andygrove commented on PR #1615: URL: https://github.com/apache/datafusion-ballista/pull/1615#issuecomment-4338982157
The performance benefits in this PR are: 1. make it cheaper to combine the spill files into the final file - file copy rather than re-encode 2. allow the use of `IO_BLOCK_TRANSPORT` with sort-based shuffle The standalone benchmark only measures the first item. I did not see a significant performance improvement with local tests. The numbers were about the same. -- 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]
