wehub-resource-sync
74 lines
2.9 KiB
YAML
74 lines
2.9 KiB
YAML
# An unique identifier for the head node and workers of this cluster.
|
|
cluster_name: development
|
|
|
|
# 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
|
|
|
|
# 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
|
|
|
|
# How Ray will authenticate with newly launched nodes.
|
|
auth:
|
|
ssh_user: ubuntu
|
|
|
|
# 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:
|
|
# 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
|
|
ray.head.default:
|
|
node_config:
|
|
InstanceType: m4.16xlarge
|
|
ImageId: ami-0def3275 # Default Ubuntu 16.04 AMI.
|
|
|
|
# Set primary volume to 25 GiB
|
|
BlockDeviceMappings:
|
|
- DeviceName: /dev/sda1
|
|
Ebs:
|
|
VolumeSize: 50
|
|
|
|
# List of shell commands to install ray from source.
|
|
setup_commands:
|
|
# Consider uncommenting these if you run into dpkg locking issues
|
|
# - sudo pkill -9 apt-get || true
|
|
# - sudo pkill -9 dpkg || true
|
|
# - sudo dpkg --configure -a
|
|
# Install basics.
|
|
- sudo apt-get update
|
|
- sudo apt-get install -y build-essential curl unzip
|
|
# Install Node.js in order to build the dashboard.
|
|
- curl -sL https://deb.nodesource.com/setup_12.x | sudo -E bash
|
|
- sudo apt-get install -y nodejs
|
|
# Install Anaconda.
|
|
- wget https://repo.continuum.io/archive/Anaconda3-5.0.1-Linux-x86_64.sh || true
|
|
- bash Anaconda3-5.0.1-Linux-x86_64.sh -b -p $HOME/anaconda3 || true
|
|
- echo 'export PATH="$HOME/anaconda3/bin:$PATH"' >> ~/.bashrc
|
|
# Build Ray.
|
|
- git clone https://github.com/ray-project/ray || true
|
|
- ray/ci/env/install-bazel.sh
|
|
- cd ray/python/ray/dashboard/client; npm ci; npm run build
|
|
- pip install boto3>=1.4.8 cython==0.29.37 aiohttp grpcio psutil setproctitle
|
|
- cd ray/python; pip install -e . --verbose
|
|
|
|
# Command to start ray on the head node. You don't need to change this.
|
|
head_start_ray_commands:
|
|
- ray stop
|
|
- ulimit -n 65536; ray start --head --port=6379 --autoscaling-config=~/ray_bootstrap_config.yaml
|
|
|
|
# Command to start ray on worker nodes. You don't need to change this.
|
|
worker_start_ray_commands:
|
|
- ray stop
|
|
- ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379
|