattributes
              - resourcedetection/system
              - resourcedetection/eks
              - resourcedetection/gcp
              - resourcedetection/aks
              - resource/k8s
              - resource/hostname
              - resource/cloud
            exporters:
              - otlp/gateway
          metrics/node/otel:
            receivers:
              - kubeletstats
              - hostmetrics
            processors:
              - batch/metrics
              - k8sattributes
              - resourcedetection/system
              - resourcedetection/eks
              - resourcedetection/gcp
              - resourcedetection/aks
              - resource/k8s
              - resource/hostname
              - resource/cloud
            exporters:
              # - debug
              - otlp/gateway
          metrics/otel-apm:
            receivers:
              - otlp
            processors:
              - batch/metrics
              - resource/hostname
            exporters:
              - otlp/gateway
          logs/apm:
            receivers:
              - otlp
            processors:
              - batch
              - resource/hostname
            exporters:
              - otlp/gateway
          traces/apm:
            receivers:
              - otlp
            processors:
              - batch
              - resource/hostname
            exporters:
              - otlp/gateway
  #  Gateway is a K8s deployment EDOT collector focused on processing and
  #  forwarding telemetry to an Elasticsearch endpoint.
  gateway:
    fullnameOverride: "opentelemetry-kube-stack-gateway"
    suffix: gateway
    replicas: 2
    autoscaler:
      minReplicas: 2 # Start with at least 2 replicas for better availability.
      maxReplicas: 5 # Allow more scale-out if needed.
      targetCPUUtilization: 70 # Scale when CPU usage exceeds 70%.
      targetMemoryUtilization: 75 # Scale when memory usage exceeds 75%.
    resources:
      limits:
        cpu: 500m
        memory: 1000Mi
      requests:
        cpu: 100m
        memory: 500Mi
    enabled: true
    env:
      - name: ELASTIC_AGENT_OTEL
        value: '"true"'
      - name: ELASTIC_OTLP_ENDPOINT
        valueFrom:
          secretKeyRef:
            name: elastic-secret-otel
            key: elastic_otlp_endpoint
      - name: ELASTIC_API_KEY
        valueFrom:
          secretKeyRef:
            name: elastic-secret-otel
            key: elastic_api_key
    config:
      receivers:
        otlp:
          protocols:
            grpc:
              endpoint: ${env:MY_POD_IP}:4317
            http:
              endpoint: ${env:MY_POD_IP}:4318
      processors:
        batch:
          send_batch_size: 1000
          timeout: 1s
          send_batch_max_size: 1500
        batch/metrics:
          # explicitly set send_batch_max_size to 0, as splitting metrics requests may cause version_conflict_engine_exception in TSDB
          send_batch_max_size: 0
          timeout: 1s
      exporters:
        debug:
        otlp/ingest:
          endpoint: ${env:ELASTIC_OTLP_ENDPOINT}
          headers:
            Authorization: ApiKey ${env:ELASTIC_API_KEY}
      service:
        pipelines:
          metrics:
            receivers: [otlp]
            processors: [batch/metrics]
            exporters: [debug, otlp/ingest]
          logs:
            receivers: [otlp]
            processors: [batch]
            exporters: [debug, otlp/ingest]
          traces:
            receivers: [otlp]
            processors: [batch]
            exporters: [debug, otlp/ingest]
# For more details on OpenTelemetry's zero-code instrumentation, see:
# https://opentelemetry.io/docs/concepts/instrumentation/zero-code/
instrumentation:
  name: elastic-instrumentation
  enabled: true # Enable/disable auto-instrumentation.
  exporter:
    endpoint: http://opentelemetry-kube-stack-daemon-collector.opentelemetry-operator-system.svc.cluster.local:4318 # The daemonset OpenTelemetry Collector endpoint where telemetry data will be exported.
  propagators:
    - tracecontext # W3C TraceContext propagator for distributed tracing.
    - baggage # Baggage propagator to include baggage information in trace context.
    - b3 # B3 propagator for Zipkin-based distributed tracing compatibility.
  sampler:
    type: parentbased_traceidratio # Sampler type
    argument: "1.0" # Sampling rate set to 100% (all traces are sampled).
  java:
    image: docker.elastic.co/observability/elastic-otel-javaagent:1.3.0
  nodejs:
    image: docker.elastic.co/observability/elastic-otel-node:1.0.0
  dotnet:
    image: docker.elastic.co/observability/elastic-otel-dotnet:1.0.1
  python:
    image: docker.elastic.co/observability/elastic-otel-python:1.0.0
  go:
    image: ghcr.io/open-telemetry/opentelemetry-go-instrumentation/autoinstrumentation-go:v0.21.0