Skip to content

Openib proc accounting fix #1260

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 3 commits into from
Dec 27, 2015
Merged

Openib proc accounting fix #1260

merged 3 commits into from
Dec 27, 2015

Conversation

artpol84
Copy link
Contributor

@hjelmn
I'm still working on this, however I'd like to know your position regarding this changes.
Right now it works for OSU tests and I am currently testing it with the full MTT test suite.

@artpol84 artpol84 changed the title Openib proc account fix Openib proc accounting fix Dec 24, 2015
@artpol84
Copy link
Contributor Author

MTT looks fine. No degradation.

@artpol84
Copy link
Contributor Author

Not true - looks like I see some problems with mpi-test-suite. Let me check.

@artpol84
Copy link
Contributor Author

@hjelmn I've checked, the problem is out of the scope of this patch.
I'm seeing rear hangs of mpi_test_suite, on Gather but this appears with both tcp and openib BTL.

@artpol84
Copy link
Contributor Author

@rhc54 @jsquyres @hppritcha @hjelmn
Merry Christmas, dear colleagues :).

@artpol84
Copy link
Contributor Author

Update: the hang that I was observing with mpi-test-suite seems to be related to vader BTL. If I use sm all runs fine. I recall that @rhc54 has told me that somebody was reporing vader hangs. I think that's it.
I'll try to investigate.

@artpol84
Copy link
Contributor Author

mpi-test-suite problem addressed in PR #1264.

@hjelmn
Copy link
Member

hjelmn commented Dec 27, 2015

PR to v2.x

hjelmn added a commit that referenced this pull request Dec 27, 2015
@hjelmn
Merge pull request #1260 from artpol84/openib_proc_account_fix
700a210 
Openib proc accounting fix
@hjelmn hjelmn merged commit 700a210 into open-mpi:master Dec 27, 2015
@artpol84
Copy link
Contributor Author

@hjelmn, to PR this to v2.x we need to merge open-mpi/ompi-release#868 first. This PR depends on it.

@artpol84 artpol84 deleted the openib_proc_account_fix branch December 29, 2015 14:53
artpol84 added a commit to artpol84/ompi that referenced this pull request Dec 29, 2015
@artpol84
Fix Mellanox copyrights with respect to the following PRs:
2abb297 
* open-mpi#1184
* open-mpi#1188
* open-mpi#1197
* open-mpi#1202
* open-mpi#1210
* open-mpi#1216
* open-mpi#1236
* open-mpi#1237
* open-mpi#1248
* open-mpi#1260
* open-mpi#1264
@artpol84 artpol84 mentioned this pull request Dec 29, 2015
Merged
@artpol84 artpol84 mentioned this pull request Jan 11, 2016
Merged
jsquyres added a commit to jsquyres/ompi that referenced this pull request Aug 23, 2016
@jsquyres
Merge pull request open-mpi#1260 from ggouaillardet/topic/v2.x/coll_f…
4e9efd4 
…ixes

v2.x: various mca/coll fixes
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
Severity: critical
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@artpol84 @hjelmn