Repository navigation
Conversation
The graceful finalize wait discarded waitpid status, so a stub that died on SIGSEGV, SIGABRT, SIGBUS, SIGILL, or SIGFPE looked like a normal exit. Signed-off-by: Yingge He <yinggeh@nvidia.com>
8 of 20 tasks
|
The waitpid check cleared stub_pid_ before comparing it with the return value, so the crash log never ran. Signed-off-by: Yingge He <yinggeh@nvidia.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does the PR do?
Log an error when the Python backend stub exits on SIGSEGV, SIGABRT, SIGBUS, SIGILL, or SIGFPE during the graceful finalize wait. SIGKILL stays unlogged because an unhealthy stub is terminated that way on purpose.
Checklist
<commit_type>: <Title>Commit Type:
Check the conventional commit type
box here and add the label to the github PR.
Related PRs:
Where should the reviewer start?
src/stub_launcher.cc,WaitForStubProcessWithTimeout.Test plan:
Build the devel image from this branch and run
L0_backend_python--baseandL0_infer--basewith the matching server branch. Intentional stub kills inmodel_readinessandrestartmust stay green.Caveats:
A crash already reaped by
StubActive()has no status left, so it is not logged.Background
The graceful finalize wait discarded
waitpidstatus, so a stub that died on a crash signal looked like a normal exit.Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)