mirror of
https://github.com/wassname/ray.git
synced 2026-07-03 03:45:55 +08:00
Robert Nishihara
164 lines
6.2 KiB
YAML
164 lines
6.2 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 initial number of worker nodes to launch in addition to the head
|
|
# node. When the cluster is first brought up (or when it is refreshed with a
|
|
# subsequent `ray up`) this number of nodes will be started.
|
|
initial_workers: 0
|
|
|
|
# Whether or not to autoscale aggressively. If this is enabled, if at any point
|
|
# we would start more workers, we start at least enough to bring us to
|
|
# initial_workers.
|
|
autoscaling_mode: default
|
|
|
|
# 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., tensorflow/tensorflow:1.5.0-py3
|
|
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"
|
|
|
|
|
|
# The autoscaler will scale up the cluster to this target fraction of resource
|
|
# usage. For example, if a cluster of 10 nodes is 100% busy and
|
|
# target_utilization is 0.8, it would resize the cluster to 13. This fraction
|
|
# can be decreased to increase the aggressiveness of upscaling.
|
|
# This value must be less than 1.0 for scaling to happen.
|
|
target_utilization_fraction: 0.8
|
|
|
|
# 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
|
|
|
|
# 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
|
|
head_node:
|
|
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/family/tf-1-13-cpu
|
|
|
|
# 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: []
|
|
|
|
worker_nodes:
|
|
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/family/tf-1-13-cpu
|
|
# Run workers on preemtible instance by default.
|
|
# Comment this out to use on-demand.
|
|
scheduling:
|
|
- preemptible: true
|
|
|
|
# Additional options can be found in in the compute docs at
|
|
# https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
|
|
|
|
# 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",
|
|
}
|
|
|
|
# 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).
|
|
# - echo 'export PATH="$HOME/anaconda3/envs/tensorflow_p36/bin:$PATH"' >> ~/.bashrc
|
|
|
|
# Install Anaconda.
|
|
- >-
|
|
wget https://repo.continuum.io/archive/Anaconda3-5.0.1-Linux-x86_64.sh -O ~/anaconda3.sh
|
|
|| true
|
|
&& bash ~/anaconda3.sh -b -p ~/anaconda3 || true
|
|
&& rm ~/anaconda3.sh
|
|
&& echo 'export PATH="$HOME/anaconda3/bin:$PATH"' >> ~/.profile
|
|
|
|
# Install ray
|
|
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp27-cp27mu-manylinux1_x86_64.whl
|
|
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp35-cp35m-manylinux1_x86_64.whl
|
|
- pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp36-cp36m-manylinux1_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
|
|
- >-
|
|
ulimit -n 65536;
|
|
ray start
|
|
--head
|
|
--redis-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
|