Allocation pool the chunked iters in InstanceEnv
#2038
Merged
Conversation
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
coolreader18
approved these changes
Dec 9, 2024
Collaborator
coolreader18
left a comment
coolreader18
left a comment
There was a problem hiding this comment.
LGTM. Do you know if we have any tests that actually exercise the chunk.len() > ROW_ITER_CHUNK_SIZE codepath? That feels like it'd be good to have if not especially as this gets optimized more.
Contributor
Author
No sorry, I can neither confirm nor deny the existence of such tests. 😊 |
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Outdated suggestions cannot be applied.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.
Description of Changes
This adds a
ChunkPoolwhichChunkedWriteruses.Also removes some dead code in
InstanceEnv.Based on flame graphs and timings, I'm not sure this changes much :/We might want to try a different approach that doesn't do any chunking at all but rather writes to a singe buffer that we pool.
We can then keep an offset when iterating instead. Not sure how this will work with row boundaries though.
I measured things again for
.iter(), and in this case, it seems like the time spent indatastore_table_scan_bsatndecreased by a few %. Not a huge amount, but still an improvement. The index scan bit not improving makes sense -- there's a unique index there and only a single element is fetched.Fixes #2020.