feat: optimize one segmented vector segment per run#6402
Merged
Conversation
Xuanwo
force-pushed
the
xuanwo/segmented-vector-index-optimize
branch
from
745d07f to
5001720
Compare
BubbleCal
reviewed
Apr 3, 2026
rust/lance/src/index/vector/ivf.rs
Outdated
| let split_candidate = | ||
| (max_partition_size > split_threshold).then(|| SegmentRebalanceCandidate { | ||
| segment_id: metadata.uuid, | ||
| score: max_partition_size - split_threshold, |
Contributor
There was a problem hiding this comment.
maybe use the number of partitions which are over split_threshold as the score?
rust/lance/src/index/vector/ivf.rs
Outdated
| (num_partitions > 1 && min_partition_size < join_threshold).then(|| { | ||
| SegmentRebalanceCandidate { | ||
| segment_id: metadata.uuid, | ||
| score: join_threshold - min_partition_size, |
Xuanwo
force-pushed
the
xuanwo/segmented-vector-index-optimize
branch
from
5001720 to
a1824b2
Compare
BubbleCal
reviewed
Apr 3, 2026
BubbleCal
approved these changes
Apr 3, 2026
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This changes segmented vector index optimize so the default rebalance path keeps segment boundaries and rewrites only the single worst segment in each run. It builds on #6400's logical vector index / IVF view work and avoids the current behavior where segmented optimize treats the logical index as one physical index.
I also added a regression test that creates a skewed two-segment IVF index and verifies that optimize replaces only the oversized segment while leaving the other segment untouched.