Feature/probinso/fast completion detection - #185
Open
robinson96 wants to merge 21 commits into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
SUMMARY
Refactor completion handling behind a CompletionDetector interface so
machine launch/cleanup code can select between detector strategies instead
of hard-coding one polling path.
Adds 2 queue-based completion detection modes alongside the legacy polling behavior. completion_queue (or reap) uses a reaper thread to notice when subprocesses end and mark the corresponding test for later processing. (Lower overhead, but not technically safe, but reasonably safe in practice). completion_queue_simple launches 1 thread per test to notice when that test is finished, marking it for later processing. Higher thread count and memory overhead, but safer threading model. Does not scale past a few hundred concurrent tests.
Add detector configuration plumbing, completion stats/spans hooks, updated
scheduler-extension documentation, and focused detector tests.
Record and summarize warnings when the queue-mode reaper observes child
exits that do not belong to registered ATS tests, so the known
waitpid(-1) race is visible in final reporting.
Restore Flux processor-capacity reporting through the normal ATS summary
path and keep unsupported queue-mode paths explicitly rejected where needed.