zhuqi-lucas commented on PR #21182: URL: https://github.com/apache/datafusion/pull/21182#issuecomment-4143464401
Thanks for the review @adriangb! I've addressed all feedback: - **Benchmark split**: Removed benchmark code from this PR, will submit as a follow-up PR - **"Unsupported if already in order"**: Clarified the comment — expanded to explain that `Unsupported` means no change was made to the plan (files were already in the correct order, nothing to optimize) - **Row-group-level stats reordering**: Great idea for a follow-up — same concept as file-level reordering but at finer granularity, especially powerful with morselized scans - **Lopsided partitions**: Minimal impact in practice since file count >> partition count, imbalance is at most 1 extra file Also rebased onto latest main. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
