mirror of
https://github.com/wassname/ray.git
synced 2026-07-05 07:04:52 +08:00
Ian Rodney
123 lines
5.0 KiB
YAML
123 lines
5.0 KiB
YAML
# An unique identifier for the head node and workers of this cluster.
|
|
cluster_name: default
|
|
|
|
# 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: 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"
|
|
# image: rayproject/ray:latest-gpu # use this one if you don't need ML dependencies, it's faster to pull
|
|
container_name: "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: False
|
|
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: azure
|
|
# https://azure.microsoft.com/en-us/global-infrastructure/locations
|
|
location: westus2
|
|
resource_group: ray-cluster
|
|
# set subscription id otherwise the default from az cli will be used
|
|
# subscription_id: 00000000-0000-0000-0000-000000000000
|
|
|
|
# How Ray will authenticate with newly launched nodes.
|
|
auth:
|
|
ssh_user: ubuntu
|
|
# you must specify paths to matching private and public key pair files
|
|
# use `ssh-keygen -t rsa -b 4096` to generate a new ssh key pair
|
|
ssh_private_key: ~/.ssh/id_rsa
|
|
# changes to this should match what is specified in file_mounts
|
|
ssh_public_key: ~/.ssh/id_rsa.pub
|
|
|
|
# Provider-specific config for the head node, e.g. instance type. By default
|
|
# Ray will auto-configure unspecified fields using defaults.yaml
|
|
head_node:
|
|
azure_arm_parameters:
|
|
vmSize: Standard_NC6
|
|
# List images https://docs.microsoft.com/en-us/azure/virtual-machines/linux/cli-ps-findimage
|
|
imagePublisher: microsoft-dsvm
|
|
imageOffer: ubuntu-1804
|
|
imageSku: "1804"
|
|
imageVersion: 20.07.06
|
|
|
|
# Provider-specific config for worker nodes, e.g. instance type. By default
|
|
# Ray will auto-configure unspecified fields using defaults.yaml
|
|
worker_nodes:
|
|
azure_arm_parameters:
|
|
vmSize: Standard_NC6
|
|
# List images https://docs.microsoft.com/en-us/azure/virtual-machines/linux/cli-ps-findimage
|
|
imagePublisher: microsoft-dsvm
|
|
imageOffer: ubuntu-1804
|
|
imageSku: "1804"
|
|
imageVersion: 20.07.06
|
|
|
|
# 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",
|
|
"/home/ubuntu/.ssh/id_rsa.pub": "~/.ssh/id_rsa.pub"
|
|
}
|
|
|
|
# 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:
|
|
# get rid of annoying Ubuntu message
|
|
- touch ~/.sudo_as_admin_successful
|
|
|
|
# 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 'eval "$(conda shell.bash hook)"' >> ~/.bashrc
|
|
# - echo 'conda activate py37_pytorch' >> ~/.bashrc
|
|
- echo 'conda activate py37_tensorflow' >> ~/.bashrc
|
|
- pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-1.1.0.dev0-cp37-cp37m-manylinux2014_x86_64.whl
|
|
# Consider uncommenting these if you also want to run apt-get commands during setup
|
|
# - sudo pkill -9 apt-get || true
|
|
# - sudo pkill -9 dpkg || true
|
|
# - sudo dpkg --configure -a
|
|
|
|
# Custom commands that will be run on the head node after common setup.
|
|
head_setup_commands:
|
|
- pip install azure-cli-core==2.4.0 azure-mgmt-compute==12.0.0 azure-mgmt-msi==1.0.0 azure-mgmt-network==10.1.0
|
|
|
|
# Custom commands that will be run on worker nodes after common setup.
|
|
worker_setup_commands: []
|
|
|
|
# Command to start ray on the head node. You don't need to change this.
|
|
head_start_ray_commands:
|
|
- ray stop
|
|
- ulimit -n 65536; ray start --head --port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml
|
|
|
|
# Command to start ray on worker nodes. You don't need to change this.
|
|
worker_start_ray_commands:
|
|
- ray stop
|
|
- ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076
|