mirror of
https://github.com/vale981/ray
synced 2025-03-10 13:26:39 -04:00
b1308b1c8c
This fixes the previous problems from team column revert. This has 2 additional changes; alert handler receives the team argument, which was the root cause of breakage; https://github.com/ray-project/ray/pull/21289 Previously, tests without a team column were raising an exception, but I made the condition weaker (warning logs). I will eventually change it to raise an exception, but for smoother transition, we will log warning instead for a short time
40 lines
1.3 KiB
Python
40 lines
1.3 KiB
Python
import datetime
|
|
|
|
from typing import Dict, Optional
|
|
|
|
|
|
def handle_result(created_on: datetime.datetime, category: str,
|
|
test_suite: str, test_name: str, status: str, results: Dict,
|
|
artifacts: Dict, last_logs: str, team: str) -> Optional[str]:
|
|
assert test_suite == "long_running_tests"
|
|
|
|
# elapsed_time = results.get("elapsed_time", 0.)
|
|
last_update_diff = results.get("last_update_diff", float("inf"))
|
|
|
|
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 = 120
|
|
|
|
elif test_name in ["apex", "impala", "many_ppo", "pbt"]:
|
|
# Tune/RLLib style tests
|
|
target_update_diff = 360
|
|
elif test_name in ["serve", "serve_failure"]:
|
|
# Serve tests have workload logs every five minutes.
|
|
# Leave up to 60 seconds overhead.
|
|
target_update_diff = 360
|
|
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
|