Repository navigation
fix(snapshot): hold the inode lock from read to write when marking a file shared - #100
Merged
Merged
Conversation
…file shared The mark read the source inode without a lock and wrote it back with only an extent conflict check, so it undid any other change made in between, such as another node's append size, mode or times. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The TODO race (a snapshot sharing a block between an in-place write's refcount check and its data write) is already closed. #42 re-checks under the shared inode lock and holds it until the data lands, and #29/#90 make that lock exclusive across nodes.
TestSnapshotDuringInPlaceWriteAcrossNodescovers it.While checking, I found a nearby gap: the mark wrote back a stale copy of the inode.
TestSnapshotMarkKeepsConcurrentAppendfails 3/3 on agents-base: another node's acknowledged append loses its size.10 instrumented VM snapshot-during-writes runs on .68: 100 snapshots unchanged, 0 double holds.
Not fixed here: two delete jobs for one snapshot can truncate a reused data inode.
🤖 Generated with Claude Code