Fix SAM3 visual segment concurrency race (DATAMAN-183)#2124
Open
digaobarbosa wants to merge 2 commits intomainfrom
Open
Fix SAM3 visual segment concurrency race (DATAMAN-183)#2124digaobarbosa wants to merge 2 commits intomainfrom
digaobarbosa wants to merge 2 commits intomainfrom
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Fix concurrency race condition in
/sam3/visual_segmentendpoint causing "An image must be set with .set_image(...) before mask prediction" errors in production.Root cause:
predict_inst()in the sam3 library internally manages predictor state (_is_image_set,_features) on a sharedinst_interactive_predictorinstance. It sets_is_image_set = True, callspredict(), then clears_is_image_set = False. With concurrent requests, one thread's cleanup can execute between another thread's state-set and the state-check inside_predict(), causing the RuntimeError.Fix: Wrap
predict_inst()call in the existing_state_lock(RLock) to serialize access and prevent concurrent state corruption.Logs in prod indicate this error always appear before the 500 in visual_segment
Type of change
How has this change been tested?
Draft - testing in progress.
Will the change affect Universe?
No
Any specific deployment considerations
None - backward compatible, no API changes.
Docs