feiniaofeiafei opened a new pull request, #65799: URL: https://github.com/apache/doris/pull/65799
- Adjust the “large join” threshold by increasing the build-side row-count limit from 400K to 1M. - Allow aggregation to continue pushing down to the current join branch when the opposite subtree is large or outputs String/Character types, so that data participating in the join can be reduced earlier. - Tighten aggregation benefit evaluation: treat Group By keys with NDV > rowCount / 10 as having extremely low aggregation benefit; for multi-column Group By, skip aggregation pushdown if any key falls into this category, avoiding low-benefit pushdown caused by high cardinality. - Propagate a “bottom small broadcast join” marker in the pushdown context and apply stricter checks on the probe side: reject pushdown when Group By column statistics are unknown, or when any Group By key is estimated to reduce rows by less than 1000×. - Extend aggregation pushdown traversal to support passing through LogicalAggregate and LogicalIntersect nodes. -- 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]
