Do not sort rows in FirstValueAccumulator
#14402
Open
+66
−58
Conversation
This file contains 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
github-actions
bot
added
core
|
blaginin
commented
Feb 1, 2025
Comment on lines
-641
to
+618
| let indices = lexsort_to_indices(&sort_cols, None)?; | ||
| take_arrays(&filtered_states, &indices, None)? | ||
| }; | ||
| let comparator = LexicographicalComparator::try_new(&sort_columns)?; |
There was a problem hiding this comment.
In lexsort_to_indices there are some additional optimizations when there's just one column - so I also wrote a version which reuses lexsort_to_indices - but the speed increase there is actually 20% smaller than here
blaginin
commented
Feb 1, 2025
| @@ -3003,7 +3003,7 @@ SELECT FIRST_VALUE(amount ORDER BY ts ASC) AS fv1, | |||
| LAST_VALUE(amount ORDER BY ts ASC) AS fv2 | |||
| FROM sales_global | |||
| ---- | |||
| 30 100 | |||
| 30 80 | |||
There was a problem hiding this comment.
IMO, it actually makes more sense because that line has the same ORDER BY value but appears last in the table.
|
fyi @jayzhan211 |
jayzhan211
reviewed
Feb 2, 2025
| } | ||
| let comparator = LexicographicalComparator::try_new(&sort_columns)?; | ||
| let best = (0..value.len()) | ||
| .filter(|&index| !(self.ignore_nulls && value.is_null(index))) |
There was a problem hiding this comment.
If we make 'ignore nulls' a constant generic, it might be faster than we can avoid filter logic for null if we don't ignore nulls
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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?
Closes #14215
Rationale for this change
Right now, merging / updating batches in
first_value/last_valuewe sometimes sort input to find just one max / min row. In some cases, we request to sort only top-1 value but even that produces extra index buffers...What changes are included in this PR?
Instead of sorting arrays, just finding min / max directly.
Are these changes tested?
Yes, by
aggregate.slt. Also added new benches to illustrate the speed improvementAre there any user-facing changes?
No