DataMate/deployment/helm/ray/ray-cluster/values.yaml

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

# The KubeRay community welcomes PRs to expose additional configuration
# in this Helm chart.

image:
  repository: runtime
  tag: latest
  pullPolicy: IfNotPresent

nameOverride: "kuberay"
fullnameOverride: ""

imagePullSecrets: []
# - name: an-existing-secret

# common defined values shared between the head and worker
common:
  # containerEnv specifies environment variables for the Ray head and worker containers.
  # Follows standard K8s container env schema.
  containerEnv: []
  #  - name: BLAH
  #    value: VAL
head:
  # rayVersion determines the autoscaler's image version.
  # It should match the Ray version in the image of the containers.
  # rayVersion: 2.46.0
  # If enableInTreeAutoscaling is true, the autoscaler sidecar will be added to the Ray head pod.
  # Ray autoscaler integration is supported only for Ray versions >= 1.11.0
  # Ray autoscaler integration is Beta with KubeRay >= 0.3.0 and Ray >= 2.0.0.
  # enableInTreeAutoscaling: true
  # autoscalerOptions is an OPTIONAL field specifying configuration overrides for the Ray autoscaler.
  # The example configuration shown below represents the DEFAULT values.
  # autoscalerOptions:
  # upscalingMode: Default
  # idleTimeoutSeconds is the number of seconds to wait before scaling down a worker pod which is not using Ray resources.
  # idleTimeoutSeconds: 60
  # imagePullPolicy optionally overrides the autoscaler container's default image pull policy (IfNotPresent).
  # imagePullPolicy: IfNotPresent
  # Optionally specify the autoscaler container's securityContext.
  # securityContext: {}
  # env: []
  # envFrom: []
  # resources specifies optional resource request and limit overrides for the autoscaler container.
  # For large Ray clusters, we recommend monitoring container resource usage to determine if overriding the defaults is required.
  # resources:
  #   limits:
  #     cpu: "500m"
  #     memory: "512Mi"
  #   requests:
  #     cpu: "500m"
  #     memory: "512Mi"
  initContainers: []
  labels: {}
  # Note: From KubeRay v0.6.0, users need to create the ServiceAccount by themselves if they specify the `serviceAccountName`
  # in the headGroupSpec. See https://github.com/ray-project/kuberay/pull/1128 for more details.
  serviceAccountName: ""
  restartPolicy: ""
  rayStartParams:
    object-store-memory: '78643200'
  # containerEnv specifies environment variables for the Ray container,
  # Follows standard K8s container env schema.
  containerEnv:
    - name: RAY_DEDUP_LOGS
      value: "0"
    - name: RAY_TQDM_PATCH_PRINT
      value: "0"
    - name: MYSQL_HOST
      value: "mysql"
    - name: MYSQL_PORT
      value: "3306"
    - name: MYSQL_USER
      value: "root"
    - name: MYSQL_PASSWORD
      value: "Huawei@123"
    - name: MYSQL_DATABASE
      value: "datamate"
  # - name: EXAMPLE_ENV
  #   value: "1"
  envFrom: []
    # - secretRef:
  #     name: my-env-secret
  # ports optionally allows specifying ports for the Ray container.
  # ports: []
  # resource requests and limits for the Ray head container.
  # Modify as needed for your application.
  # Note that the resources in this example are much too small for production;
  # we don't recommend allocating less than 8G memory for a Ray pod in production.
  # Ray pods should be sized to take up entire K8s nodes when possible.
  # Always set CPU and memory limits for Ray pods.
  # It is usually best to set requests equal to limits.
  # See https://docs.ray.io/en/latest/cluster/kubernetes/user-guides/config.html#resources
  # for further guidance.
  resources:
    limits:
      cpu: "2"
      # To avoid out-of-memory issues, never allocate less than 2G memory for the Ray head.
      memory: "4G"
    requests:
      cpu: "1"
      memory: "2G"
  annotations: {}
  nodeSelector: {}
  tolerations: []
  affinity: {}
  # Pod security context.
  podSecurityContext: {}
  # Ray container security context.
  securityContext: {}
  # Optional: The following volumes/volumeMounts configurations are optional but recommended because
  # Ray writes logs to /tmp/ray/session_latests/logs instead of stdout/stderr.
  volumes:
    - name: log-volume
      hostPath:
        path: /opt/data-mate/data/log
        type: DirectoryOrCreate
    - name: dataset-volume
      hostPath:
        path: /opt/data-mate/data/dataset
        type: DirectoryOrCreate
    - name: flow-volume
      hostPath:
        path: /opt/data-mate/data/flow
        type: DirectoryOrCreate
  volumeMounts:
    - mountPath: /tmp/ray
      name: log-volume
      subPath: ray/head
    - mountPath: /dataset
      name: dataset-volume
    - mountPath: /flow
      name: flow-volume
  # sidecarContainers specifies additional containers to attach to the Ray pod.
  # Follows standard K8s container spec.
  sidecarContainers:
    - name: runtime
      image: runtime
      imagePullPolicy: IfNotPresent
      command:
        - python
        - /opt/runtime/datamate/operator_runtime.py
        - --port
        - "8081"
      env:
        - name: MYSQL_HOST
          value: "mysql"
        - name: MYSQL_PORT
          value: "3306"
        - name: MYSQL_USER
          value: "root"
        - name: MYSQL_PASSWORD
          value: "Huawei@123"
        - name: MYSQL_DATABASE
          value: "datamate"
      ports:
        - containerPort: 8081
      volumeMounts:
        - mountPath: /tmp/ray
          name: log-volume
          subPath: ray/head
        - mountPath: /var/log/data-mate
          name: log-volume
        - mountPath: /dataset
          name: dataset-volume
        - mountPath: /flow
          name: flow-volume
  # See docs/guidance/pod-command.md for more details about how to specify
  # container command for head Pod.
  command: []
  args: []
  # Optional, for the user to provide any additional fields to the service.
  # See https://pkg.go.dev/k8s.io/Kubernetes/pkg/api/v1#Service
  headService: {}
    # metadata:
    #   annotations:
  #     prometheus.io/scrape: "true"

  # Custom pod DNS configuration
  # See https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/#pod-dns-config
  # dnsConfig:
  #   nameservers:
  #     - 8.8.8.8
  #   searches:
  #     - example.local
  #   options:
  #     - name: ndots
  #       value: "2"
  #     - name: edns0
  topologySpreadConstraints: []


worker:
  # If you want to disable the default workergroup
  # uncomment the line below
  # disabled: true
  groupName: workergroup
  replicas: 1
  minReplicas: 1
  maxReplicas: 3
  labels: {}
  serviceAccountName: ""
  restartPolicy: ""
  rayStartParams: {}
  initContainers: []
  # containerEnv specifies environment variables for the Ray container,
  # Follows standard K8s container env schema.
  containerEnv:
    - name: RAY_DEDUP_LOGS
      value: "0"
    - name: RAY_TQDM_PATCH_PRINT
      value: "0"
    - name: MYSQL_HOST
      value: "mysql"
    - name: MYSQL_PORT
      value: "3306"
    - name: MYSQL_USER
      value: "root"
    - name: MYSQL_PASSWORD
      value: "Huawei@123"
    - name: MYSQL_DATABASE
      value: "datamate"
  # - name: EXAMPLE_ENV
  #   value: "1"
  envFrom: []
    # - secretRef:
  #     name: my-env-secret
  # ports optionally allows specifying ports for the Ray container.
  # ports: []
  # resource requests and limits for the Ray head container.
  # Modify as needed for your application.
  # Note that the resources in this example are much too small for production;
  # we don't recommend allocating less than 8G memory for a Ray pod in production.
  # Ray pods should be sized to take up entire K8s nodes when possible.
  # Always set CPU and memory limits for Ray pods.
  # It is usually best to set requests equal to limits.
  # See https://docs.ray.io/en/latest/cluster/kubernetes/user-guides/config.html#resources
  # for further guidance.
  resources:
    limits:
      cpu: "4"
      memory: "8G"
    requests:
      cpu: "1"
      memory: "1G"
  annotations: {}
  nodeSelector: {}
  tolerations: []
  affinity: {}
  # Pod security context.
  podSecurityContext: {}
  # Ray container security context.
  securityContext: {}
  # Optional: The following volumes/volumeMounts configurations are optional but recommended because
  # Ray writes logs to /tmp/ray/session_latests/logs instead of stdout/stderr.
  volumes:
    - name: log-volume
      hostPath:
        path: /opt/data-mate/data/log
        type: DirectoryOrCreate
    - name: dataset-volume
      hostPath:
        path: /opt/data-mate/data/dataset
        type: DirectoryOrCreate
    - name: flow-volume
      hostPath:
        path: /opt/data-mate/data/flow
        type: DirectoryOrCreate
  volumeMounts:
    - mountPath: /tmp/ray
      name: log-volume
      subPath: ray/worker
    - mountPath: /dataset
      name: dataset-volume
    - mountPath: /flow
      name: flow-volume
  # sidecarContainers specifies additional containers to attach to the Ray pod.
  # Follows standard K8s container spec.
  sidecarContainers: []
  # See docs/guidance/pod-command.md for more details about how to specify
  # container command for worker Pod.
  command: []
  args: []
  topologySpreadConstraints: []


  # Custom pod DNS configuration
  # See https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/#pod-dns-config
  # dnsConfig:
  #   nameservers:
  #     - 8.8.8.8
  #   searches:
  #     - example.local
  #   options:
  #     - name: ndots
  #       value: "2"
  #     - name: edns0

# The map's key is used as the groupName.
# For example, key:small-group in the map below
# will be used as the groupName
additionalWorkerGroups:
  smallGroup:
    # Disabled by default
    disabled: true
    replicas: 0
    minReplicas: 0
    maxReplicas: 3
    labels: {}
    serviceAccountName: ""
    restartPolicy: ""
    rayStartParams: {}
    # containerEnv specifies environment variables for the Ray container,
    # Follows standard K8s container env schema.
    containerEnv: []
      # - name: EXAMPLE_ENV
    #   value: "1"
    envFrom: []
      # - secretRef:
    #     name: my-env-secret
    # ports optionally allows specifying ports for the Ray container.
    # ports: []
    # resource requests and limits for the Ray head container.
    # Modify as needed for your application.
    # Note that the resources in this example are much too small for production;
    # we don't recommend allocating less than 8G memory for a Ray pod in production.
    # Ray pods should be sized to take up entire K8s nodes when possible.
    # Always set CPU and memory limits for Ray pods.
    # It is usually best to set requests equal to limits.
    # See https://docs.ray.io/en/latest/cluster/kubernetes/user-guides/config.html#resources
    # for further guidance.
    resources:
      limits:
        cpu: 1
        memory: "1G"
      requests:
        cpu: 1
        memory: "1G"
    annotations: {}
    nodeSelector: {}
    tolerations: []
    affinity: {}
    # Pod security context.
    podSecurityContext: {}
    # Ray container security context.
    securityContext: {}
    # Optional: The following volumes/volumeMounts configurations are optional but recommended because
    # Ray writes logs to /tmp/ray/session_latests/logs instead of stdout/stderr.
    volumes:
      - name: log-volume
        hostPath:
          path: /opt/data-mate/data/log
          type: DirectoryOrCreate
      - name: dataset-volume
        hostPath:
          path: /opt/data-mate/data/dataset
          type: DirectoryOrCreate
      - name: flow-volume
        hostPath:
          path: /opt/data-mate/data/flow
          type: DirectoryOrCreate
    volumeMounts:
      - mountPath: /tmp/ray
        name: log-volume
        subPath: ray
      - mountPath: /dataset
        name: dataset-volume
      - mountPath: /flow
        name: flow-volume
    sidecarContainers: []
    # See docs/guidance/pod-command.md for more details about how to specify
    # container command for worker Pod.
    command: []
    args: []

    # Topology Spread Constraints for worker pods
    # See: https://kubernetes.io/docs/concepts/scheduling-eviction/topology-spread-constraints/
    topologySpreadConstraints: []

    # Custom pod DNS configuration
    # See https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/#pod-dns-config
    # dnsConfig:
    #   nameservers:
    #     - 8.8.8.8
    #   searches:
    #     - example.local
    #   options:
    #     - name: ndots
    #       value: "2"
    #     - name: edns0

# Configuration for Head's Kubernetes Service
service:
  # This is optional, and the default is ClusterIP.
  type: NodePort