ray/ci/stress_tests/application_cluster_template.yaml

####################################################################
# All nodes in this cluster will auto-terminate in 1 hour
####################################################################

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

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

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

# 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., tensorflow/tensorflow:1.5.0-py3
    container_name: "" # e.g. ray_docker

# 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: 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-2b

# 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

# Provider-specific config for the head node, 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
head_node:
    InstanceType: <<<HEAD_TYPE>>>
    ImageId: ami-0027dfad6168539c7  # Amazon Deep Learning AMI (Ubuntu), Version 21.2

    # You can provision additional disk space with a conf as follows
    BlockDeviceMappings:
        - DeviceName: /dev/sda1
          Ebs:
              VolumeSize: 100

    # Additional options in the boto docs.

# Provider-specific config for worker nodes, 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
worker_nodes:
    InstanceType: <<<WORKER_TYPE>>>
    ImageId: ami-0027dfad6168539c7  # Amazon Deep Learning AMI (Ubuntu), Version 21.2

    # 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.

# 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.
setup_commands:
    - echo 'export PATH="$HOME/anaconda3/envs/tensorflow_<<<PYTHON_VERSION>>>/bin:$PATH"' >> ~/.bashrc
    - ray || wget https://s3-us-west-2.amazonaws.com/ray-wheels/releases/<<<RAY_VERSION>>>/<<<RAY_COMMIT>>>/ray-<<<RAY_VERSION>>>-<<<WHEEL_STR>>>-manylinux1_x86_64.whl
    - rllib || pip install -U ray-<<<RAY_VERSION>>>-<<<WHEEL_STR>>>-manylinux1_x86_64.whl[rllib]
    - pip install tensorflow-gpu==1.12.0
    - echo "sudo halt" | at now + 60 minutes
    # 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 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 --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