metesynnada commented on PR #6772: URL: https://github.com/apache/arrow-datafusion/pull/6772#issuecomment-1627292528
> The performance increase depends a bit on how many / what kind of columns are necessary in the output projection. For example, if we can skip `take` on some string arrays then the benefit will be higher than in other cases. Yeah, you are quite right, it will prevent unnecessary `compute::take` s in some cases. Do you also plan to change the `PushDownProjection` rule? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
