# A cluster setup for ML / RLlib workloads. Note that this uses pytorch by default.
# If you want to use tensorflow, change pytorch_p36 to tensorflow_p36 below.
#
# Important: Make sure to run "source activate pytorch_p36" in your sessions to
# activate the right conda environment. Otherwise you won't be able to import ray.
#
cluster_name: ml

# 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: 0

# 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: "" # e.g., rayproject/ray-ml:latest
    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-ml:latest-gpu"

    # worker_image: "rayproject/ray-ml:latest"

# 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 will be launched in the first listed availability zone and will
    # be tried in the subsequent availability zones if launching fails.
    availability_zone: us-west-2a,us-west-2b
    # Whether to allow node reuse. If set to False, nodes will be terminated
    # instead of stopped.
    cache_stopped_nodes: True # If not present, the default is True.

# 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:
    ray.head.default:
      node_config:
        InstanceType: m4.16xlarge
        ImageId: latest_dlami

        # You can provision additional disk space with a conf as follows
        BlockDeviceMappings:
            - DeviceName: /dev/sda1
              Ebs:
                  VolumeSize: 140

    ray.worker.default:
      node_config:
        InstanceType: m4.16xlarge
        ImageId: latest_dlami

        # Comment this in to use spot nodes.
        # 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",
}

# 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: []

# 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).
    - source activate pytorch_p36 && pip install -U ray
    - source activate pytorch_p36 && pip install -U ray[rllib] ray[tune] ray
    # 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:
    - source activate pytorch_p36 && ray stop
    - ulimit -n 65536; source activate pytorch_p36 && 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:
    - source activate pytorch_p36 && ray stop
    - ulimit -n 65536; source activate pytorch_p36 && ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076