-
Notifications
You must be signed in to change notification settings - Fork 25
Add timeout to Grype DB update with graceful fallback to prevent indefinite readiness probe failures #320
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.
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
Merged
Merged
Add timeout to Grype DB update with graceful fallback to prevent indefinite readiness probe failures #320
Changes from all commits
Commits
Show all changes
5 commits
Select commit
Hold shift + click to select a range
9be0f58
Initial plan
Copilot d0a087c
Add context timeout to Grype DB update to prevent stuck updates
Copilot ab6534c
Address code review comments: add comments and use consistent exit code
Copilot d291b49
Increase timeout to 15min and prevent crashloop by keeping existing D…
Copilot adec623
Add dbVersionLocked helper and use it
matthyx File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
Oops, something went wrong.
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Outdated suggestions cannot be applied.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.
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Deadlock:
g.DBVersion(ctx)acquires read lock while write lock is held.At line 183,
g.DBVersion(ctx)is called whileg.mu.Lock()is already held (acquired at line 130). TheDBVersionmethod (lines 112-118) attempts to acquireg.mu.RLock(), which will deadlock since Go'ssync.RWMutexdoes not support re-entrant locking.🔧 Proposed fix: access dbStatus directly without calling DBVersion
case <-updateCtx.Done(): if hasExistingDB { // We have an existing DB, keep using it instead of crashing // This prevents crashloop in case of slow but functional network + parts := strings.Split(g.dbStatus.From, "%3A") + existingVersion := parts[len(parts)-1] logger.L().Ctx(ctx).Warning("grype DB update timed out after 15 minutes, continuing with existing DB", - helpers.String("existingDBVersion", g.DBVersion(ctx))) + helpers.String("existingDBVersion", existingVersion)) // Update lastDbUpdate to prevent immediate retry, will retry in next 24h cycle g.lastDbUpdate = now return trueAlternatively, create an internal helper that doesn't acquire the lock:
🤖 Prompt for AI Agents
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@copilot can you check?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.