Repository navigation
Write constant columns as one chunk - #11400
Open
robert3005 wants to merge 2 commits into
Open
robert3005 wants to merge 2 commits into
robert3005 wants to merge 2 commits into
Conversation
The default write strategy splits each column into 8K-row blocks and then into blocks of about 1 MiB of uncompressed data. For a constant column, each block compresses to the same constant, so the splits only add chunks, segments and zone maps. Add ConstantStrategy in front of the per-column repartition. It reads chunks while they all hold the same value. If the stream ends in this state, it writes one ConstantArray with the flat strategy. Otherwise, it gives the stream to the usual pipeline, with the rows read until then first as one ConstantArray. While it reads, it keeps only the most recent sequence ID, so that other columns can continue to write their segments. Part of #3874. Signed-off-by: Robert Kruszewski <github@robertk.io>
robert3005
marked this pull request as ready for review
November 11, 2026 21:40
Merging this PR will improve performance by 10.85%2 warnings
Performance Changes
Tip Curious why performance improved? Comment Comparing 
Footnotes
|
joseph-isaacs
added
the
action/bench-sql
github-actions
Bot
removed
the
action/bench-sql
Contributor
Polar Signals Profiling ResultsLatest Run
Powered by Polar Signals Cloud |
Contributor
Benchmarks: PolarSignals Profiling 📖Commits: PR datafusion / vortex-file-compressed / ns (0.943x ➖, 2↑ 0↓)
|
Contributor
Benchmarks: FineWeb NVMe 📖Commits: PR How to read Verdict and Engines
datafusion / vortex-file-compressed / ns (0.944x ➖, 1↑ 0↓)
datafusion / parquet / ns (1.003x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed / ns (0.986x ➖, 0↑ 0↓)
duckdb / parquet / ns (0.989x ➖, 0↑ 0↓)
|
Contributor
Benchmarks: TPC-H SF=1 on NVME 📖Commits: PR How to read Verdict and Engines
datafusion / vortex-file-compressed / ns (0.998x ➖, 0↑ 0↓)
datafusion / parquet / ns (0.999x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed / ns (1.000x ➖, 0↑ 1↓)
duckdb / parquet / ns (1.000x ➖, 0↑ 0↓)
|
Contributor
Benchmarks: TPC-H SF=10 on NVME 📖Commits: PR How to read Verdict and Engines
datafusion / vortex-file-compressed / ns (0.993x ➖, 0↑ 0↓)
datafusion / parquet / ns (0.997x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed / ns (0.997x ➖, 0↑ 0↓)
duckdb / parquet / ns (0.997x ➖, 0↑ 0↓)
|
Contributor
Benchmarks: TPC-DS SF=1 on NVME 📖Commits: PR How to read Verdict and Engines
datafusion / vortex-file-compressed / ns (0.993x ➖, 0↑ 0↓)
datafusion / parquet / ns (0.995x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed / ns (0.994x ➖, 1↑ 0↓)
duckdb / parquet / ns (0.988x ➖, 1↑ 0↓)
|
Contributor
Benchmarks: Clickbench on NVME 📖Commits: PR How to read Verdict and Engines
datafusion / vortex-file-compressed / ns (0.995x ➖, 1↑ 0↓)
datafusion / parquet / ns (0.996x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed / ns (1.009x ➖, 0↑ 0↓)
duckdb / parquet / ns (1.014x ➖, 0↑ 1↓)
|
Contributor
Benchmarks: TPC-H SF=1 on S3 📖Commits: PR How to read Verdict and Engines
datafusion / vortex-file-compressed / ns (1.186x ➖, 0↑ 6↓)
datafusion / parquet / ns (0.963x ➖, 2↑ 0↓)
duckdb / vortex-file-compressed / ns (0.988x ➖, 1↑ 1↓)
duckdb / parquet / ns (0.993x ➖, 1↑ 0↓)
|
Contributor
Benchmarks: TPC-DS SF=10 on NVME 📖Commits: PR How to read Verdict and Engines
datafusion / vortex-file-compressed / ns (0.996x ➖, 0↑ 0↓)
datafusion / parquet / ns (1.001x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed / ns (1.005x ➖, 1↑ 0↓)
duckdb / parquet / ns (1.006x ➖, 0↑ 0↓)
|
This branch has not been deployed
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
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.
fixes #3874.
The default write strategy splits each column into 8K-row blocks, then into blocks of about 1 MiB of uncompressed data. For a constant column, each block compresses to the same
ConstantArray. The splits only add chunks, segments and a zone map that have no use.Change
ConstantStrategy(vortex-layout/src/layouts/constant.rs). It reads chunks while they all hold the same value:ConstantArraywith the flat strategy. There is no repartition, no zone map and no chunked layout.ConstantArray. The run stores only a scalar and a length, so nothing is materialized.UnionandVariantcolumns skip detection, becauseis_constantcannot examine them.WriteStrategyBuilder::buildputsConstantStrategyin front of the per-column repartition. It writes constant columns with the configured flat strategy, sowith_flat_strategystill applies.