Uh oh!
There was an error while loading. Please reload this page.
bench: multi-conjunct shared-prefix struct row-filter pushdown - #23524
Merged
adriangb merged 4 commits intoAug 6, 2026
Conversation
kumarUjjawal
commented
Aug 3, 2026
Contributor
Hi @SubhamSinghal I will take a look. Can you please resolve the conflict. |
SubhamSinghal
commented
Aug 3, 2026
ContributorAuthor
resolved merge conflict |
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@## main #23524 +/- ##
==========================================
+ Coverage 80.87% 80.91% +0.03%
==========================================
Files 1101 1102 +1 Lines 375765 377102 +1337 Branches 375765 377102 +1337 ==========================================
+ Hits 303915 305123 +1208 - Misses 53747 53786 +39 - Partials 18103 18193 +90 ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
Uh oh!
There was an error while loading. Please reload this page.
kumarUjjawal
approved these changes
Aug 5, 2026
kumarUjjawal
left a comment
Contributor
There was a problem hiding this comment.
Thank you @SubhamSinghal
This looks good
Uh oh!
There was an error while loading. Please reload this page.
kosiew pushed a commit
to kosiew/datafusion
that referenced
this pull request
Aug 12, 2026
…e#23524) ## Which issue does this PR close? - Follow-up to review feedback on apache#23217. ## Rationale for this change The row-filter planner in `datafusion-datasource-parquet` walks the accessed struct-field paths for every filter, resolves the Parquet leaves, and builds a pruned Arrow schema. When multiple predicates share a common struct prefix, the planner can consolidate that traversal work — this is the case the `StructAccessTree` refactor in apache#23217 is intended to accelerate. The existing bench suite does not cover this shape: - `parquet_struct_query` — single-field struct predicates only (`WHERE s['id'] = 5`). - `parquet_struct_projection` — projection-only, no `WHERE` clause. So multi-conjunct shared-prefix planning is currently uninstrumented, and the effect of consolidating access-path traversals is invisible against the existing suite. ## What changes are included in this PR? ## Are these changes tested? ## Are there any user-facing changes? No. Benchmark-only; no library or API surface is touched.
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 freeto 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?
Rationale for this change
The row-filter planner in
datafusion-datasource-parquetwalks the accessed struct-field paths for every filter, resolves the Parquet leaves, and builds a pruned Arrow schema. When multiple predicates share a common struct prefix, the planner can consolidate that traversal work — this is the case theStructAccessTreerefactor in #23217 is intended to accelerate.The existing bench suite does not cover this shape:
parquet_struct_query— single-field struct predicates only(
WHERE s['id'] = 5).parquet_struct_projection— projection-only, noWHEREclause.So multi-conjunct shared-prefix planning is currently uninstrumented, and the effect of consolidating access-path traversals is invisible against the existing suite.
What changes are included in this PR?
Are these changes tested?
Are there any user-facing changes?
No. Benchmark-only; no library or API surface is touched.