wehub-resource-sync
192 lines
8.2 KiB
YAML
192 lines
8.2 KiB
YAML
# An unique identifier for the head node and workers of this cluster.
|
|
cluster_name: default
|
|
|
|
# The maximum number of workers nodes to launch in addition to the head
|
|
# node.
|
|
max_workers: 2
|
|
|
|
# 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: "rayproject/ray-ml:latest-gpu" # 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: "ray_container"
|
|
# 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: gcp
|
|
region: us-west1
|
|
availability_zone: us-west1-a
|
|
project_id: null # Globally unique project id
|
|
|
|
# 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. This requires that you have added the key into the
|
|
# project wide meta-data.
|
|
# 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:
|
|
# The resources provided by this node type.
|
|
resources: {"CPU": 2}
|
|
# Provider-specific config for the head node, e.g. instance type. By default
|
|
# Ray will auto-configure unspecified fields such as subnets and ssh-keys.
|
|
# For more documentation on available fields, see:
|
|
# https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
|
|
node_config:
|
|
machineType: n1-standard-2
|
|
disks:
|
|
- boot: true
|
|
autoDelete: true
|
|
type: PERSISTENT
|
|
initializeParams:
|
|
diskSizeGb: 50
|
|
# See https://cloud.google.com/compute/docs/images for more images
|
|
sourceImage: projects/deeplearning-platform-release/global/images/common-cpu-v20240922
|
|
|
|
# Additional options can be found in in the compute docs at
|
|
# https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
|
|
|
|
# If the network interface is specified as below in both head and worker
|
|
# nodes, the manual network config is used. Otherwise an existing subnet is
|
|
# used. To use a shared subnet, ask the subnet owner to grant permission
|
|
# for 'compute.subnetworks.use' to the ray autoscaler account...
|
|
# networkInterfaces:
|
|
# - kind: compute#networkInterface
|
|
# subnetwork: path/to/subnet
|
|
# aliasIpRanges: []
|
|
ray_worker_small:
|
|
# The minimum number of worker nodes of this type to launch.
|
|
# This number should be >= 0.
|
|
min_workers: 1
|
|
# The maximum number of worker nodes of this type to launch.
|
|
# This takes precedence over min_workers.
|
|
max_workers: 2
|
|
# The resources provided by this node type.
|
|
resources: {"CPU": 2}
|
|
# Provider-specific config for the head node, e.g. instance type. By default
|
|
# Ray will auto-configure unspecified fields such as subnets and ssh-keys.
|
|
# For more documentation on available fields, see:
|
|
# https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
|
|
node_config:
|
|
machineType: n1-standard-2
|
|
disks:
|
|
- boot: true
|
|
autoDelete: true
|
|
type: PERSISTENT
|
|
initializeParams:
|
|
diskSizeGb: 50
|
|
# See https://cloud.google.com/compute/docs/images for more images
|
|
sourceImage: projects/deeplearning-platform-release/global/images/common-cpu-v20240922
|
|
# Run workers on preemtible instance by default.
|
|
# Comment this out to use on-demand.
|
|
scheduling:
|
|
- preemptible: true
|
|
# Un-Comment this to launch workers with the Service Account of the Head Node
|
|
# serviceAccounts:
|
|
# - email: ray-autoscaler-sa-v1@<project_id>.iam.gserviceaccount.com
|
|
# scopes:
|
|
# - https://www.googleapis.com/auth/cloud-platform
|
|
|
|
# Additional options can be found in in the compute docs at
|
|
# https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
|
|
|
|
# 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: []
|
|
|
|
# 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:
|
|
- pip install google-api-python-client==1.7.8
|
|
|
|
# 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
|