Uploaded image for project: 'Flink'
  1. Flink
  2. FLINK-36527

Introduce a parameter to support the autoscaler to adopt a more aggressive strategy when Source or upstream shuffle is keyBy

    XMLWordPrintableJSON

Details

    Description

      In https://issues.apache.org/jira/browse/FLINK-36192
      We have completed the optimization of Souce parallelism determination.

      Task Source or upstream shuffle is keyBy will be adjusted to be a divisor of the number of partitions or the maximum degree of parallelism.
      This Jira hopes to introduce a parameter to enable a more aggressive strategy : https://github.com/apache/flink-kubernetes-operator/pull/879#discussion_r1764419949

      Attachments

        Issue Links

          Activity

            People

              heigebupahei yuanfenghu
              heigebupahei yuanfenghu
              Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: