Unified Storage Performance Optimizations #1
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
…#97529) * dont lazy init unified storage * Inits index when creating new resource server. Fixes trace propagation by passing span ctx. Update some logging. * Use finer grained cache locking when building indexes to speed things up. Locking the whole function was slowing things down. * formatting * linter fix * go mod * make update-workspace * fix workspaces check error * update dependency owner in mod file * wait 1 second before querying metrics * try with big timeout, see if fixes CI. Wont fail locally. * skips postgres integration test. Only fails in drone. Will fix later. * put delay back to 500 ms
Author
|
cursor review |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
|
|
||
| b.cacheMu.Lock() | ||
| b.cache[key] = idx | ||
| b.cacheMu.Unlock() |
There was a problem hiding this comment.
Bug: Race Condition: Unnecessary Index Generation
Moving the mutex lock to after index building creates a race condition where multiple goroutines can concurrently build the same index for the same key. All goroutines will perform the expensive index building work, then race to write to the cache. The lock needs to protect the entire check-and-build operation to prevent duplicate work and ensure only one index is built per key.
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Outdated suggestions cannot be applied.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.
Test 10
Replicated from ai-code-review-evaluation/grafana-cursor#10
Note
Centralizes ResourceServer initialization (init at construction, reordered startup), improves search index tracing/logging and Bleve cache locking, and skips a flaky Postgres test.
serverduring construction (NewResourceServer) and remove per-requestInitcalls across CRUD, List, Watch, Search, History, Origin, Health, and Blob methods.searchSupport.initandbuild; add startup log withduration_secsandtotal_docs.s.log.Warn.GetResourceStatsspan.Written by Cursor Bugbot for commit d762a96. Configure here.