Return orphaned catchup ranges to the front of the queue - #420
Draft
sisuresh wants to merge 1 commit into
Draft
Conversation
A worker that dies mid-catchup (OOMKill, eviction, node loss) leaves its range in the in_progress queue with nobody working on it. Recovery only fired when every worker in the fleet was unreachable, so a single orphan waited for all other ranges to finish before being retried. A worker now records the range it claims against its own pod name, and on startup hands back whatever its previous incarnation was holding. A range orphaned too many times is failed rather than retried forever. Fixes stellar#409.
sisuresh
force-pushed
the
sidd/parallel-catchup-lease-reaper
branch
from
August 1, 2026 00:25
1ab7e37 to
5b21b2f
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A worker now records the range it claims against its own pod name, and on startup hands back whatever its previous incarnation was holding — straight to the front of the job queue. Previously a range whose worker died stayed in
in_progressuntil every other range had finished and the monitor saw the whole fleet idle, so one orphan serialized the tail.Ranges orphaned more than
recovery.max_attemptstimes are failed instead of retried, since recovering promptly makes #334 easier to hit.Fixes #409.