GitHub user marmbrus opened a pull request:
https://github.com/apache/spark/pull/7213
[SPARK-5707][SQL] Avoid codegen for HashedRelation keys
Using codegen causes serialized code generated row types to leak out of the
JVM when doing broadcast joins. This PR changes it so we always use generic
rows for hashtables.
TODO:
- [ ] tests
- [ ] perf numbers
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/marmbrus/spark codeGenKeys
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/7213.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 #7213
----
commit fb463925f5fc4917979efe84fadbdfe393e71053
Author: Michael Armbrust <[email protected]>
Date: 2015-07-03T19:02:12Z
[SPARK-5707][SQL] Avoid codegen for HashedRelation keys
----
---
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]
