ray/release/stress_tests/autoscaler-cluster.yaml
2021-01-15 17:41:17 -08:00

117 lines
4.5 KiB
YAML

####################################################################
# All nodes in this cluster will auto-terminate in 1 hour
####################################################################
# An unique identifier for the head node and workers of this cluster.
cluster_name: autoscaler-stress-test
# The minimum number of workers nodes to launch in addition to the head
# node. This number should be >= 0.
min_workers: 100
# The maximum number of workers nodes to launch in addition to the head
# node. This takes precedence over min_workers.
max_workers: 100
# 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-1
availability_zone: us-west-1a
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: m4.16xlarge
ImageId: ami-0cc472544ce594a19 # Custom ami
# Set primary volume to 25 GiB
BlockDeviceMappings:
- DeviceName: /dev/sda1
Ebs:
VolumeSize: 100
# Additional options in the boto docs.
docker:
image: "rayproject/ray:latest-gpu" # You can change this to latest-cpu if you don't need GPU support and want a faster startup
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: ["--ulimit nofile=1045876"] # Extra options to pass into "docker run"
# Provider-specific config for worker nodes, 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
worker_nodes:
InstanceType: m4.large
ImageId: ami-0cc472544ce594a19 # Custom ami
# Set primary volume to 25 GiB
BlockDeviceMappings:
- DeviceName: /dev/sda1
Ebs:
VolumeSize: 100
# Run workers on spot by default. Comment this out to use on-demand.
InstanceMarketOptions:
MarketType: spot
# Additional options can be found in the boto docs, e.g.
# SpotOptions:
# MaxPrice: MAX_HOURLY_PRICE
# Additional options in the boto docs.
# List of shell commands to run to set up nodes.
setup_commands:
# Uncomment these if you want to build ray from source.
# - sudo apt-get -qq update
# - sudo apt-get install -y build-essential curl unzip
# # Build Ray.
# - git clone https://github.com/ray-project/ray || true
# - ray/ci/travis/install-bazel.sh
- pip install -U pip
- pip install terminado
- pip install boto3==1.4.8 cython==0.29.0
# - cd ray/python; git checkout master; git pull; pip install -e . --verbose
- pip install -U pip install https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-2.0.0.dev0-cp38-cp38-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
- ulimit -n 65536; ray start --head --port=6379 --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 --num-gpus=100