Remove FilterExec from CoalesceBatches optimization rule, add fetch support #18630
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
github-actions
bot
added
optimizer
Contributor
|
🤖 |
Contributor
|
🤖: Benchmark completed Details
|
Contributor
|
🤖 |
Contributor
|
🤖: Benchmark completed Details
|
Contributor
Author
|
Looks like performance (as expected) is roughly the same. |
martin-g
reviewed
Nov 12, 2025
53 tasks
…row-datafusion into remove_coalesce_batches_exec
Dandandan
changed the title
alamb
approved these changes
Nov 13, 2025
Contributor
alamb
left a comment
alamb
left a comment
There was a problem hiding this comment.
Thank you @Dandandan -- these plans are so much nicer to read
I feel there may be some follow ons. I can file some tickets if you agree
- Somehow standardize on LimitedBatchCoalescer
- Support
LimitedBatchCoalescer::push_batch_with_filter - Apply this same pattern to
HashJoinExecandRepartitionExecand then removeCoalesceBatchesentirely 🤔
|
|
||
| self.batch_coalescer.push_batch_with_filter(batch.clone(), filter_array)?; | ||
| Ok(()) | ||
| // TODO: support push_batch_with_filter in LimitedBatchCoalescer |
Contributor
There was a problem hiding this comment.
this is a good todo -- it would be good to file as a follow on ticket / PR perhaps
I can do it if you like
Contributor
Author
There was a problem hiding this comment.
Thanks, that would be nice
| // The goal here is to detect operators that could produce small batches and only | ||
| // wrap those ones with a CoalesceBatchesExec operator. An alternate approach here | ||
| // would be to build the coalescing logic directly into the operators | ||
| // See https://github.com/apache/datafusion/issues/139 |
Contributor
There was a problem hiding this comment.
This comment could probably be removed now (the ticket is long since closed)
| // See https://github.com/apache/datafusion/issues/139 | ||
| let wrap_in_coalesce = plan_any.downcast_ref::<FilterExec>().is_some() | ||
| || plan_any.downcast_ref::<HashJoinExec>().is_some() | ||
| let wrap_in_coalesce = plan_any.downcast_ref::<HashJoinExec>().is_some() |
Contributor
There was a problem hiding this comment.
It looks like we only have HashJoinExec and RepartitionExec to update before we could remove CoalesceBatches entirely 🤔
Contributor
Author
There was a problem hiding this comment.
Yes - I tried to apply this optimization to RepartitionExec but unfortunately got some regressions (my feeling is due to some decreased parallelism / work distribution).
HashJoinExec would be a great candidate as it might be possible to avoid the take followed by concat which might speed up things.
Contributor
|
Thank you for the review @geoffreyclaude and @martin-g |
jizezhang
pushed a commit
to jizezhang/datafusion
that referenced
this pull request
Nov 15, 2025
…upport (apache#18630) 0## Which issue does this PR close? <!-- We generally require a GitHub issue to be filed for all bug fixes and enhancements and this helps us generate change logs for our releases. You can link an issue to this PR using the GitHub syntax. For example `Closes apache#123` indicates that this PR will close issue apache#123. --> - Closes apache#18646 ## Rationale for this change Cleans up the plan by removing `CoalesceBatchesExec`. I do not expect any performance improvement. <!-- Why are you proposing this change? If this is already explained clearly in the issue then this section is not needed. Explaining clearly why changes are proposed helps reviewers understand your changes and offer better suggestions for fixes. --> Making plans better to read and avoid useless `CoalesceBatchesExec` Also adds back fetch support by adding it to FilterExec ## What changes are included in this PR? <!-- There is no need to duplicate the description in the issue here but it is sometimes worth providing a summary of the individual changes in this PR. --> ## Are these changes tested? <!-- We typically require tests for all PRs in order to: 1. Prevent the code from being accidentally broken by subsequent changes 2. Serve as another way to document the expected behavior of the code If tests are not included in your PR, please explain why (for example, are they covered by existing tests)? --> ## Are there any user-facing changes? <!-- If there are user-facing changes then we may require documentation to be updated before approving the PR. --> <!-- If there are any breaking changes to public APIs, please add the `api change` label. -->
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
0## Which issue does this PR close?
Rationale for this change
Cleans up the plan by removing
CoalesceBatchesExec. I do not expect any performance improvement.Making plans better to read and avoid useless
CoalesceBatchesExecAlso adds back fetch support by adding it to FilterExec
What changes are included in this PR?
Are these changes tested?
Are there any user-facing changes?