perf: Disable morsel splitting for fast-count on streaming engine #26245
+343
−42
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Outdated suggestions cannot be applied.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.
Streaming queries that collect to an in-memory DataFrame and consist only of column projections (and
pl.len()) will now disable morsel splitting at supported sources.E.g -
scan_parquet().collect()scan_parquet().select(pl.len()).collect()scan_parquet().select("<column>", "column", ..).collect()Equivalently when starting from
InMemorySource-LazyFrame().collect()LazyFrame().select(pl.len()).collect()LazyFrame().select("<column>", "column", ..).collect()Benchmark
Description:
scan_parquet().select(pl.len()).collect()File: 4B rows x 0 columns
Before this PR the parquet source would split to morsels of 100k rows (sending ~42,949 morsels). It now sends only a single morsel.
Test script