GitHub user chenghao-intel opened a pull request:
https://github.com/apache/spark/pull/8798
[SPARK-10474][SQL][WIP]Avoid eat out all of the offheap memory by
UnsafeHashAggregation
As https://issues.apache.org/jira/browse/SPARK-10474 shows, before turn to
SortBased Aggregation, the Hash Aggregation probably has eat out all of the
offheap memory, and eventually cause exception when spill the data.
A workaround solution is to control the size of hash aggregation buffer.
And in long term, we should have to provide a mechanism to estimate how much we
have to left for data spill.
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/chenghao-intel/spark hashaggr
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/8798.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #8798
----
commit 0418127d3e1237ca88f99f3202a4032bae3dcd72
Author: Cheng Hao <[email protected]>
Date: 2015-09-17T13:23:24Z
wip
----
---
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]
