vinycalves commented on issue #22758: URL: https://github.com/apache/datafusion/issues/22758#issuecomment-6826342144
I'd like to work on the hash aggregation sliced-batch memory overcount (#22526) under this EPIC. I'll start with a reproducer that shows the downstream reservation charging the whole parent batch, then compare emitting fixed-size batches with accounting only the used slice or distinct buffers, and benchmark the spill impact. -- 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]
