Skip to content

orte: shutdown #6239

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.

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

Merged

Conversation

hppritcha
Copy link
Member

@hppritcha hppritcha commented Jan 4, 2019

be more careful about closing frameworks as part of
orte_finalize. Owing to recent restructuring in opal to handle
finalize in a more general fashion, the missing framework
closes were causing meltdowns as the mca vars subsystem
was cleaning itself up.

This problem was recently reported by Siegmar:

https://www.mail-archive.com/[email protected]//msg32946.html

Signed-off-by: Howard Pritchard [email protected]

be more careful about closing framewworks as part of
orte_finalize.  Owing to recent restructuring in opal to handle
finalize in a more general fashion, the missing framework
closes were causing meltdowns as the mca vars subsystem
was cleaning itself up.

This problem was recently reported by Siegmar:

https://www.mail-archive.com/[email protected]//msg32946.html

Signed-off-by: Howard Pritchard <[email protected]>
@hppritcha
Copy link
Member Author

@rhc54 i'll open a PR on prrte if you'd like.

@hppritcha
Copy link
Member Author

@siegmargross you may want to try this branch and see if it fixes the problem you reported.

@hppritcha
Copy link
Member Author

note this meltdown occurs only in the non HNP orted instances.

@rhc54
Copy link
Contributor

rhc54 commented Jan 4, 2019

@rhc54 i'll open a PR on prrte if you'd like.

Hmmm...we haven't picked up the new OPAL finalize logic, so a PR won't work over there. Guess this is part of the "what do we do about OPAL" issue we haven't really resolved yet.

@hppritcha hppritcha added the PR to PRRTE for PRs that we may want to push to PRRTE label Jan 4, 2019
@hppritcha hppritcha merged commit 3a4a1f9 into open-mpi:master Jan 4, 2019
@siegmargross
Copy link

Thank you very much for the solution. It works again.

@hppritcha hppritcha deleted the topic/swat_orte_shutdown_mca_issue branch October 29, 2021 17:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug PR to PRRTE for PRs that we may want to push to PRRTE
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants