Skip to content

fix: Improve error handling for Python backend model initialization failures #408

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 8 commits into from
Aug 7, 2025
Merged

fix: Improve error handling for Python backend model initialization failures #408

merged 8 commits into from
Aug 7, 2025
+59 −19

Conversation

pskiran1
Copy link
Member

@pskiran1 pskiran1 commented Jul 21, 2025 •
edited
Loading

  • This change aims to prevent the server from hanging when a Python backend model fails to initialize. It replaces an indefinite wait for a message from the stub process with the ReceiveMessageFromStub function, which correctly detects errors from the stub process.
  • Additionally, it fixes shm cleanup when a model fails to initialize (DLIS-8432).

@pskiran1 pskiran1 mentioned this pull request Jul 21, 2025
Merged
20 tasks
@pskiran1 pskiran1 requested review from krishung5 and yinggeh July 21, 2025 17:07
@pskiran1
Copy link
Member Author

Found a bug that the Python backend internal SHM is not destroyed upon model initialization failure, and have created an internal ticket DLIS-8432.

@pskiran1 pskiran1 changed the title fix: Improve error handling for Python backend model initialization failures [Do Not Merge] fix: Improve error handling for Python backend model initialization failures Aug 4, 2025
@pskiran1 pskiran1 changed the title [Do Not Merge] fix: Improve error handling for Python backend model initialization failures fix: Improve error handling for Python backend model initialization failures Aug 5, 2025
@pskiran1 pskiran1 requested a review from yinggeh August 5, 2025 19:04
@pskiran1 pskiran1 requested a review from kthui August 6, 2025 14:56
yinggeh
yinggeh reviewed Aug 6, 2025
View reviewed changes
@yinggeh yinggeh self-requested a review August 7, 2025 00:08
kthui
kthui approved these changes Aug 7, 2025
View reviewed changes
Copy link
Contributor

@kthui kthui left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice work making the stub launch process more robust!

krishung5
krishung5 approved these changes Aug 7, 2025
View reviewed changes
Copy link
Contributor

@krishung5 krishung5 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm, great work!

yinggeh
yinggeh approved these changes Aug 7, 2025
View reviewed changes
Copy link
Contributor

@yinggeh yinggeh left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice work!

@pskiran1 pskiran1 merged commit 8f2df55 into main Aug 7, 2025
3 checks passed
@pskiran1 pskiran1 deleted the spolisetty_pb_model_load branch August 7, 2025 10:56
pskiran1 added a commit that referenced this pull request Aug 7, 2025
@pskiran1
fix: Improve error handling for Python backend model initialization f…
cf4aeb8 
…ailures (#408)
@pskiran1 pskiran1 mentioned this pull request Aug 7, 2025
Merged
mc-nv pushed a commit that referenced this pull request Aug 7, 2025
@pskiran1
fix: Improve error handling for Python backend model initialization f…
c94f397 
…ailures (#408) (#413)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@kthui kthui kthui approved these changes

@krishung5 krishung5 krishung5 approved these changes

@yinggeh yinggeh yinggeh approved these changes

Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@pskiran1 @kthui @krishung5 @yinggeh