ray/python/ray/autoscaler/gcp/example-gpu-docker.yaml

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

# The minimum number of workers nodes to launch in addition to the head
# node. This number should be >= 0.
min_workers: 0

# The maximum number of workers nodes to launch in addition to the head
# node. This takes precedence over min_workers.
max_workers: 2

# The initial number of worker nodes to launch in addition to the head
# node. When the cluster is first brought up (or when it is refreshed with a
# subsequent `ray up`) this number of nodes will be started.
initial_workers: 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: "tensorflow/tensorflow:1.12.0-gpu-py3"
    container_name: "ray-nvidia-docker-test" # e.g. ray_docker
    run_options:
      - --runtime=nvidia


# The autoscaler will scale up the cluster to this target fraction of resource
# usage. For example, if a cluster of 10 nodes is 100% busy and
# target_utilization is 0.8, it would resize the cluster to 13. This fraction
# can be decreased to increase the aggressiveness of upscaling.
# This value must be less than 1.0 for scaling to happen.
target_utilization_fraction: 0.8

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

# Cloud-provider specific configuration.
provider:
    type: gcp
    region: us-west1
    availability_zone: us-west1-b
    project_id: <project_id> # Globally unique project id

# 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. This requires that you have added the key into the
# project wide meta-data.
#    ssh_private_key: /path/to/your/key.pem

# Provider-specific config for the head node, e.g. instance type. By default
# Ray will auto-configure unspecified fields such as subnets and ssh-keys.
# For more documentation on available fields, see:
# https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
head_node:
    machineType: custom-6-16384
    disks:
      - boot: true
        autoDelete: true
        type: PERSISTENT
        initializeParams:
          diskSizeGb: 50
          # See https://cloud.google.com/compute/docs/images for more images
          sourceImage: projects/deeplearning-platform-release/global/images/family/tf-latest-gpu
    guestAccelerators:
      - acceleratorType: projects/<project_id>/zones/us-west1-b/acceleratorTypes/nvidia-tesla-k80
        acceleratorCount: 1
    metadata:
      items:
        - key: install-nvidia-driver
          value: "True"
    scheduling:
      - onHostMaintenance: TERMINATE

    # Additional options can be found in in the compute docs at
    # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert

worker_nodes:
    machineType: n1-standard-2
    disks:
      - boot: true
        autoDelete: true
        type: PERSISTENT
        initializeParams:
          diskSizeGb: 50
          # See https://cloud.google.com/compute/docs/images for more images
          sourceImage: projects/deeplearning-platform-release/global/images/family/tf-latest-gpu
    guestAccelerators:
      - acceleratorType: projects/<project_id>/zones/us-west1-b/acceleratorTypes/nvidia-tesla-k80
        acceleratorCount: 1
    metadata:
      items:
        - key: install-nvidia-driver
          value: "True"
    # Run workers on preemtible instance by default.
    # Comment this out to use on-demand.
    scheduling:
      - preemptible: true
      - onHostMaintenance: TERMINATE

    # Additional options can be found in in the compute docs at
    # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert

# 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",
}

initialization_commands:
    # Wait until nvidia drivers are installed
    - >-
      timeout 300 bash -c "
          command -v nvidia-smi && nvidia-smi
          until [ \$? -eq 0 ]; do
              command -v nvidia-smi && nvidia-smi
          done"

# List of shell commands to run to set up nodes.
setup_commands:
    # Note: if you're developing Ray, you probably want to create an AMI that
    # has your Ray repo pre-cloned. Then, you can replace the pip installs
    # below with a git checkout <your_sha> (and possibly a recompile).
    # - echo 'export PATH="$HOME/anaconda3/envs/tensorflow_p36/bin:$PATH"' >> ~/.bashrc

    # Install ray
    # - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.7.0.dev1-cp27-cp27mu-manylinux1_x86_64.whl
    - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.7.0.dev1-cp35-cp35m-manylinux1_x86_64.whl
    # - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.7.0.dev1-cp36-cp36m-manylinux1_x86_64.whl

# Custom commands that will be run on the head node after common setup.
head_setup_commands:
  - pip install google-api-python-client==1.7.8

# 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
      --head
      --redis-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
      --redis-address=$RAY_HEAD_IP:6379
      --object-manager-port=8076