qdrant

mirror of https://github.com/qdrant/qdrant.git synced 2026-09-29 01:17:56 -05:00

Files

T

History

Andrey VasnetsovandClaude Opus 5 f16b007daa fix(edge): tell manifest skew apart from a real fault when skipping a segment (#10627 )

Every failure to open a segment was reported the same way: one warning,
same wording, segment dropped, shard serves without it. Two very
different things land there.

The manifest is superset-biased, so it may list a segment the leader has
not finalized yet or has already removed. Both arrive as `FileNotFound`,
both fix themselves once the follower catches up, and both are routine.

Anything else is a segment that should have loaded and did not. The shard
opens without it and answers queries over a subset of its data, returning
success to the client. In a recent load test this produced 667 warnings
indistinguishable from ordinary leader churn.

Report the first at debug and the second at error. The manifest does not
need re-reading to tell them apart, so this costs nothing on the open
path.

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-13 16:23:15 +02:00

builders

feat: pin per-shard search pool to a core (#10029 )

2026-07-30 20:41:48 +02:00

config

Expose id tracker memory placement in collection config (#10597 )

2026-09-12 12:28:24 +02:00

edge_shard

Rename ReadOnlyEdgeShard::refresh to live_reload (#10444 )

2026-09-02 17:31:17 +02:00

read_only

fix(edge): tell manifest skew apart from a real fault when skipping a segment (#10627 )