mirror of
https://github.com/vale981/ray
synced 2025-03-06 02:21:39 -05:00
331b71ea8d
Adds a unit-tested and restructured ray_release package for running release tests.
Relevant changes in behavior:
Per default, Buildkite will wait for the wheels of the current commit to be available. Alternatively, users can a) specify a different commit hash, b) a wheels URL (which we will also wait for to be available) or c) specify a branch (or user/branch combination), in which case the latest available wheels will be used (e.g. if master is passed, behavior matches old default behavior).
The main subpackages are:
Cluster manager: Creates cluster envs/computes, starts cluster, terminates cluster
Command runner: Runs commands, e.g. as client command or sdk command
File manager: Uploads/downloads files to/from session
Reporter: Reports results (e.g. to database)
Much of the code base is unit tested, but there are probably some pieces missing.
Example build (waited for wheels to be built): https://buildkite.com/ray-project/kf-dev/builds/51#_
Wheel build: https://buildkite.com/ray-project/ray-builders-branch/builds/6023
43 lines
1.1 KiB
Python
43 lines
1.1 KiB
Python
from typing import Optional
|
|
|
|
from ray_release.config import Test
|
|
from ray_release.result import Result
|
|
|
|
|
|
def handle_result(
|
|
test: Test,
|
|
result: Result,
|
|
) -> Optional[str]:
|
|
last_update_diff = result.results.get("last_update_diff", float("inf"))
|
|
|
|
test_name = test["legacy"]["test_name"]
|
|
|
|
if test_name in [
|
|
"actor_deaths",
|
|
"many_actor_tasks",
|
|
"many_drivers",
|
|
"many_tasks",
|
|
"many_tasks_serialized_ids",
|
|
"node_failures",
|
|
"object_spilling_shuffle",
|
|
]:
|
|
# Core tests
|
|
target_update_diff = 300
|
|
|
|
elif test_name in ["apex", "impala", "many_ppo", "pbt"]:
|
|
# Tune/RLLib style tests
|
|
target_update_diff = 480
|
|
elif test_name in ["serve", "serve_failure"]:
|
|
# Serve tests have workload logs every five minutes.
|
|
# Leave up to 180 seconds overhead.
|
|
target_update_diff = 480
|
|
else:
|
|
return None
|
|
|
|
if last_update_diff > target_update_diff:
|
|
return (
|
|
f"Last update to results json was too long ago "
|
|
f"({last_update_diff:.2f} > {target_update_diff})"
|
|
)
|
|
|
|
return None
|