quickwit-oss/tantivy

About 15% regression on string sorts

Open

#2776 opened on Dec 15, 2025

View on GitHub
 (12 comments) (0 reactions) (0 assignees)Rust (8,354 stars) (499 forks)batch import
good first issue

Description

Post https://github.com/quickwit-oss/tantivy/pull/2726, there is about a 15% regression on string sorts.

I have not had time to triage this yet, but I strongly suspect that it is due to impl SortKeyComputer for SortByString doing individual lookups to the column's dictionary per term: https://github.com/quickwit-oss/tantivy/blob/d0e16001357b0238645d2e09db59e913b09fee07/src/collector/sort_key/sort_by_string.rs#L62-L72

When ordering by strings, the resulting values will be sequential in the column's dictionary. Because the dictionary is compressed, each of these lookups will decompress a block of the term dictionary, and since the values are potentially contiguous in the dictionary, this can mean that we decompress the same block multiple times.

Previously on main, this used sorted_ords_to_term_cb to batch convert the TermOrdinals into terms. One way to get this performance back would be to change SegmentSortKeyComputer::convert_segment_sort_key into a batch method.

Contributor guide

Tech stack
rust
Domain
performance
Issue type
performance
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Rust programming languageFamiliarity with tantivy's sort code
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50
Research direction
Investigate the regression caused by PR #2726. The issue suggests that `SortByString` does individual lookups to the column's dictionary per term, causing repeated decompression of blocks. The prior approach used `sorted ords to term cb` for batching. To recover performance, modify `SegmentSortKeyComputer::convert segment sort key` into a batch method. Key files: `src/collector/sort key/sort by string.rs` (lines 62-72) and `src/collector/top score collector.rs` (lines 192-243). Review the existing implementation and design a batching approach similar to the previous one.