btl/ofi: fixes for multi mpi init/fini scenarios #13020
Merged
+11
−9
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
The OFI BTL was caching a context -in the case of normal OFI EPs - which needed across multiple sessions init/finalize and resulting in segfaults. Also, there were some symbols being exported which should not have been. Related to open-mpi#13019 Signed-off-by: Howard Pritchard <[email protected]>
devreal
approved these changes
Jan 6, 2025
Turns out that when Open MPI is configured with --enable-mca-dso and is using the OFI MTL/BTL/common, a problem is brought out with the patcher framework the second time through closing the bml and hence btl frameworks. See issue open-mpi#13021. This patch fixes this problem. Signed-off-by: Howard Pritchard <[email protected]>
This was referenced Jan 13, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
The OFI BTL was caching a context -in the case of normal OFI EPs - across multiple sessions init/finalize, resulting in segfaults.
Also, there were some symbols being exported which should not have been.
Related to #13019