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
41 lines
1.1 KiB
Python
41 lines
1.1 KiB
Python
from ray_release.config import Test
|
|
from ray_release.exception import ReleaseTestConfigError, ResultsAlert
|
|
from ray_release.logger import logger
|
|
from ray_release.result import Result
|
|
|
|
from ray_release.alerts import (
|
|
default,
|
|
long_running_tests,
|
|
rllib_tests,
|
|
tune_tests,
|
|
xgboost_tests,
|
|
)
|
|
|
|
|
|
result_to_handle_map = {
|
|
"default": default.handle_result,
|
|
"long_running_tests": long_running_tests.handle_result,
|
|
"rllib_tests": rllib_tests.handle_result,
|
|
"tune_tests": tune_tests.handle_result,
|
|
"xgboost_tests": xgboost_tests.handle_result,
|
|
}
|
|
|
|
|
|
def handle_result(test: Test, result: Result):
|
|
alert_suite = test.get("alert", "default")
|
|
|
|
logger.info(
|
|
f"Checking results for test {test['name']} using alerting suite "
|
|
f"{alert_suite}"
|
|
)
|
|
|
|
if alert_suite not in result_to_handle_map:
|
|
raise ReleaseTestConfigError(f"Alert suite {alert_suite} not found.")
|
|
|
|
handler = result_to_handle_map[alert_suite]
|
|
error = handler(test, result)
|
|
|
|
if error:
|
|
raise ResultsAlert(error)
|
|
|
|
logger.info("No alerts have been raised - test passed successfully!")
|