ray/release/data_processing_tests/dask_on_ray.yaml

cluster_name: Dask-on-ray-release-cluster

# The minimum number of workers nodes to launch in addition to the head
# node. This number should be >= 0.
min_workers: 250

# The maximum number of workers nodes to launch in addition to the head
# node. This takes precedence over min_workers.
max_workers: 250

# 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: "" # You can change this to latest-cpu if you don't need GPU support and want a faster startup
    # image: rayproject/ray:latest-gpu   # use this one if you don't need ML dependencies, it's faster to pull
    container_name: ""
    # 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"
    # Allow Ray to automatically detect GPUs

    # worker_image: "rayproject/ray-ml:latest-cpu"
    # worker_run_options: []

# 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
    # 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

available_node_types:
    head_node_t:
        node_config:
            InstanceType: r5n.16xlarge
        # For AWS instances, autoscaler will automatically add the available
        # CPUs/GPUs/accelerator_type ({"CPU": 4} for m4.xlarge) in "resources".
        # resources: {"CPU": 4}
        resources: {"CPU": 0}
    worker_node_t:
        node_config:
            InstanceType: r5.4xlarge
        # Autoscaler will auto fill the CPU resources below.
        resources: {"CPU": 96}
        min_workers: 250
        max_workers: 250

head_node_type: head_node_t

# 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: i3.8xlarge
    ImageId: ami-0a2363a9cff180a64 # Deep Learning AMI (Ubuntu) Version 30

    # You can provision additional disk space with a conf as follows
    BlockDeviceMappings:
        - DeviceName: /dev/sda1
          Ebs:
              VolumeSize: 1000

    # 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: r5.4xlarge
    ImageId: ami-0a2363a9cff180a64 # Deep Learning AMI (Ubuntu) Version 30

    # You can provision additional disk space with a conf as follows
    BlockDeviceMappings:
        - DeviceName: /dev/sda1
          Ebs:
              VolumeSize: 1000

# Patterns for files to exclude when running rsync up or rsync down
rsync_exclude:
    - "**/.git"
    - "**/.git/**"

# Pattern files to use for filtering out files when running rsync up or rsync down. The file is searched for
# in the source directory and recursively through all subdirectories. For example, if .gitignore is provided
# as a value, the behavior will match git's behavior for finding and using .gitignore files.
rsync_filter:
    - ".gitignore"

# 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:
    # - sudo apt install -y iotop
    # - sudo apt install -y gdb
    # - sudo apt install -y linux-tools-common
    - echo 'export PATH="$HOME/anaconda3/envs/tensorflow_p36/bin:$PATH"' >> ~/.bashrc
    - pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-2.0.0.dev0-cp36-cp36m-manylinux2014_x86_64.whl"
    - sudo bash -c 'rm -rf /etc/security/limits.d; echo "* soft nofile 165536" >> /etc/security/limits.conf; echo "* hard nofile 165536" >> /etc/security/limits.conf;'
    - pip install tqdm
    - pip install -U dask
    - pip install fastparquet --ignore-installed
    - pip install -U numpy==1.19.5 scipy xarray dataclasses zarr

# Command to start ray on the head node. You don't need to change this.
head_start_ray_commands:
    - ray stop
    - ray start --num-cpus=0 --head --port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml --system-config='{"asio_event_loop_stats_collection_enabled":true,"scheduler_loadbalance_spillback":true}'

# Command to start ray on worker nodes. You don't need to change this.
worker_start_ray_commands:
    - ray stop
    - ray start --address=$RAY_HEAD_IP:6379 --num-cpus=96 --object-manager-port=8076