Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-37063 SQL Adaptive Query Execution QA: Phase 2
  3. SPARK-37267

OptimizeSkewInRebalancePartitions support optimize non-root node

    XMLWordPrintableJSON

Details

    • Sub-task
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • 3.3.0
    • 3.3.0
    • SQL
    • None

    Description

      `OptimizeSkewInRebalancePartitions` now is applied if the `RebalancePartitions` is the root node, but sometimes, we expect a local sort after do RebalancePartitions that can improve the compression ratio.

      After SPARK-36184, we make validate easy that whether the rule introduces extra shuffle or not and the output partitioning is ensured by `AQEShuffleReadExec.outputPartitioning`.

      So it is safe to make `OptimizeSkewInRebalancePartitions` support optimize non-root node.

      Attachments

        Activity

          People

            ulysses XiDuo You
            ulysses XiDuo You
            Votes:
            0 Vote for this issue
            Watchers:
            3 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: