andygrove commented on issue #5905: URL: https://github.com/apache/datafusion-comet/issues/5905#issuecomment-5870677963
Adding one item from #5002, which I'm closing in favour of this issue. `buffer_partitioned_batch_may_spill` in `native/shuffle/src/partitioners/multi_partition.rs` still pushes the row indices one at a time after `reserve` (lines 508-511). `indices.extend(row_indices.iter().map(|&r| (buffered_partition_idx, r)))` would get the trusted-length specialization. -- 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]
