mirror of
https://github.com/vale981/ray
synced 2025-03-10 13:26:39 -04:00
75504b9586
Running `./ci/long_running_tests/start_workloads.sh` will start several workloads running (each in their own EC2 instance). - The workloads run forever. - The workloads all simulate multiple nodes but use a single machine. - You can get the tail of each workload by running `./ci/long_running_tests/check_workloads.sh`. - You have to manually shut down the instances. As discussed with @ericl @richardliaw, the idea here is to optimize for the debuggability of the tests. If one of them fails, you can ssh to the relevant instance and see all of the logs.
65 lines
2.1 KiB
YAML
65 lines
2.1 KiB
YAML
cluster_name: default
|
|
min_workers: 0
|
|
max_workers: 0
|
|
target_utilization_fraction: 0.8
|
|
idle_timeout_minutes: 5
|
|
|
|
# Cloud-provider specific configuration.
|
|
provider:
|
|
type: aws
|
|
region: us-west-2
|
|
availability_zone: us-west-2a
|
|
auth:
|
|
ssh_user: ubuntu
|
|
|
|
head_node:
|
|
InstanceType: m5.2xlarge
|
|
ImageId: ami-0def3275 # Default Ubuntu 16.04 AMI.
|
|
|
|
# Set primary volume to 25 GiB
|
|
BlockDeviceMappings:
|
|
- DeviceName: /dev/sda1
|
|
Ebs:
|
|
VolumeSize: 50
|
|
|
|
worker_nodes:
|
|
InstanceType: m5.large
|
|
ImageId: ami-0def3275 # Default Ubuntu 16.04 AMI.
|
|
|
|
# Set primary volume to 25 GiB
|
|
BlockDeviceMappings:
|
|
- DeviceName: /dev/sda1
|
|
Ebs:
|
|
VolumeSize: 50
|
|
|
|
# Run workers on spot by default. Comment this out to use on-demand.
|
|
InstanceMarketOptions:
|
|
MarketType: spot
|
|
|
|
# List of shell commands to run to set up nodes.
|
|
setup_commands:
|
|
# 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
|
|
# Some Python dependencies.
|
|
- pip install boto3==1.4.8 cython==0.29.0
|
|
# # Uncomment the following if you wish to install Ray instead.
|
|
# - sudo apt-get update
|
|
# - sudo apt-get install -y cmake pkg-config build-essential autoconf curl libtool unzip flex bison python
|
|
# - git clone https://github.com/ray-project/ray || true
|
|
# - cd ray/python; git checkout master; git pull; pip install -e . --verbose
|
|
# Install nightly Ray wheels.
|
|
- pip install https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.7.0.dev0-cp36-cp36m-manylinux1_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: []
|
|
|
|
# Command to start ray on worker nodes. You don't need to change this.
|
|
worker_start_ray_commands: []
|