Deadlock Patch - #551
Merged
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Golden/hibernate snapshots capture the rootfs fsfrozen; the wake path thawed it by exec'ing
fsfreezefrom that frozen rootfs — a deadlock (exec needs fs, fs needs thaw) that intermittently hangs every post-restore RPC into a 524 (what #548 backstops). Replaces the exec thaw with a native Thaw RPC issuing FITHAW on an O_RDONLY|O_NOATIME fd: no exec, no write to the frozen fs. Falls back to exec for pre-Thaw agents. Reverts a debug log flag. Validated on dev (stall released in 5ms).the bugs impact is a small, intermittent subset — not every wake. The deadlock only closes when the thaw's exec happens to hit a write-lock on the frozen rootfs (atime/timing dependent); usually it squeaks through and wakes complete normally, so only a rare tail 524s. The fix is a net gain: native FITHAW thaws without exec or a write to the frozen fs, removing the hazard entirely, with no change to the healthy path, no wire break, and an exec fallback for old agents during rollout.