ray_cluster.yaml

# An unique identifier for the head node and workers of this cluster.
cluster_name: gpu-docker

min_workers: 1
max_workers: 4

# 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.
upscaling_speed: 1.0

# This executes all commands on all nodes in the docker container,
# and opens all the necessary ports to support the Ray cluster.
# Empty string means disabled.
docker:
  image: "rayproject/ray-ml:latest-gpu"
  # image: rayproject/ray:latest-gpu   # use this one if you don't need ML dependencies, it's faster to pull
  container_name: "ray_nvidia_docker" # e.g. ray_docker


# If a node is idle for this many minutes, it will be removed.
idle_timeout_minutes: 5

# Cloud-provider specific configuration.
provider:
  type: aws
  region: us-west-2
  # Availability zone(s), comma-separated, that nodes may be launched in.
  # Nodes are currently spread between zones by a round-robin approach,
  # however this implementation detail should not be relied upon.
  availability_zone: us-west-2a,us-west-2b
  security_group:
    GroupName: dashboard_group
    IpPermissions:
      - FromPort: 20002
        ToPort: 20002
        IpProtocol: TCP
        IpRanges:
          - CidrIp: 0.0.0.0/0


# How Ray will authenticate with newly launched nodes.
auth:
  ssh_user: ubuntu
# By default Ray creates a new private keypair, but you can also use your own.
# If you do so, make sure to also set "KeyName" in the head and worker node
# configurations below.
#    ssh_private_key: /path/to/your/key.pem

# Tell the autoscaler the allowed node types and the resources they provide.
# The key is the name of the node type, which is just for debugging purposes.
# The node config specifies the launch config and physical instance type.
available_node_types:
  # GPU head node.
  ray.head.gpu:
    # worker_image: rayproject/ray:latest-gpu   # use this one if you don't need ML dependencies, it's faster to pull
    # The node type's CPU and GPU resources are auto-detected based on AWS instance type.
    # If desired, you can override the autodetected CPU and GPU resources advertised to the autoscaler.
    # You can also set custom resources.
    # For example, to mark a node type as having 1 CPU, 1 GPU, and 5 units of a resource called "custom", set
    # resources: {"CPU": 1, "GPU": 1, "custom": 5}
    resources: {}
    # Provider-specific config for this node type, e.g. instance type. By default
    # Ray will auto-configure unspecified fields such as SubnetId and KeyName.
    # For more documentation on available fields, see:
    # http://boto3.readthedocs.io/en/latest/reference/services/ec2.html#EC2.ServiceResource.create_instances
    node_config:
      InstanceType: p2.xlarge
      ImageId: ami-0a2363a9cff180a64 # Deep Learning AMI (Ubuntu) Version 30
      # You can provision additional disk space with a conf as follows
      BlockDeviceMappings:
        - DeviceName: /dev/sda1
          Ebs:
            VolumeSize: 100
      # Additional options in the boto docs.
  # CPU workers.
  ray.worker.default:
    # Override global docker setting.
    # This node type will run a CPU image,
    # rather than the GPU image specified in the global docker settings.
    docker:
      worker_image: "rayproject/ray-ml:latest-cpu"
    # The minimum number of nodes of this type to launch.
    # This number should be >= 0.
    min_workers: 1
    # The maximum number of workers nodes of this type to launch.
    # This takes precedence over min_workers.
    max_workers: 2
    # The node type's CPU and GPU resources are auto-detected based on AWS instance type.
    # If desired, you can override the autodetected CPU and GPU resources advertised to the autoscaler.
    # You can also set custom resources.
    # For example, to mark a node type as having 1 CPU, 1 GPU, and 5 units of a resource called "custom", set
    # resources: {"CPU": 1, "GPU": 1, "custom": 5}
    resources: {}
    # Provider-specific config for this node type, e.g. instance type. By default
    # Ray will auto-configure unspecified fields such as SubnetId and KeyName.
    # For more documentation on available fields, see:
    # http://boto3.readthedocs.io/en/latest/reference/services/ec2.html#EC2.ServiceResource.create_instances
    node_config:
      InstanceType: m5.large
      ImageId: ami-0a2363a9cff180a64 # Deep Learning AMI (Ubuntu) Version 30
      # Run workers on spot by default. Comment this out to use on-demand.
      InstanceMarketOptions:
        MarketType: spot
        # Additional options can be found in the boto docs, e.g.
        #   SpotOptions:
        #       MaxPrice: MAX_HOURLY_PRICE
      # Additional options in the boto docs.

# Specify the node type of the head node (as configured above).
head_node_type: ray.head.gpu

# Files or directories to copy to the head and worker nodes. The format is a
# dictionary from REMOTE_PATH: LOCAL_PATH, e.g.
file_mounts: {
  #    "/path1/on/remote/machine": "/path1/on/local/machine",
  #    "/path2/on/remote/machine": "/path2/on/local/machine",
}

# List of shell commands to run to set up nodes.
# NOTE: rayproject/ray:latest has ray latest bundled
setup_commands: []
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-2.0.0.dev0-cp36-cp36m-manylinux2014_x86_64.whl
# - pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-2.0.0.dev0-cp37-cp37m-manylinux2014_x86_64.whl"

# Custom commands that will be run on the head node after common setup.
head_setup_commands:
  - pip install boto3==1.4.8  # 1.4.8 adds InstanceMarketOptions

# Custom commands that will be run on worker nodes after common setup.
worker_setup_commands: []

# Command to start ray on the head node. You don't need to change this.
head_start_ray_commands:
  - ray stop
  - ulimit -n 65536; ray start --dashboard-port 20002 --dashboard-host=0.0.0.0 --include-dashboard True --head --port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml

# Command to start ray on worker nodes. You don't need to change this.
worker_start_ray_commands:
  - ray stop
  - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076