Github user cloud-fan commented on the issue:
https://github.com/apache/spark/pull/16985
Sorry for the delay, pretty busy this month...
So a summary of this patch: order does matter for hash partitioning keys,
but doesn't matter for join keys. So we can reorder the join keys to match the
child hash partitioning to avoid shuffle.
My last concern is
https://github.com/apache/spark/pull/16985#discussion_r116176419 . Ideally it
is a valid I think, but we may have some problems in the implementation. Can we
investigate it?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
