Github user StephanEwen commented on the pull request:
https://github.com/apache/flink/pull/370#issuecomment-74236667
The chained reducer variant makes more sense. The question is, what is
cheaper - serialized exchange through the in-mem-channel, or the copying. My
gut feeling is that the copy is a bit better, so it may be worth 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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
