KamilMroczek/ray.yaml

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

# The maximum number of workers nodes to launch in addition to the head
# node.
max_workers: 16

# 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: XXXXXX.dkr.ecr.us-east-1.amazonaws.com/image:0.0.1
    container_name: "image-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"
        - --ulimit nofile=65536:65536

    # 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-east-1
    # 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-east-1a,us-east-1b,us-east-1c,us-east-1d,us-east-1e,us-east-1f
    # Whether to allow node reuse. If set to False, nodes will be terminated
    # instead of stopped.
    cache_stopped_nodes: False # If not present, the default is True.
    security_group:
      GroupName: group-name

# 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: ~/.ssh/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:
        min_workers: 1
        max_workers: 1
        # The node type's CPU and GPU resources are auto-detected based on AWS instance type.
        # If desired, you can override the autodetected CPU and GPU resources advertised to the autoscaler.
        # You can also set custom resources.
        # For example, to mark a node type as having 1 CPU, 1 GPU, and 5 units of a resource called "custom", set
        # resources: {"CPU": 1, "GPU": 1, "custom": 5}
        # resources: {}
        # Provider-specific config for this node type, 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
        node_config:
            InstanceType: m5.large
            # Default AMI for us-east-1.
            # Check https://github.com/ray-project/ray/blob/master/python/ray/autoscaler/_private/aws/config.py
            # for default images for other zones.
            ImageId: ami-0dd6adfad4ad37eec
            # You can provision additional disk space with a conf as follows
            KeyName: key
            EbsOptimized: True
            IamInstanceProfile:
                Name: IamInstance
            BlockDeviceMappings:
                - DeviceName: /dev/sda1
                  Ebs:
                      VolumeType: gp3
                      VolumeSize: 140
            TagSpecifications:
                - ResourceType: instance
                  Tags:
                      - Key: Environment
                        Value: 'development'
                      - Key: Product
                        Value: 'project'
                - ResourceType: volume
                  Tags:
                      - Key: Environment
                        Value: 'development'
                      - Key: Product
                        Value: 'project'
    ray.worker.default:
        # The minimum number of worker nodes of this type to launch.
        # This number should be >= 0.
        min_workers: 5
        # The maximum number of worker nodes of this type to launch.
        # This takes precedence over min_workers.
        #max_workers: 2
        # The node type's CPU and GPU resources are auto-detected based on AWS instance type.
        # If desired, you can override the autodetected CPU and GPU resources advertised to the autoscaler.
        # You can also set custom resources.
        # For example, to mark a node type as having 1 CPU, 1 GPU, and 5 units of a resource called "custom", set
        # resources: {"CPU": 1, "GPU": 1, "custom": 5}
        # resources: {}
        # Provider-specific config for this node type, 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
        node_config:
            InstanceType: m5.large
            # Default AMI for us-east-1.
            # Check https://github.com/ray-project/ray/blob/master/python/ray/autoscaler/_private/aws/config.py
            # for default images for other zones.
            # https://us-east-1.console.aws.amazon.com/ec2/home?region=us-east-1#Images:visibility=public-images;owner=898082745236;architecture=arm64;v=3;$case=tags:false%5C,client:false;$regex=tags:false%5C,client:false
            ImageId: ami-0dd6adfad4ad37eec
            # Run workers on spot by default. Comment this out to use on-demand.
            # NOTE: If relying on spot instances, it is best to specify multiple different instance
            # types to avoid interruption when one instance type is experiencing heightened demand.
            # Demand information can be found at https://aws.amazon.com/ec2/spot/instance-advisor/
            KeyName: key
            EbsOptimized: True
            IamInstanceProfile:
              Name: IamInstanceProfile
            InstanceMarketOptions:
                MarketType: spot
                # Additional options can be found in the boto docs, e.g.
                #   SpotOptions:
                #       MaxPrice: MAX_HOURLY_PRICE
            TagSpecifications:
                - ResourceType: instance
                  Tags:
                      - Key: Environment
                        Value: 'development'
                      - Key: Product
                        Value: 'project'
                - ResourceType: volume
                  Tags:
                      - Key: Environment
                        Value: 'development'
                      - Key: Product
                        Value: 'project'

# Specify the node type of the head node (as configured above).
head_node_type: ray.head.default

# 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

# 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: [
  'aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin XXXXXXX.dkr.ecr.us-east-1.amazonaws.com'
]

# List of shell commands to run to set up nodes.
setup_commands: []
    # Note: if you're developing Ray, you probably want to create a Docker image 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).
    # To run the nightly version of ray (as opposed to the latest), either use a rayproject docker image
    # that has the "nightly" (e.g. "rayproject/ray-ml:nightly-gpu") or uncomment the following line:
    # - pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp37-cp37m-manylinux2014_x86_64.whl"

# Custom commands that will be run on the head node after common setup.
head_setup_commands: []

# 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
    - 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
    - ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076
	# An unique identifier for the head node and workers of this cluster.
	cluster_name: cluster_name

	# The maximum number of workers nodes to launch in addition to the head
	# node.
	max_workers: 16

	# 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: XXXXXX.dkr.ecr.us-east-1.amazonaws.com/image:0.0.1
	container_name: "image-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"
	- --ulimit nofile=65536:65536

	# 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-east-1
	# 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-east-1a,us-east-1b,us-east-1c,us-east-1d,us-east-1e,us-east-1f
	# Whether to allow node reuse. If set to False, nodes will be terminated
	# instead of stopped.
	cache_stopped_nodes: False # If not present, the default is True.
	security_group:
	GroupName: group-name

	# 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: ~/.ssh/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:
	min_workers: 1
	max_workers: 1
	# The node type's CPU and GPU resources are auto-detected based on AWS instance type.
	# If desired, you can override the autodetected CPU and GPU resources advertised to the autoscaler.
	# You can also set custom resources.
	# For example, to mark a node type as having 1 CPU, 1 GPU, and 5 units of a resource called "custom", set
	# resources: {"CPU": 1, "GPU": 1, "custom": 5}
	# resources: {}
	# Provider-specific config for this node type, 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
	node_config:
	InstanceType: m5.large
	# Default AMI for us-east-1.
	# Check https://github.com/ray-project/ray/blob/master/python/ray/autoscaler/_private/aws/config.py
	# for default images for other zones.
	ImageId: ami-0dd6adfad4ad37eec
	# You can provision additional disk space with a conf as follows
	KeyName: key
	EbsOptimized: True
	IamInstanceProfile:
	Name: IamInstance
	BlockDeviceMappings:
	- DeviceName: /dev/sda1
	Ebs:
	VolumeType: gp3
	VolumeSize: 140
	TagSpecifications:
	- ResourceType: instance
	Tags:
	- Key: Environment
	Value: 'development'
	- Key: Product
	Value: 'project'
	- ResourceType: volume
	Tags:
	- Key: Environment
	Value: 'development'
	- Key: Product
	Value: 'project'
	ray.worker.default:
	# The minimum number of worker nodes of this type to launch.
	# This number should be >= 0.
	min_workers: 5
	# The maximum number of worker nodes of this type to launch.
	# This takes precedence over min_workers.
	#max_workers: 2
	# The node type's CPU and GPU resources are auto-detected based on AWS instance type.
	# If desired, you can override the autodetected CPU and GPU resources advertised to the autoscaler.
	# You can also set custom resources.
	# For example, to mark a node type as having 1 CPU, 1 GPU, and 5 units of a resource called "custom", set
	# resources: {"CPU": 1, "GPU": 1, "custom": 5}
	# resources: {}
	# Provider-specific config for this node type, 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
	node_config:
	InstanceType: m5.large
	# Default AMI for us-east-1.
	# Check https://github.com/ray-project/ray/blob/master/python/ray/autoscaler/_private/aws/config.py
	# for default images for other zones.
	# https://us-east-1.console.aws.amazon.com/ec2/home?region=us-east-1#Images:visibility=public-images;owner=898082745236;architecture=arm64;v=3;$case=tags:false%5C,client:false;$regex=tags:false%5C,client:false
	ImageId: ami-0dd6adfad4ad37eec
	# Run workers on spot by default. Comment this out to use on-demand.
	# NOTE: If relying on spot instances, it is best to specify multiple different instance
	# types to avoid interruption when one instance type is experiencing heightened demand.
	# Demand information can be found at https://aws.amazon.com/ec2/spot/instance-advisor/
	KeyName: key
	EbsOptimized: True
	IamInstanceProfile:
	Name: IamInstanceProfile
	InstanceMarketOptions:
	MarketType: spot
	# Additional options can be found in the boto docs, e.g.
	# SpotOptions:
	# MaxPrice: MAX_HOURLY_PRICE
	TagSpecifications:
	- ResourceType: instance
	Tags:
	- Key: Environment
	Value: 'development'
	- Key: Product
	Value: 'project'
	- ResourceType: volume
	Tags:
	- Key: Environment
	Value: 'development'
	- Key: Product
	Value: 'project'

	# Specify the node type of the head node (as configured above).
	head_node_type: ray.head.default

	# 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

	# 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: [
	'aws ecr get-login-password --region us-east-1 \| docker login --username AWS --password-stdin XXXXXXX.dkr.ecr.us-east-1.amazonaws.com'
	]

	# List of shell commands to run to set up nodes.
	setup_commands: []
	# Note: if you're developing Ray, you probably want to create a Docker image 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).
	# To run the nightly version of ray (as opposed to the latest), either use a rayproject docker image
	# that has the "nightly" (e.g. "rayproject/ray-ml:nightly-gpu") or uncomment the following line:
	# - pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp37-cp37m-manylinux2014_x86_64.whl"

	# Custom commands that will be run on the head node after common setup.
	head_setup_commands: []

	# 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
	- 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
	- ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076