Dandandan commented on PR #15380: URL: https://github.com/apache/datafusion/pull/15380#issuecomment-2808612984
I wonder if we can make a more "simple" change for now: * `concat` regresses because it copies the _all columns_ of the recordbatch before sorting. * We can concat the sorting columns instead + generate a Vec of `(batch_id, row_id)` and map output of `lexsort_to_indices` back to the original values. Doing this I think will benefit existing sorting without (too much) regressions. we probably try increase the in memory threshold value (`sort_in_place_threshold_bytes`). -- 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: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
