name: long-running-tests
description: "Ray's long running stress tests"

cluster:
  config: ray-project/cluster.yaml

commands:
  - name: run
    help: "Start a long running stress test."
    command: |
      # Install nightly Ray wheels.
      source activate tensorflow_p36 && pip install -q -U {{wheel}} Click
      source activate tensorflow_p36 && pip install -q ray[all] gym[atari]
      source activate tensorflow_p36 && python workloads/{{workload}}.py
    params:
      - name: wheel
        help: "URL to the ray wheel to test (defaults to latest)."
        default: https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp36-cp36m-manylinux1_x86_64.whl
      - name: workload
        help: "Name of the workload to run."
        choices:
          [
            "actor_deaths",
            "apex",
            "impala",
            "many_actor_tasks",
            "many_drivers",
            "many_tasks",
            "node_failures",
            "pbt",
            "serve",
          ]
    config:
      tmux: true

  - name: check-load
    command: uptime
    help: "Check load of the workload."

  - name: show-output
    command: tmux capture-pane -p
    help: "Show tail of the workoad output."

# 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",