clearml-helm-charts/charts/clearml/values.yaml

clearml:
  defaultCompany: "d1bd92a3b039400cbafc60a7a5b1e52b"
ingress:
  enabled: false
  name: clearml-server-ingress
  annotations: {}
  app:
    hostName: "app.clearml.127-0-0-1.nip.io"
    tlsSecretName: ""
  api:
    hostName: "api.clearml.127-0-0-1.nip.io"
    tlsSecretName: ""
  files:
    hostName: "files.clearml.127-0-0-1.nip.io"
    tlsSecretName: ""

apiserver:
  prepopulateEnabled: "true"
  prepopulateZipFiles: "/opt/clearml/db-pre-populate"
  prepopulateArtifactsPath: "/mnt/fileserver"
  configDir: /opt/clearml/config

  service:
    type: NodePort
    port: 8008

  livenessDelay: 60
  readinessDelay: 60

  replicaCount: 1

  image:
    repository: "allegroai/clearml"
    pullPolicy: IfNotPresent
    tag: "1.1.1"

  extraEnvs: []

  podAnnotations: {}

  resources: {}
    # We usually recommend not to specify default resources and to leave this as a conscious
    # choice for the user. This also increases chances charts run on environments with little
    # resources, such as Minikube. If you do want to specify resources, uncomment the following
    # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
    # limits:
    #   cpu: 100m
    #   memory: 128Mi
    # requests:
    #   cpu: 100m
    #   memory: 128Mi

  nodeSelector: {}

  tolerations: []

  affinity: {}

  additionalConfigs: {}
    # services.conf: |
    #   tasks {
    #     non_responsive_tasks_watchdog {
    #       # In-progress tasks that haven't been updated for at least 'value' seconds will be stopped by the watchdog
    #       threshold_sec: 21000
    #       # Watchdog will sleep for this number of seconds after each cycle
    #       watch_interval_sec: 900
    #     }
    #   }

fileserver:
  service:
    type: NodePort
    port: 8081

  replicaCount: 1

  image:
    repository: "allegroai/clearml"
    pullPolicy: IfNotPresent
    tag: "1.1.1"

  extraEnvs: []

  podAnnotations: {}

  resources: {}
    # We usually recommend not to specify default resources and to leave this as a conscious
    # choice for the user. This also increases chances charts run on environments with little
    # resources, such as Minikube. If you do want to specify resources, uncomment the following
    # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
    # limits:
    #   cpu: 100m
    #   memory: 128Mi
    # requests:
    #   cpu: 100m
    #   memory: 128Mi

  nodeSelector: {}

  tolerations: []

  affinity: {}

  storage:
    data:
      class: "standard"
      size: 50Gi

webserver:
  extraEnvs: []

  service:
    type: NodePort
    port: 80

  replicaCount: 1

  image:
    repository: "allegroai/clearml"
    pullPolicy: IfNotPresent
    tag: "1.1.1"

  podAnnotations: {}

  resources: {}
    # We usually recommend not to specify default resources and to leave this as a conscious
    # choice for the user. This also increases chances charts run on environments with little
    # resources, such as Minikube. If you do want to specify resources, uncomment the following
    # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
    # limits:
    #   cpu: 100m
    #   memory: 128Mi
    # requests:
    #   cpu: 100m
    #   memory: 128Mi

  nodeSelector: {}

  tolerations: []

  affinity: {}

agentservices:
  enabled: false
  clearmlHostIp: null
  agentVersion: ""
  clearmlWebHost: null
  clearmlFilesHost: null
  clearmlGitUser: null
  clearmlGitPassword: null
  awsAccessKeyId: null
  awsSecretAccessKey: null
  awsDefaultRegion: null
  azureStorageAccount: null
  azureStorageKey: null
  googleCredentials: null
  clearmlWorkerId: "clearml-services"

  replicaCount: 1

  image:
    repository: "allegroai/clearml-agent-services"
    pullPolicy: IfNotPresent
    tag: "latest"

  extraEnvs: []

  podAnnotations: {}

  resources: {}
    # We usually recommend not to specify default resources and to leave this as a conscious
    # choice for the user. This also increases chances charts run on environments with little
    # resources, such as Minikube. If you do want to specify resources, uncomment the following
    # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
    # limits:
    #   cpu: 100m
    #   memory: 128Mi
    # requests:
    #   cpu: 100m
    #   memory: 128Mi

  nodeSelector: {}

  tolerations: []

  affinity: {}

  storage:
    data:
      class: "standard"
      size: 50Gi

agentGroups:
  agent-group-cpu:
    enabled: true
    name: agent-group-cpu
    replicaCount: 1
    updateStrategy: Recreate
    nvidiaGpusPerAgent: 0
    agentVersion: ""  # if set, it *MUST* include comparison operator (e.g. ">=0.16.1")
    queues: "default"  # multiple queues can be specified separated by a space (e.g. "important_jobs default")
    clearmlGitUser: null
    clearmlGitPassword: null
    clearmlAccessKey: null
    clearmlSecretKey: null
    awsAccessKeyId: null
    awsSecretAccessKey: null
    awsDefaultRegion: null
    azureStorageAccount: null
    azureStorageKey: null
    clearmlConfig: |-
      sdk {
      }

    image:
      repository: "ubuntu"
      pullPolicy: IfNotPresent
      tag: "18.04"

    podAnnotations: {}

    nodeSelector: {}

    tolerations: []

    affinity: {}

  agent-group-gpu:
    enabled: true
    name: agent-group-gpu
    replicaCount: 0
    updateStrategy: Recreate
    nvidiaGpusPerAgent: 1
    agentVersion: ""  # if set, it *MUST* include comparison operator (e.g. ">=0.16.1")
    queues: "default"  # multiple queues can be specified separated by a space (e.g. "important_jobs default")
    clearmlGitUser: null
    clearmlGitPassword: null
    clearmlAccessKey: null
    clearmlSecretKey: null
    awsAccessKeyId: null
    awsSecretAccessKey: null
    awsDefaultRegion: null
    azureStorageAccount: null
    azureStorageKey: null
    clearmlConfig: |-
      sdk {
      }

    image:
      repository: "nvidia/cuda"
      pullPolicy: IfNotPresent
      tag: "11.0-base-ubuntu18.04"

    podAnnotations: {}

    nodeSelector: {}

    tolerations: []

    affinity: {}

redis:  # configuration from https://github.com/bitnami/charts/blob/master/bitnami/redis/values.yaml
  enabled: true
  usePassword: false
  databaseNumber: 0
  master:
    name: "{{ .Release.Name }}-redis-master"
    port: 6379
    persistence:
      enabled: true
      accessModes:
        - ReadWriteOnce
      size: 5Gi
  cluster:
    enabled: false

mongodb:  # configuration from https://github.com/bitnami/charts/blob/master/bitnami/mongodb/values.yaml
  enabled: true
  architecture: standalone
  auth:
    enabled: false
  replicaCount: 1
  persistence:
    enabled: true
    accessModes:
      - ReadWriteOnce
    size: 50Gi
  service:
    name: "{{ .Release.Name }}-mongodb"
    type: ClusterIP
    port: 27017
    portName: mongo-service

elasticsearch:  # configuration from https://github.com/elastic/helm-charts/blob/7.10/elasticsearch/values.yaml
  enabled: true
  httpPort: 9200
  roles:
    master: "true"
    ingest: "true"
    data: "true"
    remote_cluster_client: "true"
  replicas: 1
  # Readiness probe hack for a single-node cluster (where status will never be green). Should be removed if using replicas > 1
  clusterHealthCheckParams: "wait_for_status=yellow&timeout=1s"

  minimumMasterNodes: 1
  clusterName: clearml-elastic
  esJavaOpts: "-Xmx2g -Xms2g"
  extraEnvs:
    - name: bootstrap.memory_lock
      value: "false"
    - name: cluster.routing.allocation.node_initial_primaries_recoveries
      value: "500"
    - name: cluster.routing.allocation.disk.watermark.low
      value: 500mb
    - name: cluster.routing.allocation.disk.watermark.high
      value: 500mb
    - name: cluster.routing.allocation.disk.watermark.flood_stage
      value: 500mb
    - name: http.compression_level
      value: "7"
    - name: reindex.remote.whitelist
      value: '*.*'
    - name: xpack.monitoring.enabled
      value: "false"
    - name: xpack.security.enabled
      value: "false"
  resources:
    requests:
      memory: "4Gi"
    limits:
      memory: "4Gi"
  persistence:
    enabled: true
  volumeClaimTemplate:
    accessModes: ["ReadWriteOnce"]
    resources:
      requests:
        storage: 50Gi
  esConfig:
    elasticsearch.yml: |
      xpack.security.enabled: false