cluster_resource_demand.yaml

cluster_name: default

min_workers: 0
max_workers: 5
initial_workers: 0
autoscaling_mode: default
target_utilization_fraction: 1.0
idle_timeout_minutes: 99999

provider:
  type: kubernetes
  use_internal_ips: true
  namespace: ray
  autoscaler_service_account:
    apiVersion: v1
    kind: ServiceAccount
    metadata:
      name: autoscaler
  autoscaler_role:
    kind: Role
    apiVersion: rbac.authorization.k8s.io/v1
    metadata:
      name: autoscaler
    rules:
      - apiGroups:
          - ''
        resources:
          - pods
          - pods/status
          - pods/exec
        verbs:
          - get
          - watch
          - list
          - create
          - delete
          - patch
  autoscaler_role_binding:
    apiVersion: rbac.authorization.k8s.io/v1
    kind: RoleBinding
    metadata:
      name: autoscaler
    subjects:
      - kind: ServiceAccount
        name: autoscaler
    roleRef:
      kind: Role
      name: autoscaler
      apiGroup: rbac.authorization.k8s.io
  services:
    - apiVersion: v1
      kind: Service
      metadata:
        name: ray-head
      spec:
        selector:
          component: ray-head
        ports:
          - protocol: TCP
            port: 8000
            targetPort: 8000
    - apiVersion: v1
      kind: Service
      metadata:
        name: ray-workers
      spec:
        selector:
          component: ray-worker
        ports:
          - protocol: TCP
            port: 8000
            targetPort: 8000

available_node_types:
  k8s_head_node:
    resources: {"CPU": 1}
    max_workers: 100
    node_config:
      apiVersion: v1
      kind: Pod
      metadata:
        generateName: ray-head-
        labels:
          component: ray-head
      spec:
        serviceAccountName: autoscaler
        restartPolicy: Never
        volumes:
          - name: dshm
            emptyDir:
              medium: Memory
        containers:
          - name: ray-node
            image: 'rayproject/ray-ml:1.0.1'
            command:
              - /bin/bash
              - '-c'
              - '--'
            args:
              - 'trap : TERM INT; sleep infinity & wait;'
            ports:
              - containerPort: 6379
              - containerPort: 6380
              - containerPort: 6381
              - containerPort: 12345
              - containerPort: 12346
            volumeMounts:
              - mountPath: /dev/shm
                name: dshm
            resources:
              requests:
                cpu: 1000m
                memory: 512Mi
              limits:
                memory: 2Gi
            env:
              - name: MY_CPU_REQUEST
                valueFrom:
                  resourceFieldRef:
                    resource: requests.cpu
  k8s_worker_nodes:
    resources: {"CPU": 1}
    max_workers: 100
    node_config:
      apiVersion: v1
      kind: Pod
      metadata:
        generateName: ray-worker-
        labels:
          component: ray-worker
      spec:
        serviceAccountName: default
        restartPolicy: Never
        volumes:
          - name: dshm
            emptyDir:
              medium: Memory
        containers:
          - name: ray-node
            image: 'rayproject/ray-ml:1.0.1'
            command:
              - /bin/bash
              - '-c'
              - '--'
            args:
              - 'trap : TERM INT; sleep infinity & wait;'
            ports:
              - containerPort: 12345
              - containerPort: 12346
            volumeMounts:
              - mountPath: /dev/shm
                name: dshm
            resources:
              requests:
                cpu: 1000m
                memory: 512Mi
              limits:
                memory: 2Gi
            env:
              - name: MY_CPU_REQUEST
                valueFrom:
                  resourceFieldRef:
                    resource: requests.cpu

head_node_type: k8s_head_node
worker_default_node_type: k8s_worker_nodes

file_mounts: {}
cluster_synced_files: []
file_mounts_sync_continuously: false
initialization_commands: []
setup_commands: []

head_setup_commands: []
worker_setup_commands:
  - echo "done sleeping"
head_start_ray_commands:
  - ray stop
  - >-
    ulimit -n 65536; ray start --head --num-cpus=$MY_CPU_REQUEST --port=6379
    --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml
    --dashboard-host 0.0.0.0
worker_start_ray_commands:
  - ray stop
  - >-
    ulimit -n 65536; ray start --num-cpus=$MY_CPU_REQUEST
    --address=$RAY_HEAD_IP:6379 --object-manager-port=8076

request_resource.py

import ray
import os

ray.init(address="auto")

@ray.remote(num_cpus=1)
def spin():
    import time
    while True:
        print("running... with host name ", os.environ["HOSTNAME"])
        time.sleep(5)

ray.get(spin.remote())