[GitHub] flink pull request: [FLINK-3336] Add Rescale Data Shipping for Dat...

[aljoscha <gi...@git.apache.org>]

Github user aljoscha commented on the pull request:

    https://github.com/apache/flink/pull/1589#issuecomment-180284761
  
    I addressed @uce's comments, thanks for those. I also had a discussion with @StephanEwen and he came up with the name `rescale()` for this distribution pattern. The reasoning is that you basically increase or decrease/increase the parallelism of downstream operations by some factor x and elements from the upstream operation will be sent only to x downstream operations to which no other upstream operation sends elements. It should be clear from the picture what I mean by that exactly. We have a source with parallelism 3, then a map with parallelism 9 and then the sink has parallelism 3 again.
    <img width="1986" alt="screen shot 2016-02-05 at 11 18 16" src="https://cloud.githubusercontent.com/assets/68551/12843516/3d509ab6-cbfa-11e5-850d-d4cd25f08de5.png">
      


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---