Skip to content

Add projection to HashJoinExec to avoid unecessary output creation #6768

@Dandandan

Description

@Dandandan

Is your feature request related to a problem or challenge?

Currently HashJoinExec returns all the columns from both sides of the join.

We can add the necessary output columns so we can save some work in gathering values (take) from batches based on matching indices.

This is similar to #5436

Describe the solution you'd like

Add projection to hashjoinexec, use it to reduce output.

Describe alternatives you've considered

No response

Additional context

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or requestperformanceMake DataFusion faster

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions