ITS: track memory allocations + graceful of exceeding limit #14326
Merged
mconcas merged 2 commits intoAliceO2Group:devfrom Jun 4, 2025
Merged
ITS: track memory allocations + graceful of exceeding limit #14326mconcas merged 2 commits intoAliceO2Group:devfrom
mconcas merged 2 commits intoAliceO2Group:devfrom
Conversation
Contributor
|
REQUEST FOR PRODUCTION RELEASES: This will add The following labels are available |
07c3649 to
a11c4bd
Compare
Signed-off-by: Felix Schlepper <felix.schlepper@cern.ch>
eca3b1e to
bf7cbab
Compare
Signed-off-by: Felix Schlepper <felix.schlepper@cern.ch>
mpuccio
approved these changes
Jun 3, 2025
Contributor
mpuccio
left a comment
There was a problem hiding this comment.
Looks good to me, thanks a lot!
mconcas
approved these changes
Jun 4, 2025
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
based on #14312 (will rebase if merged)
the pr aims to allow to stop the occasional exponential growth of buffers by using a custom allocator which throws an exception if the configurable memory limit is exceeded by the request. the algorithm then gracefully (before allocating any memory) drops the time slice.
for this to work a switch to tbb had to be done since in omp the exception thrown has to be handled by the throwing thread and is not propagated to the master thread. tbb guarantees this + cancellation of all parallel work.
Validation of getting the same output after modifications:

no particular gain/loss for the vertexing:

a >50% gain in findRoads due an optimisation switching away from an atomic variable under heavy contention:

before the change:

after the change:

P.S. Also sorry for these insanely big PRs, this is not nice for reviewers or to other people that work on the code basis.