mirror of
https://github.com/qdrant/qdrant.git
synced 2026-09-21 21:47:39 -05:00
test_recover_from_snapshot_2 and test_upload_snapshot_2 start snapshot recovery on a freshly joined peer as soon as it lists the collection. The collection appears once the creation entry is applied, while the peer is still replaying the rest of the raft log, including the removal of the killed peer. Recovery then decides which other replicas to remove or mark dead from that stale local view and drops a healthy replica, leaving a shard with a single replica. Add a helper that waits until all peers share the same commit index and have no pending operations, and use it in both tests before recovering. Also fix a misleading comment in the recovery replica cleanup branch. Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>