prov/sockets: fix rx_buffered arrived befor fi_av_insert - #11037
Closed
hzhou wants to merge 1 commit into
Closed
Conversation
When an unexpected message arrive before fi_av_insert, the av_index won't be available and was set to FI_ADDR_NOTAVAIL. It eventually may get mismatched to a wrong recv entry. Store the raw ip address for this case and try to recover the av_index at match time. Signed-off-by: Hui Zhou <hzhou321@anl.gov>
hzhou
commented
May 16, 2025
| } | ||
| rx_posted = sock_rx_get_entry(rx_ctx, rx_buffered->addr, | ||
| rx_buffered->tag, | ||
| rx_buffered->is_tagged); |
Contributor
Author
There was a problem hiding this comment.
Question: do we allow FI_ADDR_NOTAVAIL to be matched? If so, what is the use case?
Contributor
There was a problem hiding this comment.
It should be allowed. The posted recv may not care who the sender is (i.e. rx_entry->addr == FI_ADDR_UNSPEC).
Contributor
|
This pull request is stale because it has been open 360 days with no activity. Remove stale label or comment, otherwise it will be closed in 7 days. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When an unexpected message arrive before fi_av_insert, the av_index won't be available and was set to FI_ADDR_NOTAVAIL. It eventually may get mismatched to a wrong receive entry. Store the raw ip address for this case and try to recover the av_index at match time.
This bug is triggered in MPICH recent CI testing after we revamped support for MPI Sessions. With world model, we have a barrier at the end of MPI_Init, preventing messages to arrive before all
fi_av_insertscompletes. With sessions, we no longer have such barriers.