beam-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Aviem Zur (JIRA)" <>
Subject [jira] [Created] (BEAM-1623) Transform Reshuffle directly in Spark runner
Date Sat, 04 Mar 2017 13:47:45 GMT
Aviem Zur created BEAM-1623:

             Summary: Transform Reshuffle directly in Spark runner
                 Key: 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

View raw message