ray/deploy/components/example_cluster.yaml

apiVersion: cluster.ray.io/v1
kind: RayCluster
metadata:
  name: example-cluster
spec:
  # The maximum number of workers nodes to launch in addition to the head node.
  maxWorkers: 3
  # The autoscaler will scale up the cluster faster with higher upscaling speed.
  # E.g., if the task requires adding more nodes then autoscaler will gradually
  # scale up the cluster in chunks of upscaling_speed*currently_running_nodes.
  # This number should be > 0.
  upscalingSpeed: 1.0
  # If a node is idle for this many minutes, it will be removed.
  idleTimeoutMinutes: 5
  # Specify the pod type for the ray head node (as configured below).
  headPodType: head-node
  # Optionally, configure ports for the Ray head service.
  # The ports specified below are the defaults.
  headServicePorts:
    - name: client
      port: 10001
      targetPort: 10001
    - name: dashboard
      port: 8265
      targetPort: 8265
    - name: ray-serve
      port: 8000
      targetPort: 8000
  # Specify the allowed pod types for this ray cluster and the resources they provide.
  podTypes:
  - name: head-node
    podConfig:
      apiVersion: v1
      kind: Pod
      metadata:
        # The operator automatically prepends the cluster name to this field.
        generateName: ray-head-
      spec:
        restartPolicy: Never

        # This volume allocates shared memory for Ray to use for its plasma
        # object store. If you do not provide this, Ray will fall back to
        # /tmp which cause slowdowns if is not a shared memory volume.
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
        containers:
        - name: ray-node
          imagePullPolicy: Always
          image: rayproject/ray:latest
          # Do not change this command - it keeps the pod alive until it is
          # explicitly killed.
          command: ["/bin/bash", "-c", "--"]
          args: ["trap : TERM INT; touch /tmp/raylogs; tail -f /tmp/raylogs; sleep infinity & wait;"]
          ports:
          - containerPort: 6379  # Redis port for Ray <= 1.10.0. GCS server port for Ray >= 1.11.0.
          - containerPort: 10001  # Used by Ray Client
          - containerPort: 8265  # Used by Ray Dashboard
          - containerPort: 8000 # Used by Ray Serve

          # This volume allocates shared memory for Ray to use for its plasma
          # object store. If you do not provide this, Ray will fall back to
          # /tmp which cause slowdowns if is not a shared memory volume.
          volumeMounts:
          - mountPath: /dev/shm
            name: dshm
          resources:
            requests:
              cpu: 1000m
              memory: 512Mi
              ephemeral-storage: 1Gi
            limits:
              # The maximum memory that this pod is allowed to use. The
              # limit will be detected by ray and split to use 10% for
              # redis, 30% for the shared memory object store, and the
              # rest for application memory. If this limit is not set and
              # the object store size is not set manually, ray will
              # allocate a very large object store in each pod that may
              # cause problems for other pods.
              memory: 512Mi
  - name: worker-node
    # Minimum number of Ray workers of this Pod type.
    minWorkers: 2
    # Maximum number of Ray workers of this Pod type. Takes precedence over minWorkers.
    maxWorkers: 3
    # User-specified custom resources for use by Ray.
    # (Ray detects CPU and GPU from pod spec resource requests and limits, so no need to fill those here.)
    rayResources: {"example-resource-a": 1, "example-resource-b": 1}
    podConfig:
      apiVersion: v1
      kind: Pod
      metadata:
        # The operator automatically prepends the cluster name to this field.
        generateName: ray-worker-
      spec:
        restartPolicy: Never
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
        containers:
        - name: ray-node
          imagePullPolicy: Always
          image: rayproject/ray:latest
          command: ["/bin/bash", "-c", "--"]
          args: ["trap : TERM INT; touch /tmp/raylogs; tail -f /tmp/raylogs; sleep infinity & wait;"]
          # This volume allocates shared memory for Ray to use for its plasma
          # object store. If you do not provide this, Ray will fall back to
          # /tmp which cause slowdowns if is not a shared memory volume.
          volumeMounts:
          - mountPath: /dev/shm
            name: dshm
          resources:
            requests:
              cpu: 1000m
              memory: 512Mi
              ephemeral-storage: 1Gi
            limits:
              # The maximum memory that this pod is allowed to use. The
              # limit will be detected by ray and split to use 10% for
              # redis, 30% for the shared memory object store, and the
              # rest for application memory. If this limit is not set and
              # the object store size is not set manually, ray will
              # allocate a very large object store in each pod that may
              # cause problems for other pods.
              memory: 512Mi
  # Commands to start Ray on the head node. You don't need to change this.
  # Note dashboard-host is set to 0.0.0.0 so that Kubernetes can port forward.
  headStartRayCommands:
    - ray stop
    - ulimit -n 65536; ray start --head --port=6379 --no-monitor --dashboard-host 0.0.0.0 &> /tmp/raylogs
  # Commands to start Ray on worker nodes. You don't need to change this.
  workerStartRayCommands:
    - ray stop
    - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 &> /tmp/raylogs