mirror of
https://github.com/vale981/ray
synced 2025-03-06 10:31:39 -05:00
87 lines
3.2 KiB
YAML
87 lines
3.2 KiB
YAML
|
# This file is generated by `ray project create`.
|
||
|
|
|
||
|
|
# A unique identifier for the head node and workers of this cluster.
|
||
|
|
cluster_name: long-running-distributed-tests
|
||
|
|
|
||
|
|
# The minimum number of workers nodes to launch in addition to the head
|
||
|
|
# node. This number should be >= 0.
|
||
|
|
min_workers: 3
|
||
|
|
# The maximum number of workers nodes to launch in addition to the head
|
||
|
|
# node. This takes precedence over min_workers. min_workers defaults to 0.
|
||
|
|
max_workers: 3
|
||
|
|
|
||
|
|
# 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: aws
|
||
|
|
region: us-west-2
|
||
|
|
availability_zone: us-west-2a
|
||
|
|
cache_stopped_nodes: False
|
||
|
|
|
||
|
|
# 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
|
||
|
|
|
||
|
|
# 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: g3.8xlarge
|
||
|
|
ImageId: ami-0888a3b5189309429 # DLAMI 7/1/19
|
||
|
|
BlockDeviceMappings:
|
||
|
|
- DeviceName: /dev/sda1
|
||
|
|
Ebs:
|
||
|
|
VolumeSize: 150
|
||
|
|
|
||
|
|
worker_nodes:
|
||
|
|
InstanceType: g3.8xlarge
|
||
|
|
ImageId: ami-0888a3b5189309429 # DLAMI 7/1/19
|
||
|
|
BlockDeviceMappings:
|
||
|
|
- DeviceName: /dev/sda1
|
||
|
|
Ebs:
|
||
|
|
VolumeSize: 150
|
||
|
|
InstanceMarketOptions:
|
||
|
|
MarketType: spot
|
||
|
|
|
||
|
|
setup_commands:
|
||
|
|
# Install ray.
|
||
|
|
- pip install -U pip
|
||
|
|
- ray || pip install -U {{ray-wheel}}
|
||
|
|
# Installing this without -U to make sure we don't replace the existing Ray installation
|
||
|
|
- pip install ray[rllib]
|
||
|
|
- pip install -U ipdb
|
||
|
|
# There have been some recent problems with torch 1.5 and torchvision 0.6
|
||
|
|
# not recognizing GPUs.
|
||
|
|
# So, we force install torch 1.4 and torchvision 0.5.
|
||
|
|
# https://github.com/pytorch/pytorch/issues/37212#issuecomment-623198624.
|
||
|
|
- pip install torch==1.4.0 torchvision==0.5.0
|
||
|
|
- echo set-window-option -g mouse on > ~/.tmux.conf
|
||
|
|
- echo 'termcapinfo xterm* ti@:te@' > ~/.screenrc
|
||
|
|
|
||
|
|
# Command to start ray on the head node. You don't need to change this.
|
||
|
|
head_start_ray_commands:
|
||
|
|
- ray stop
|
||
|
|
- export RAY_BACKEND_LOG_LEVEL=debug
|
||
|
|
- 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
|
||
|
|
- export RAY_BACKEND_LOG_LEVEL=debug
|
||
|
|
- ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076
|