ray/doc/examples/lm/lm-cluster.yaml

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

# The minimum number of workers nodes to launch in addition to the head
# node. This number should be >= 0.
min_workers: 1

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


# 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

# 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: m5.xlarge
    ImageId: ami-0b294f219d14e6a82 # Deep Learning AMI (Ubuntu) Version 21.0
    SecurityGroupIds:
        - "{{SecurityGroupId}}"
    # 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: p3.2xlarge
    ImageId: ami-0b294f219d14e6a82 # Deep Learning AMI (Ubuntu) Version 21.0
    SecurityGroupIds:
        - "{{SecurityGroupId}}"
    # 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.

# 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="$HOME/anaconda3/envs/pytorch_p36/bin:$PATH"' >> ~/.bashrc;
        source ~/.bashrc;
        pip install -U ray;
        pip install -U fairseq==0.8.0;
    - sudo kill -9 `sudo lsof /var/lib/dpkg/lock-frontend | awk '{print $2}' | tail -n 1`;
        sudo pkill -9 apt-get;
        sudo pkill -9 dpkg;
        sudo dpkg --configure -a;
        sudo apt-get -y install binutils;
        cd $HOME;
        git clone https://github.com/aws/efs-utils;
        cd $HOME/efs-utils;
        ./build-deb.sh;
        sudo apt-get -y install ./build/amazon-efs-utils*deb;
        cd $HOME;
        mkdir efs;
        sudo mount -t efs {{FileSystemId}}:/ efs;
        sudo chmod 777 efs;

# 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 --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