Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Plan joins with PartitionMode::Auto by default #15349

Open
Dandandan opened this issue Mar 21, 2025 · 0 comments · May be fixed by #15339
Open

Plan joins with PartitionMode::Auto by default #15349

Dandandan opened this issue Mar 21, 2025 · 0 comments · May be fixed by #15339
Labels
enhancement New feature or request performance Make DataFusion faster

Comments

@Dandandan
Copy link
Contributor

Dandandan commented Mar 21, 2025 •
edited
Loading

Is your feature request related to a problem or challenge?

Currently PartitionMode::Partitioned is the default when statistics collection is not used.
This lead to suboptimal plans whenever CollectLeft could be used based on file or plan-derived (e.g. limit 10)) statistics.

Describe the solution you'd like

Use PartitionMode::Auto and let optimizer figure out if statistics can be used.

Describe alternatives you've considered

No response

Additional context

No response
@Dandandan Dandandan added enhancement New feature or request performance Make DataFusion faster labels Mar 21, 2025
@Dandandan Dandandan changed the title Plan joins with PartitionMode::Auto by default Plan joins with PartitionMode::Auto by default Mar 21, 2025
@Dandandan Dandandan linked a pull request Mar 21, 2025 that will close this issue
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request performance Make DataFusion faster
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Always use PartitionMode::Auto in planner Dandandan/arrow-datafusion
1 participant
@Dandandan