Skip per-row filter evaluation when all row groups are fully matched#21372
Closed
Dandandan wants to merge 1 commit intoapache:mainfrom
Closed
Skip per-row filter evaluation when all row groups are fully matched#21372Dandandan wants to merge 1 commit intoapache:mainfrom
Dandandan wants to merge 1 commit intoapache:mainfrom
Conversation
When statistics prove that every remaining row group fully satisfies the filter predicate, skip attaching the row filter to the Parquet decoder entirely. This avoids unnecessary per-row filter evaluation for queries like `WHERE col <> 0` or `WHERE col <> ''` when min/max statistics show the filter is trivially true for all row groups. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Contributor
Author
|
run benchmarks |
|
🤖 Benchmark running (GKE) | trigger CPU Details (lscpu)Comparing skip-filter-fully-matched (ebe07a1) to c17c87c (merge-base) diff using: clickbench_partitioned File an issue against this benchmark runner |
|
🤖 Benchmark running (GKE) | trigger CPU Details (lscpu)Comparing skip-filter-fully-matched (ebe07a1) to c17c87c (merge-base) diff using: tpch File an issue against this benchmark runner |
|
🤖 Benchmark running (GKE) | trigger CPU Details (lscpu)Comparing skip-filter-fully-matched (ebe07a1) to c17c87c (merge-base) diff using: tpcds File an issue against this benchmark runner |
|
🤖 Benchmark completed (GKE) | trigger Instance: CPU Details (lscpu)Details
Resource Usagetpcds — base (merge-base)
tpcds — branch
File an issue against this benchmark runner |
|
🤖 Benchmark completed (GKE) | trigger Instance: CPU Details (lscpu)Details
Resource Usageclickbench_partitioned — base (merge-base)
clickbench_partitioned — branch
File an issue against this benchmark runner |
Contributor
Author
|
run benchmarks |
|
🤖 Benchmark running (GKE) | trigger CPU Details (lscpu)Comparing skip-filter-fully-matched (ebe07a1) to c17c87c (merge-base) diff using: clickbench_partitioned File an issue against this benchmark runner |
|
🤖 Benchmark running (GKE) | trigger CPU Details (lscpu)Comparing skip-filter-fully-matched (ebe07a1) to c17c87c (merge-base) diff using: tpch File an issue against this benchmark runner |
3 tasks
Member
|
Hey @Dandandan , I think the changs should be mainly in arrow-rs repo, I did some work before xudong963/arrow-rs@eaf4ab1 |
|
🤖 Benchmark running (GKE) | trigger CPU Details (lscpu)Comparing skip-filter-fully-matched (ebe07a1) to c17c87c (merge-base) diff using: tpcds File an issue against this benchmark runner |
Contributor
Author
Ah yes, I realize we could also do that at arrow-rs side! |
Member
yes, I'll make a PR recently |
|
🤖 Benchmark completed (GKE) | trigger Instance: CPU Details (lscpu)Details
Resource Usageclickbench_partitioned — base (merge-base)
clickbench_partitioned — branch
File an issue against this benchmark runner |
|
🤖 Benchmark completed (GKE) | trigger Instance: CPU Details (lscpu)Details
Resource Usagetpcds — base (merge-base)
tpcds — branch
File an issue against this benchmark runner |
Contributor
|
This makes a lot of sense to me. We have a hacky version of this internally, it's especially effective for filters/queries like `ts > '2026-04-05T00:15:00Z' where many files will have all rows match. Can't we do this at the file level right now in DataFusion (in fact I think we do) and once the morsels API is across the line at the row group level without any changes in arrow-rs? |
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
4 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.
Which issue does this PR close?
N/A - Performance optimization
Rationale for this change
What changes are included in this PR?
After all row group pruning (statistics, bloom filters, limit), check if every remaining row group is fully matched by the predicate. If so, drop the per-row filter from the Parquet decoder builder entirely.
Are these changes tested?
Existing parquet integration tests pass (198 tests). The optimization is transparent — it produces the same results, just avoids redundant filter evaluation.
Are there any user-facing changes?
No. This is a performance optimization that skips unnecessary work. Query results are unchanged.
🤖 Generated with Claude Code