Reuse existing null masks when superimposing struct nulls onto children - #23484
Draft
vuule wants to merge 2 commits into
Draft
Reuse existing null masks when superimposing struct nulls onto children#23484vuule wants to merge 2 commits into
vuule wants to merge 2 commits into
Conversation
The batched superimpose_nulls allocated a new null mask for every column in the struct hierarchy and moved it in, even though every nullable column already owns one of exactly the right size. AND into the existing masks instead, allocating only for columns that have no mask yet.
vuule
added
Performance
2 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
The batched
superimpose_nulls, reached from the Parquet, ORC and Avro readers viaenforce_null_consistency, allocated a new null mask for every column in the struct hierarchy and moved it in, even though every nullable column already owns one of exactly the right size. It now ANDs into the existing masks withinplace_segmented_bitmask_binop, which removes about 192 allocations per read inparquet_read_fixed_width_struct: 3.5-4.2% faster with the pool resource, 4.2-5.6% with async, and 19.5 MiB lower peak memory.Checklist