jychen7 commented on issue #5969: URL: https://github.com/apache/arrow-datafusion/issues/5969#issuecomment-1507915671
> reg to flamegraph the datafusion::physical_plan::aggregates::row_hash::slice_and_maybe_filter is expensive. it is expensive because excessive vector allocations that makes sense. From my debugging above, I think `SortExec` is not a slow part. Looks like its children's plan like `RepartitionExec` or `AggregateExec` is slow -- 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]
