ctsk commented on PR #14234:
URL: https://github.com/apache/datafusion/pull/14234#issuecomment-2614112816
I plan to test this again with a larger TPCH scale factor, and compare
collectLeft (parallel hashing) vs collectLeft (main branch) vs repartition joins
- On SF=1, collectLeft already outperforms repartition joins on most
queries
- another improvement to this PR could be to accumulate hashes in 1
buffer per stream instead of 1 buffer per recordbatch
--
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]
