[v4.1.x] mtl/ofi: bail gracefully if completion error context is null #12395
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
According to libfabric API, fi_cq_readerr also reports errors for requests that did not require completion, and associate a null context with the error entry. This patch adds null check and bail gracefully as to avoid invalid memory access. bot:notacherrypick Signed-off-by: Wenduo Wang <[email protected]>
jsquyres
reviewed
Mar 21, 2024
| } | ||
|
|
||
| if (!error.op_context) { | ||
| opal_output(0, "%s:%d: Error returned from fi_cq_readerr with null context. " |
Member
There was a problem hiding this comment.
All of these opal_output() calls really should be show_help calls -- show_help is de-duplicated at mpirun.
Contributor
Author
There was a problem hiding this comment.
I don't know if this error will cause a lot of duplication - it should be rather rare and isolated.
So what is the intended use case for opal_output?
Member
There was a problem hiding this comment.
I don't think show_help is needed here. Certainly wouldn't be wrong, but the current code base (including this PR) is full of existing calls to opal_output() for errors that are unlikely to be correlated across nodes.
bwbarrett
approved these changes
Mar 26, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
This is a manual cherry-pick of #12388
According to libfabric API, fi_cq_readerr also reports errors for requests that did not require completion, and associate a null context with the error entry. This patch adds null check and bail gracefully as to avoid invalid memory access.
bot:notacherrypick