Conversation
github-actions
Bot
added
documentation
|
Thank you for opening this pull request! Reviewer note: cargo-semver-checks reported the current version number is not SemVer-compatible with the changes in this pull request (compared against the base branch). Details |
peterxcli
added this pull request to stack #6
September 15, 2026 18:44
This was referenced Sep 15, 2026
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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?
Related to apache#24393. Stage 1 of the Parquet I/O stack, split from #3.
Stack, with each PR targeting its predecessor: #4 → #5 → #7 → #8 → #9.
Rationale for this change
Filter pushdown currently requires dependent reads for predicate and output columns. Allow callers to fetch those pages together while retaining filter evaluation and page-index pruning.
What changes are included in this PR?
Add
datafusion.execution.parquet.progressive_ioandParquetSource::with_progressive_io. Setting it tofalsecombines the selected output and predicate ranges. Preserve dictionary pages, reversed selections, and fully matched row-group suppression; changing dynamic filters cannot establish a permanent full match. Serialized plans retain the policy, and older plans default to progressive I/O.Background prefetch is added by the next PR.
What is the testing strategy for this PR?
On
lsa-cupid1: workspace Clippy with all targets/features; 259 Parquet tests with encryption; SQL coverage for indexed/unindexed files, nested/dictionary output, and predicate-only columns; dynamic-filter safety and older-plan serialization regressions. Formatting and documentation checks pass.Full partitioned ClickBench on
lsa-cupid1,/work/peterxcliNVMe: 100 files, 99,997,497 rows, all 43 queries, eight workers/partitions. Versus the immediate parent, the sum of query medians changes +0.97% / +0.49% warm and -0.20% with evicted files (negative is faster). Warm values are two reversed-order passes; evicted files use three runs per query.Retain this as an opt-in policy; the default stays progressive. Results and methodology · 43 per-query comparisons and CPU charts. Result-ordering limitations and synthetic-latency controls are documented in the report.
Are there any user-facing changes?
Set
datafusion.execution.parquet.progressive_io=falsebefore registering the table to request upfront reads. The default staystrue; upfront reads can fetch pages that subsequent row filtering would skip.