andygrove commented on issue #5198: URL: https://github.com/apache/datafusion-comet/issues/5198#issuecomment-6225794537
Closing in favour of #5905, which now tracks every shuffle performance finding with a status table. The items here map as follows: 1. `process_sorted_row_partition` rebuilding the schema and IPC writer per batch: #7061 (PR #7065). 2. Reader direct buffer reset per block: #7070. 3. `RowPartition` boxing: #7074. 4. Per-partition setup in the bypass writer, and `getPartition` called twice: #7074 and #7061. 5. Index-file parsing: done, offsets now come back over JNI (#5790). -- 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]
