ray/python/ray/autoscaler/azure/example-full.yaml

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

# 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

# Whether or not to autoscale aggressively. If this is enabled, if at any point
#   we would start more workers, we start at least enough to bring us to
#   initial_workers.
autoscaling_mode: default

# 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: "" # e.g., rayproject/ray:0.8.7
    container_name: "" # e.g. ray_docker
    # If true, pulls latest version of image. Otherwise, `docker run` will only pull the image
    # if no cached version is present.
    pull_before_run: True
    run_options: []  # Extra options to pass into "docker run"

    # Example of running a GPU head with CPU workers
    # head_image: "rayproject/ray:0.8.7-gpu"
    # head_run_options:
    #     - --runtime=nvidia

    # worker_image: "rayproject/ray:0.8.7"
    # worker_run_options: []

# 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: azure
    # https://azure.microsoft.com/en-us/global-infrastructure/locations
    location: westus2
    resource_group: ray-cluster
    # set subscription id otherwise the default from az cli will be used
    # subscription_id: 00000000-0000-0000-0000-000000000000

# How Ray will authenticate with newly launched nodes.
auth:
    ssh_user: ubuntu
    # you must specify paths to matching private and public key pair files
    # use `ssh-keygen -t rsa -b 4096` to generate a new ssh key pair
    ssh_private_key: ~/.ssh/id_rsa
    ssh_public_key: ~/.ssh/id_rsa.pub

# More specific customization to node configurations can be made using the ARM template azure-vm-template.json file
# See documentation here: https://docs.microsoft.com/en-us/azure/templates/microsoft.compute/2019-03-01/virtualmachines
# Changes to the local file will be used during deployment of the head node, however worker nodes deployment occurs
# on the head node, so changes to the template must be included in the wheel file used in setup_commands section below

# Provider-specific config for the head node, e.g. instance type.
head_node:
    azure_arm_parameters:
        vmSize: Standard_D2s_v3
        # List images https://docs.microsoft.com/en-us/azure/virtual-machines/linux/cli-ps-findimage
        imagePublisher: microsoft-dsvm
        imageOffer: ubuntu-1804
        imageSku: 1804-gen2
        imageVersion: 20.02.01

# Provider-specific config for worker nodes, e.g. instance type.
worker_nodes:
    azure_arm_parameters:
        vmSize: Standard_D2s_v3
        # List images https://docs.microsoft.com/en-us/azure/virtual-machines/linux/cli-ps-findimage
        imagePublisher: microsoft-dsvm
        imageOffer: ubuntu-1804
        imageSku: 1804-gen2
        imageVersion: 20.02.01
        # optionally set priority to use Spot instances
        priority: Spot
        # set a maximum price for spot instances if desired
        # billingProfile:
        #     maxPrice: -1

# 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",
}

# Files or directories to copy from the head node to the worker nodes. The format is a
# list of paths. The same path on the head node will be copied to the worker node.
# This behavior is a subset of the file_mounts behavior. In the vast majority of cases
# you should just use file_mounts. Only use this if you know what you're doing!
cluster_synced_files: []

# Whether changes to directories in file_mounts or cluster_synced_files in the head node
# should sync to the worker node continuously
file_mounts_sync_continuously: False

# List of commands that will be run before `setup_commands`. If docker is
# enabled, these commands will run outside the container and before docker
# is setup.
initialization_commands:
    # get rid of annoying Ubuntu message
    - touch ~/.sudo_as_admin_successful

# 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 'conda activate py37_pytorch' >> ~/.bashrc
    - echo 'conda activate py37_tensorflow' >> ~/.bashrc
    - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp37-cp37m-manylinux1_x86_64.whl
    # Consider uncommenting these if you also want to run apt-get commands during setup
    # - sudo pkill -9 apt-get || true
    # - sudo pkill -9 dpkg || true
    # - sudo dpkg --configure -a

# Custom commands that will be run on the head node after common setup.
head_setup_commands:
    - pip install azure-cli-core==2.4.0 azure-mgmt-compute==12.0.0 azure-mgmt-msi==1.0.0 azure-mgmt-network==10.1.0

# 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 --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