Github user lianhuiwang commented on the pull request:
https://github.com/apache/spark/pull/6875#issuecomment-117436199
@davies if we can not hold all of them in memory and then switch to sort
based, it should re-shuffle data to do sort. so its computation cost is very
expensive. i think it is determined by statistics before physical plan
execution. this problem is similar as hash join or sort-merge join. now sort
merge join is determined by spark.sql.planner.sortMergeJoin(default is false).
like sort merge join, sort based aggregation of this PR is also determined by
spark.sql.planner.sortMergeAggregate(default is false).
---
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]
