fix: race during stop of active backends #5106
Merged
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
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
✅ Deploy Preview for localai ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
mudler
changed the title
There was a problem hiding this comment.
Pull Request Overview
This PR addresses a race condition during the shutdown of active backends by refactoring the shutdown logic. Key changes include refactoring the deletion logic in deleteProcess with a retry loop, replacing the old ShutdownModel in loader.go with deleteProcess, and refining stopActiveBackends behavior based on the singleActiveBackend flag.
Reviewed Changes
Copilot reviewed 3 out of 4 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| pkg/model/process.go | Refactored deleteProcess to include a retry loop and forced shutdown |
| pkg/model/loader.go | Removed outdated shutdown logic and now calls deleteProcess |
| pkg/model/initializers.go | Adjusted stopActiveBackends logic for proper single backend handling |
Files not reviewed (1)
- .env: Language not supported
mudler
commented
Mar 31, 2025
| @@ -44,9 +62,12 @@ func (ml *ModelLoader) deleteProcess(s string) error { | |||
|
|
|||
| func (ml *ModelLoader) StopGRPC(filter GRPCProcessFilter) error { | |||
| var err error = nil | |||
| ml.mu.Lock() | |||
There was a problem hiding this comment.
here we were missing the lock when iterating over models
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Outdated suggestions cannot be applied.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
This PR is a small refactor while I was walking out the code, and found a potential race condition.
This pull request introduces several changes to improve the handling of backend shutdowns and model loading in the
pkg/modelpackage. The key changes include adding a new environment variable to force backend shutdown, refactoring thedeleteProcessmethod, and ensuring proper backend management during model loading.Backend shutdown improvements:
.env: Added a new environment variableLOCALAI_FORCE_BACKEND_SHUTDOWNto force the shutdown of backends if they are busy.pkg/model/process.go: Refactored thedeleteProcessmethod to handle retries and force shutdown if the backend is busy, using the new environment variable. [1] [2]Model loading enhancements:
pkg/model/initializers.go: Modified thestopActiveBackendsmethod to return early ifsingleActiveBackendis not set, and added comments to clarify the backend loading process. [1] [2] [3]pkg/model/loader.go: Removed the busy-wait loop from theShutdownModelmethod, delegating the shutdown process to thedeleteProcessmethod.Notes for Reviewers
Signed commits