You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@beam.apache.org by "Aviem Zur (JIRA)" <ji...@apache.org> on 2017/03/04 13:47:45 UTC

[jira] [Created] (BEAM-1623) Transform Reshuffle directly in Spark runner

Aviem Zur created BEAM-1623:
-------------------------------

             Summary: Transform Reshuffle directly in Spark runner
                 Key: BEAM-1623
                 URL: https://issues.apache.org/jira/browse/BEAM-1623
             Project: Beam
          Issue Type: Improvement
          Components: runner-spark
            Reporter: Aviem Zur
            Assignee: Amit Sela


Transform {{Reshuffle}} directly in Spark runner.
Spark's {{repartition}} is logically equivalent to {{Reshuffle}} and will cause the required fusion break without incurring the overhead of {{groupByKey}} (In streaming pipelines this will use {{updateStateByKey}}) compared to a simple {{repartition}}.



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)