apiVersion: opentelemetry.io/v1alpha1
kind: OpenTelemetryCollector
metadata:
  name: o11y-platform-otel-collector
spec:
  image: otel/opentelemetry-collector-contrib:0.120.0
  ports:
    - targetPort: 55679
      name: zpages
      port: 55679
  mode: daemonset
  serviceAccount: otel-collector
  hostNetwork: true
  env:
    - name: K8S_NODE_NAME
      valueFrom:
        fieldRef:
          fieldPath: status.hostIP
    - name: MY_POD_IP
      valueFrom:
        fieldRef:
          apiVersion: v1
          fieldPath: status.podIP
  volumeMounts:
  - mountPath: /var/log/pods
    name: varlog
    readOnly: true
  - mountPath: /var/lib/docker/containers
    name: varlibdockercontainers
    readOnly: true
  - name: hostfs
    mountPath: /hostfs
    readOnly: true
    mountPropagation: HostToContainer
  volumes:
  - name: varlog
    hostPath:
      path: /var/log/pods
  - name: varlibdockercontainers
    hostPath:
      path: /var/lib/docker/containers
  - name: hostfs
    hostPath:
      path: /
  config: |
    connectors:
      spanmetrics:
        exemplars:
          enabled: true
        namespace: span.metrics
    exporters:
      debug:
        verbosity: detailed
      otlphttp/metrics:
        headers:
          X-Scope-OrgID: o11y-platform
        auth:
          authenticator: basicauth/prw
        endpoint: http://xxxxxxx:80/otlp
        tls:
          insecure: true
        retry_on_failure:
          enabled: true
          initial_interval: 5s
          max_interval: 30s
          max_elapsed_time: 300s
        sending_queue:
          enabled: true
          queue_size: 25000000
          num_consumers: 10
          storage: db_storage
      loki:
        headers:
          X-Scope-OrgID: o11y-platform
        tls:
          insecure: true
          insecure_skip_verify: true
        auth:
          authenticator: basicauth/lokiauth
        endpoint: http://xxxxxxx:3100/loki/api/v1/push
        sending_queue:
          storage: db_storage
          enabled: true
          queue_size: 25920000
          num_consumers: 10
        retry_on_failure:
          enabled: true
          initial_interval: 5s
          max_interval: 30s
          max_elapsed_time: 30s
      otlp:
        headers:
          X-Scope-OrgID: o11y-platform
        tls:
          insecure: true
        endpoint: 108.141.204.6:4317
        sending_queue:
          storage: db_storage
          enabled: true
          queue_size: 25920000
          num_consumers: 10
        retry_on_failure:
          enabled: true
          initial_interval: 5s
          max_interval: 30s
          max_elapsed_time: 30s
    extensions:
      db_storage:
        driver: "pgx"
        datasource: "postgres://otelcol:xxxxxx@postgres.otel-collector:5432/otelcol_db?sslmode=disable"
      basicauth/prw:
        client_auth:
          username: admin
          password: xxxxxx
      basicauth/lokiauth:
        client_auth:
          username: loki
          password: xxxx
      basicauth/tempoauth:
        client_auth:
          username: tempo
          password: xxxx
      zpages:
        endpoint: ':55679'
          #      file_storage:
          #        directory: /data
          #        create_directory: true
          #        compaction:
          #          on_rebound: true
          #          max_transaction_size: 65_536
          #          rebound_needed_threshold_mib: 6
          #          rebound_trigger_threshold_mib: 11
      health_check:
        endpoint: 0.0.0.0:13133
    service:
      extensions:
      - basicauth/prw
        #      - file_storage
      - basicauth/lokiauth
      - basicauth/tempoauth
      - zpages
      - db_storage
      telemetry:
        metrics:
          address: 127.0.0.1:8888
          level: detailed
        logs:
          level: debug
      pipelines:
        metrics:
          receivers:
          - otlp
          - prometheus
          - k8s_cluster
          - kubeletstats
          - spanmetrics
          - hostmetrics
          - azuremonitor
          exporters:
          - otlphttp/metrics
          - debug
          processors:
          - memory_limiter
          - attributes/metrics
          - k8sattributes
          - resource/metrics
          - batch/metrics
        logs:
          receivers:
          - filelog
          - otlp
          - azureeventhub
          exporters:
          - loki
          processors:
          - resource/logs
        traces:
          receivers:
          - otlp
          exporters:
          - otlp
          - spanmetrics
          processors:
          - memory_limiter
          - k8sattributes
          - resource/traces
          - batch/traces
    processors:
      resourcedetection/system:
        detectors: [env, system, gcp, eks]
        timeout: 2s
        override: false
      attributes/metrics:
        actions:
          - action: insert
            key: environment
            value: xxxx 
          - action: insert
            from_attribute: k8s.pod.uid
            key: service.instance.id
          - action: insert
            key: cluster_name
            value: xxxxxx
          - action: insert
            key: cloud_provider
            value: AKS
          - action: insert
            key: X_Scope_OrgID
            value: o11y-platform
          - action: insert
            key: cluster
            value: xxxxxxxx
      resource/metrics:
        attributes:
          - action: insert
            key: node
            value: ${env:K8S_NODE_NAME}
      resource/logs:
        attributes:
          - action: insert
            from_attribute: k8s.pod.uid
            key: service.instance.id
          - action: insert
            key: cluster_name
            value: xxxxxx 
          - action: insert
            key: X_Scope_OrgID
            value: o11y-platform
          - action: insert
            key: cloud_provider
            value: AKS
          - action: insert
            key: environment
            value: xxxxxx
          - action: insert
            key: node
            value: ${env:K8S_NODE_NAME}
          - action: insert
            key: loki.format
            value: raw
          - action: insert
            key: loki.resource.labels
            value: pod, namespace, container, filename, cluster_name, X_Scope_OrgID, cloud_provider, environment, node
      resource/traces:
        attributes:
          - action: insert
            from_attribute: k8s.pod.uid
            key: service.instance.id
          - action: insert
            key: cluster_name
            value: xxxxxxxx
          - action: insert
            key: X_Scope_OrgID
            value: o11y-platform
          - action: insert
            key: cloud_provider
            value: AKS
          - action: insert
            key: environment
            value: xxxxxxx 
          - action: insert
            key: node
            value: ${env:K8S_NODE_NAME}
      batch/metrics:
        send_batch_size: 8192
        timeout: 200ms
      batch/traces:
        timeout: 10s
        send_batch_size: 1024
      memory_limiter:
        check_interval: 1s
        limit_percentage: 80
        spike_limit_percentage: 20
      k8sattributes:
        auth_type: "serviceAccount"
        passthrough: true
        filter:
          node_from_env_var: K8S_NODE_NAME
    receivers:
      kubeletstats:
        collection_interval: 10s
        auth_type: "serviceAccount"
        endpoint: ${env:K8S_NODE_NAME}:10250
        insecure_skip_verify: true
        metric_groups:
        - container
        - pod
        - volume
        - node
        extra_metadata_labels:
          - container.id
          - k8s.volume.type
      k8s_cluster:
        auth_type: serviceAccount
        collection_interval: 10s
        node_conditions_to_report: [Ready, MemoryPressure,DiskPressure,NetworkUnavailable]
        allocatable_types_to_report: [cpu, memory, storage, ephemeral-storage]
      k8s_events:
        auth_type : "serviceAccount"
      otlp:
        protocols:
          grpc:
            endpoint: ${env:MY_POD_IP}:4317
          http:
            endpoint: ${env:MY_POD_IP}:4318
      prometheus:
        config:
          scrape_configs:
            - bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
              job_name: integrations/kubernetes/cadvisor
              kubernetes_sd_configs:
                - role: node
              relabel_configs:
                - replacement: kubernetes.default.svc.cluster.local:443
                  target_label: __address__
                - regex: (.+)
                  replacement: /api/v1/nodes/$${1}/proxy/metrics/cadvisor
                  source_labels:
                    - __meta_kubernetes_node_name
                  target_label: __metrics_path__
              scheme: https
              tls_config:
                ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
                insecure_skip_verify: false
                server_name: kubernetes
            - job_name: integrations/kubernetes/kube-state-metrics
              kubernetes_sd_configs:
                - role: pod
              relabel_configs:
                - action: keep
                  regex: kube-state-metrics
                  source_labels:
                    - __meta_kubernetes_pod_label_app_kubernetes_io_name
                  target_label: namespace
            - job_name: integrations/node_exporter
              kubernetes_sd_configs:
                - role: pod
              relabel_configs:
                - action: keep
                  regex: prometheus-node-exporter.*
                  source_labels:
                    - __meta_kubernetes_pod_label_app_kubernetes_io_name
                - action: replace
                  source_labels:
                    - __meta_kubernetes_pod_node_name
                  target_label: instance
                - action: replace
                  source_labels:
                    - __meta_kubernetes_namespace
                  target_label: namespace
            - bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
              job_name: integrations/kubernetes/kubelet
              kubernetes_sd_configs:
                - role: node
              relabel_configs:
                - replacement: kubernetes.default.svc.cluster.local:443
                  target_label: __address__
                - regex: (.+)
                  replacement: /api/v1/nodes/$${1}/proxy/metrics
                  source_labels:
                    - __meta_kubernetes_node_name
                  target_label: __metrics_path__
              scheme: https
              tls_config:
                ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
                insecure_skip_verify: false
                server_name: kubernetes
            - job_name: "kubernetes-apiservers"
              kubernetes_sd_configs:
                - role: endpoints
                  namespaces:
                    names:
                      - default
              scheme: https
              tls_config:
                ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
                insecure_skip_verify: true
              bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
              relabel_configs:
              - source_labels: [__meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
                action: keep
                regex: kubernetes;https
              - action: replace
                source_labels:
                - __meta_kubernetes_namespace
                target_label: Namespace
              - action: replace
                source_labels:
                - __meta_kubernetes_service_name
                target_label: Service

      hostmetrics:
        root_path: /hostfs
        collection_interval: 10s
        scrapers:
          cpu:
            metrics:
              system.cpu.utilization:
                enabled: true
          disk: null
          load:
          filesystem:
            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
            exclude_mount_points:
              match_type: regexp
              mount_points:
              - /dev/*
              - /proc/*
              - /sys/*
              - /run/k3s/containerd/*
              - /var/lib/docker/*
              - /var/lib/kubelet/*
              - /snap/*
            metrics:
              system.filesystem.utilization:
                enabled: true
          memory:
            metrics:
              system.memory.utilization:
                enabled: true
          network:
          paging:
      filelog:
        include:
         - /var/log/pods/*/*/*.log
        start_at: beginning
        include_file_path: true
        include_file_name: false
        operators:
        - type: router
          id: get-format
          routes:
          - output: parser-docker
            expr: 'body matches "^\\{"'
          - output: parser-crio
            expr: 'body matches "^[^ Z]+ "'
          - output: parser-containerd
            expr: 'body matches "^[^ Z]+Z"'
        - type: regex_parser
          id: parser-crio
          regex: '^(?P<time>[^ Z]+) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
          output: extract_metadata_from_filepath
          timestamp:
            parse_from: attributes.time
            layout_type: gotime
            layout: '2024-03-11T13:15:05.999999999Z07:00'
        - type: regex_parser
          id: parser-containerd
          regex: '^(?P<time>[^ ^Z]+Z) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
          output: extract_metadata_from_filepath
          timestamp:
            parse_from: attributes.time
            layout: '%Y-%m-%dT%H:%M:%S.%LZ'
        - type: json_parser
          id: parser-docker
          output: extract_metadata_from_filepath
          timestamp:
            parse_from: attributes.time
            layout: '%Y-%m-%dT%H:%M:%S.%LZ'
        - type: move
          from: attributes.log
          to: body
        - type: regex_parser
          id: extract_metadata_from_filepath
          regex: '^.*\/(?P<namespace>[^_]+)_(?P<pod_name>[^_]+)_(?P<uid>[a-f0-9\-]{36})\/(?P<container_name>[^\._]+)\/(?P<restart_count>\d+)\.log$'
          parse_from: attributes["log.file.path"]
          cache:
            size: 128
        - type: move
          from: attributes["log.file.path"]
          to: resource["filename"]
        - type: move
          from: attributes.container_name
          to: resource["container"]
        - type: move
          from: attributes.namespace
          to: resource["namespace"]
        - type: move
          from: attributes.pod_name
          to: resource["pod"]
      azuremonitor:
        subscription_id: xxxxxxxxxxxxx
        tenant_id: xxxxxxxxxxxxx
        client_id: xxxxxxxxxx
        client_secret: xxxxxxxxxxxxx
        cloud: AzureCloud
        resource_groups:
          - xxxxxx
        collection_interval: 2s
        initial_delay: 1
      azureeventhub:
        connection: xxxxxxxxxxxxxxxxxx
        partition:
        group:
        offset:
        format: "azure"