mbutrovich commented on issue #17494: URL: https://github.com/apache/datafusion/issues/17494#issuecomment-6235144968
I documented this regression and my analysis on Comet: https://github.com/apache/datafusion-comet/issues/4614. Basically the plan ends up with a sequence of 8 hash joins, and because we can't fuse them the way Spark does, we end up materializing Arrow batches and re-evaluating a huge chain of joins. In Comet's case, we'd be better off falling back. -- 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]
