Github user chenghao-intel commented on the pull request:
https://github.com/apache/spark/pull/6790#issuecomment-150103961
Actually @marmbrus and I have a discussion on this long time ago, the
conclusion was we'd better to consider the worst case, to avoid the OOM, the
default `0.2` probably is too aggressive, though it works perfect for most of
the cases.
See https://github.com/apache/spark/pull/4199
And for now, I think we probably will have better solution for the
cost-based optimization in https://issues.apache.org/jira/browse/SPARK-9850
finished.
So I suggest to close this PR.
---
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]
