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

nameOverride: ""
fullnameOverride: "opentelemetry-admin-prd"

dedicatedValue: false
schedulerName: default-scheduler

labels:
  bu: "infra"
  team: "sre"
  service: "opentelemetry-admin-prd"
  env: "prd"
  priority: "p0"
  type: "opentelemetry"
  arch: "any"
  runpod: "ondemand"

externalSecret:
  enabled: true
  key: prd/admin/coralogix-keys
  secretStoreRef:
    name: vault-backend

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

# Specify which namespace should be used to deploy the resources into
namespaceOverride: ""

# Handles basic configuration of components that
# also require k8s modifications to work correctly.
# .Values.config can be used to modify/add to a preset
# component configuration, but CANNOT be used to remove
# preset configuration. If you require removal of any
# sections of a preset configuration, you cannot use
# the preset. Instead, configure the component manually in
# .Values.config and use the other fields supplied in the
# values.yaml to configure k8s as necessary.
presets:
  # Configures the collector to collect logs.
  # Adds the filelog receiver to the logs pipeline
  # and adds the necessary volumes and volume mounts.
  # Best used with mode = daemonset.
  # See https://opentelemetry.io/docs/kubernetes/collector/components/#filelog-receiver for details on the receiver.
  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
    # The maximum bytes size of the recombined field.
    # Once the size exceeds the limit, all received entries of the source will be combined and flushed.
    maxRecombineLogSize: 102400
  # 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.
  # See https://opentelemetry.io/docs/kubernetes/collector/components/#host-metrics-receiver for details on the receiver.
  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.
  # See https://opentelemetry.io/docs/kubernetes/collector/components/#kubernetes-attributes-processor for details on the receiver.
  kubernetesAttributes:
    enabled: false
    # When enabled the processor will extra all labels for an associated pod and add them as resource attributes.
    # The label's exact name will be the key.
    extractAllPodLabels: false
    # When enabled the processor will extra all annotations for an associated pod and add them as resource attributes.
    # The annotation's exact name will be the key.
    extractAllPodAnnotations: false
  # Configures the collector to collect node, pod, and container metrics from the API server on a kubelet..
  # Adds the kubeletstats receiver to the metrics pipeline
  # and adds the necessary rules to ClusteRole.
  # Best used with mode = daemonset.
  # See https://opentelemetry.io/docs/kubernetes/collector/components/#kubeletstats-receiver for details on the receiver.
  kubeletMetrics:
    enabled: false
  # Configures the collector to collect kubernetes events.
  # Adds the k8sobject receiver to the logs pipeline
  # and collects kubernetes events by default.
  # Best used with mode = deployment or statefulset.
  # See https://opentelemetry.io/docs/kubernetes/collector/components/#kubernetes-objects-receiver for details on the receiver.
  kubernetesEvents:
    enabled: false
  # 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.
  # See https://opentelemetry.io/docs/kubernetes/collector/components/#kubernetes-cluster-receiver for details on the receiver.
  clusterMetrics:
    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:
  receivers:
    otlp:
      protocols:
        grpc:
          endpoint: ${env:MY_POD_IP}:4317
          max_recv_msg_size_mib: 7
        http:
          endpoint: ${env:MY_POD_IP}:4318
  processors:
    batch:
        send_batch_size: 1024
        timeout: 5s
    # If set to null, will be overridden with values based on k8s resource limits
    memory_limiter: null
    attributes/shipper:
      actions:
        - key: shipper
          action: insert
          value: '${MY_POD_IP}'
        - key: cloud
          action: insert
          value: 'gcp'
    tail_sampling:
      decision_wait: 30s
      num_traces: 300000
      expected_new_traces_per_sec: 100000
      policies:
        [
          {
            name: errors-policy,
            type: status_code,
            status_code: {status_codes: [ERROR]}
          },
          {
          name: probablistic-policy,
          type: probabilistic,
          probabilistic: {sampling_percentage: 1}
          }
        ]
    # filter/include:
    #   spans:
    #     include:
    #       match_type: regexp
    #       services:
    #         - order-service
  exporters:
    logging: {}
    coralogix:
      domain: "coralogixsg.com"
      private_key: "${CORALOGIX_PRIVATE_KEY}"
      application_name: "default"
      subsystem_name: "nodes"
      application_name_attributes:
        - "applicationName"
        - "service.namespace"
        - "k8s.namespace.name"
      subsystem_name_attributes:
        - "service.name"
        - "k8s.deployment.name"
        - "k8s.statefulset.name"
        - "k8s.daemonset.name"
        - "k8s.cronjob.name"
        - "k8s.job.name"
        - "k8s.container.name"
      timeout: 30s
    otlp/elastic:
      endpoint: "946ece6f7b344005aa1e5c273b1a886f.apm.psc.asia-southeast1.gcp.elastic-cloud.com:443"
      headers:
        Authorization: "Bearer ehllv9fQQ7GGMOjE79"
      timeout: 10s
  extensions:
    # The health_check extension is mandatory for this chart.
    # Without the health_check extension the collector will fail the readiness and liveliness probes.
    # The health_check extension can be modified, but should never be removed.
    health_check: {}
#    memory_ballast: {}

  connectors:
    spanmetrics:
      histogram:
        explicit:
          buckets: [100us, 1ms, 2ms, 6ms, 10ms, 100ms, 250ms]
      dimensions_cache_size: 1000
      aggregation_temporality: "AGGREGATION_TEMPORALITY_CUMULATIVE"    
      metrics_flush_interval: 15s 

  service:
    telemetry:
      metrics:
        address: ${env:MY_POD_IP}:8888
    extensions:
      - health_check
#      - memory_ballast
    pipelines:
      # traces:
      #   receivers:
      #     - otlp
      #   processors:
      #     - tail_sampling 
      #     - attributes/shipper
      #     - batch
      #   exporters:
      #     - coralogix
#          - spanmetrics
      traces:
        receivers:
          - otlp
        processors:
          - tail_sampling 
          - attributes/shipper
#          - filter/include
          - batch
        exporters:
          - otlp/elastic
          # - spanmetrics
      metrics: null
      logs: null

image:
  # If you want to use the core image `otel/opentelemetry-collector`, you also need to change `command.name` value to `otelcol`.
  #repository: 847438129436.dkr.ecr.ap-southeast-1.amazonaws.com/otel/opentelemetry-collector-contrib
  repository: asia-southeast1-docker.pkg.dev/meesho-devops-admin-0622/admin/sre/opentelemetry-collector-contrib
  # repository: otel/opentelemetry-collector-contrib
  pullPolicy: IfNotPresent
  # Overrides the image tag whose default is the chart appVersion.
  tag: "0.87.0"
  # When digest is set to a non-empty value, images will be pulled by digest (regardless of tag value).
  digest: ""
imagePullSecrets: []

# OpenTelemetry Collector executable
command:
  name: otelcol-contrib
  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 to add to the clusterRoleBinding
    # Can be used in combination with presets that create a cluster role binding.
    annotations: {}
    # The name of the clusterRoleBinding 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 binding.
    name: ""

podSecurityContext: {}
securityContext: {}

# nodeSelector: []
# tolerations: {}

nodeSelector:
    dedicated: "opentelemetry"

tolerations:  
  - key: "dedicated"
    operator: "Equal"
    value: "opentelemetry"
    effect: "NoSchedule"

affinity: {}
topologySpreadConstraints: []

# Allows for pod scheduler prioritisation
priorityClassName: ""

#extraEnvs: []

extraEnvs:
- name: OTEL_RESOURCE_ATTRIBUTES
  value: "k8s.node.name=$(K8S_NODE_NAME)"
- name: KUBE_NODE_NAME
  valueFrom:
    fieldRef:
      apiVersion: v1
      fieldPath: spec.nodeName

extraEnvsFrom: []
extraVolumes: []
extraVolumeMounts: []

# Configuration for ports
# nodePort is also allowed
ports:
  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
    protocol: TCP
  jaeger-compact:
    enabled: false
    containerPort: 6831
    servicePort: 6831
    # hostPort: 6831
    protocol: UDP
  jaeger-thrift:
    enabled: false
    containerPort: 14268
    servicePort: 14268
    # hostPort: 14268
    protocol: TCP
  jaeger-grpc:
    enabled: false
    containerPort: 14250
    servicePort: 14250
    # hostPort: 14250
    protocol: TCP
  zipkin:
    enabled: false
    containerPort: 9411
    servicePort: 9411
    # hostPort: 9411
    protocol: TCP
  metrics:
    # The metrics port is disabled by default. However you need to enable the port
    # in order to use the ServiceMonitor (serviceMonitor.enabled) or PodMonitor (podMonitor.enabled).
    enabled: false
    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: {}
resources:
  requests:
    cpu: 25
    memory: 25Gi
  limits:
    cpu: 30
    memory: 30Gi

# Annotations to be added to pod
podAnnotations:
  otel.io/path: /metrics
  otel.io/port: '8888'
  otel.io/scrape: 'true'

podLabels: {}

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

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

# Custom DNS config. Required when DNS policy is None.
dnsConfig: {}

# only used with deployment mode
replicaCount: 1

# only used with deployment mode
revisionHistoryLimit: 100

annotations: {}
  # prometheus.io/path: "/metrics"
  # prometheus.io/scrape: "true"
  # prometheus.io/port: "8888"

# 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: []
# initContainers:
#   - name: test
#     image: busybox:latest
#     command:
#       - cp
#     args:
#       - /bin/sleep
#       - /test/sleep
#     volumeMounts:
#       - name: test
#         mountPath: /test
#  - name: init-fs
#    image: busybox:latest
#    command:
#      - sh
#      - '-c'
#      - 'chown -R 10001: /var/lib/storage/otc' # use the path given as per `extensions.file_storage.directory` & `extraVolumeMounts[x].mountPath`
#    volumeMounts:
#      - name: opentelemetry-collector-data # use the name of the volume used for persistence
#        mountPath: /var/lib/storage/otc # use the path given as per `extensions.file_storage.directory` & `extraVolumeMounts[x].mountPath`

# Pod lifecycle policies.
lifecycleHooks: {}
# lifecycleHooks:
#   preStop:
#     exec:
#       command:
#       - /test/sleep
#       - "5"

# liveness probe configuration
# Ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
##
livenessProbe:
  # Number of seconds after the container has started before startup, liveness or readiness probes are initiated.
  # initialDelaySeconds: 1
  # How often in seconds to perform the probe.
  # periodSeconds: 10
  # Number of seconds after which the probe times out.
  # timeoutSeconds: 1
  # Minimum consecutive failures for the probe to be considered failed after having succeeded.
  # failureThreshold: 1
  # Duration in seconds the pod needs to terminate gracefully upon probe failure.
  # terminationGracePeriodSeconds: 10
  httpGet:
    port: 13133
    path: /

# readiness probe configuration
# Ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
##
readinessProbe:
  # Number of seconds after the container has started before startup, liveness or readiness probes are initiated.
  # initialDelaySeconds: 1
  # How often (in seconds) to perform the probe.
  # periodSeconds: 10
  # Number of seconds after which the probe times out.
  # timeoutSeconds: 1
  # Minimum consecutive successes for the probe to be considered successful after having failed.
  # successThreshold: 1
  # Minimum consecutive failures for the probe to be considered failed after having succeeded.
  # failureThreshold: 1
  httpGet:
    port: 13133
    path: /

service:
  # Enable the creation of a Service.
  # By default, it's enabled on mode != daemonset.
  # However, to enable it on mode = daemonset, its creation must be explicitly enabled
  # enabled: true

  type: ClusterIP
  # type: LoadBalancer
  # loadBalancerIP: 1.2.3.4
  # loadBalancerSourceRanges: []

  # By default, Service of type 'LoadBalancer' will be created setting 'externalTrafficPolicy: Cluster'
  # unless other value is explicitly set.
  # Possible values are Cluster or Local (https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip)
  # externalTrafficPolicy: Cluster

  annotations:
    io.cilium/global-service: "true"

  # By default, Service will be created setting 'internalTrafficPolicy: Local' on mode = daemonset
  # unless other value is explicitly set.
  # Setting 'internalTrafficPolicy: Cluster' on a daemonset is not recommended
  # internalTrafficPolicy: Cluster

ingress:
  enabled: false
  # annotations: {}
  # ingressClassName: nginx
  # hosts:
  #   - host: collector.example.com
  #     paths:
  #       - path: /
  #         pathType: Prefix
  #         port: 4318
  # tls:
  #   - secretName: collector-tls
  #     hosts:
  #       - collector.example.com

  # Additional ingresses - only created if ingress.enabled is true
  # Useful for when differently annotated ingress services are required
  # Each additional ingress needs key "name" set to something unique
  additionalIngresses: []
  # - name: cloudwatch
  #   ingressClassName: nginx
  #   annotations: {}
  #   hosts:
  #     - host: collector.example.com
  #       paths:
  #         - path: /
  #           pathType: Prefix
  #           port: 4318
  #   tls:
  #     - secretName: collector-tls
  #       hosts:
  #         - collector.example.com

podMonitor:
  # The pod 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 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: true
  minReplicas: 5
  maxReplicas: 300
  behavior: {}
  targetCPUUtilizationPercentage: 80
  targetMemoryUtilizationPercentage: 80

rollout:
  # When 'mode: daemonset', maxSurge cannot be used when hostPort is set for any of the ports
  rollingUpdate:
    # maxSurge: 10%
    maxUnavailable: 5
  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"

networkPolicy:
  enabled: false

  # Annotations to add to the NetworkPolicy
  annotations: {}

  # Configure the 'from' clause of the NetworkPolicy.
  # By default this will restrict traffic to ports enabled for the Collector. If
  # you wish to further restrict traffic to other hosts or specific namespaces,
  # see the standard NetworkPolicy 'spec.ingress.from' definition for more info:
  # https://kubernetes.io/docs/reference/kubernetes-api/policy-resources/network-policy-v1/
  allowIngressFrom: []
  # # Allow traffic from any pod in any namespace, but not external hosts
  # - namespaceSelector: {}
  # # Allow external access from a specific cidr block
  # - ipBlock:
  #     cidr: 192.168.1.64/32
  # # Allow access from pods in specific namespaces
  # - namespaceSelector:
  #     matchExpressions:
  #       - key: kubernetes.io/metadata.name
  #         operator: In
  #         values:
  #           - "cats"
  #           - "dogs"

  # Add additional ingress rules to specific ports
  # Useful to allow external hosts/services to access specific ports
  # An example is allowing an external prometheus server to scrape metrics
  #
  # See the standard NetworkPolicy 'spec.ingress' definition for more info:
  # https://kubernetes.io/docs/reference/kubernetes-api/policy-resources/network-policy-v1/
  extraIngressRules: []
  # - ports:
  #   - port: metrics
  #     protocol: TCP
  #   from:
  #     - ipBlock:
  #         cidr: 192.168.1.64/32

  # Restrict egress traffic from the OpenTelemetry collector pod
  # See the standard NetworkPolicy 'spec.egress' definition for more info:
  # https://kubernetes.io/docs/reference/kubernetes-api/policy-resources/network-policy-v1/
  egressRules: []
  #  - to:
  #      - namespaceSelector: {}
  #      - ipBlock:
  #          cidr: 192.168.10.10/24
  #    ports:
  #      - port: 1234
  #        protocol: TCP