diff --git a/ci/stress_tests/ray-project/cluster.yaml b/ci/stress_tests/ray-project/cluster.yaml new file mode 100644 index 000000000..8819b906b --- /dev/null +++ b/ci/stress_tests/ray-project/cluster.yaml @@ -0,0 +1,117 @@ +#################################################################### +# 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: ray-stress-tests + +# The minimum number of workers nodes to launch in addition to the head +# node. This number should be >= 0. +min_workers: 105 + +# The maximum number of workers nodes to launch in addition to the head +# node. This takes precedence over min_workers. +max_workers: 105 + +# 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: m4.16xlarge + ImageId: ami-06d51e91cea0dac8d # Ubuntu 18.04 + + # Set primary volume to 25 GiB + BlockDeviceMappings: + - DeviceName: /dev/sda1 + Ebs: + VolumeSize: 100 + + # Additional options in the boto docs. + +# 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-06d51e91cea0dac8d # Ubuntu 18.04 + + # 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. + +# 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 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 + # Install Anaconda. + - wget --quiet 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:$PATH"' >> ~/.bashrc + # # Build Ray. + # - git clone https://github.com/ray-project/ray || true + # - ray/ci/travis/install-bazel.sh + - pip install boto3==1.4.8 cython==0.29.0 + # - cd ray/python; git checkout master; git pull; pip install -e . --verbose + - "pip install https://s3-us-west-2.amazonaws.com/ray-wheels/releases/{{ray_version}}/{{commit}}/ray-{{ray_version}}-cp36-cp36m-manylinux1_x86_64.whl" + +# Custom commands that will be run on the head node after common setup. +head_setup_commands: [] + +# Custom commands that will be run on worker nodes after common setup. +worker_setup_commands: [] + +# Command to start ray on the head node. You don't need to change this. +head_start_ray_commands: + - ray stop + - ulimit -n 65536; ray start --head --num-redis-shards=5 --redis-port=6379 --autoscaling-config=~/ray_bootstrap_config.yaml + +# Command to start ray on worker nodes. You don't need to change this. +worker_start_ray_commands: + - ray stop + - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --num-gpus=100 diff --git a/ci/stress_tests/ray-project/project.yaml b/ci/stress_tests/ray-project/project.yaml new file mode 100644 index 000000000..5f88ff230 --- /dev/null +++ b/ci/stress_tests/ray-project/project.yaml @@ -0,0 +1,35 @@ +# This file is generated by `ray project create`. + +name: ray_stress_tests + +cluster: + config: ray-project/cluster.yaml + params: + - name: ray_version # Ray version string. + default: "0.8.1" + + - name: commit # Ray commit SHA string. + default: "38ec2e70524a277d5aea307f6c843065ff982da5" + + +commands: + - name: test_many_tasks + help: "Run a stress test that executes many tasks." + command: | + python test_many_tasks.py + + - name: test_dead_actors + help: "Run a stress test that spawns and kills many actors." + command: | + python test_dead_actors.py + +# Pathnames for files and directories that should be saved +# in a snapshot but that should not be synced with a# session. Pathnames can be relative to the project +# directory or absolute. Generally, this should be files +# that were created by an active session, such as +# application checkpoints and logs. +output_files: [ + # For example, uncomment this to save the logs from the + # last ray job. + # "/tmp/ray/session_latest", +] diff --git a/ci/stress_tests/ray-project/requirements.txt b/ci/stress_tests/ray-project/requirements.txt new file mode 100644 index 000000000..0f026d879 --- /dev/null +++ b/ci/stress_tests/ray-project/requirements.txt @@ -0,0 +1 @@ +ray[debug] \ No newline at end of file