distributed icon indicating copy to clipboard operation
distributed copied to clipboard

Weigh gilknocker Prometheus metric by duration

Open crusaderky opened this issue 11 months ago • 2 comments

  • Blocked by #8560
  • Closes #8557
  • Renames prometheus metrics:
main this PR
dask_scheduler_gil_contention_total dask_scheduler_gil_contention_seconds_total
dask_worker_gil_contention_total dask_worker_gil_contention_seconds_total

stress test from #8557:

BEFORE

Screenshot from 2024-03-06 15-17-22

AFTER

Screenshot from 2024-03-07 16-25-14

CC @ntabris @milesgranger

crusaderky avatar Mar 07 '24 12:03 crusaderky

Unit Test Results

See test report for an extended history of previous test failures. This is useful for diagnosing flaky tests.

    27 files  +    26      27 suites  +26   10h 2m 13s :stopwatch: + 10h 1m 49s  4 048 tests + 4 003   3 934 :white_check_mark: + 3 926    110 :zzz: +   73   4 :x: + 4  50 828 runs  +50 783  48 463 :white_check_mark: +48 455  2 334 :zzz: +2 297  31 :x: +31 

For more details on these failures, see this check.

Results for commit f919669e. ± Comparison against base commit e16a7af1.

:recycle: This comment has been updated with latest results.

github-actions[bot] avatar Mar 07 '24 12:03 github-actions[bot]

Thanks, @crusaderky! It would be nice to be able to get more accurate GIL data via Prometheus.

ntabris avatar Mar 07 '24 16:03 ntabris