perf: avoid per-row copy in Spark hex byte encoding#23473
Open
andygrove wants to merge 1 commit into
Open
Conversation
Jefffrey
reviewed
Jul 14, 2026
| let mut values: Vec<u8> = Vec::with_capacity(len * 64); | ||
| let mut offsets: Vec<i32> = Vec::with_capacity(len + 1); | ||
| offsets.push(0); | ||
| let mut nulls = NullBufferBuilder::new(len); |
Contributor
There was a problem hiding this comment.
we can probably avoid a null builder by just cloning the input nulls? though i guess need to plumb the functions to pass those through
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Rationale for this change
The Spark
hexfunction's byte-encoding path (hex_encode_bytes) filled a reusable per-rowVecand then copied it into aStringBuilderfor every row. Since each input byte maps to exactly two hex characters, the output can be written once directly into a single value buffer, eliminating the per-row copy.What changes are included in this PR?
Rewrote
hex_encode_bytesto write hex digits directly into one growing value buffer with manually-tracked offsets and aNullBufferBuilder, constructing theStringArrayvianew_unchecked(the buffer contains only ASCII hex digits, so the existing no-validation behavior is preserved). The 256-entry lookup table and all other hex paths are unchanged.Are these changes tested?
Existing tests (
function::math::hex) pass unchanged.Benchmark (
datafusion/spark/benches/hex.rs):Are there any user-facing changes?
No