Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-24678

We should use 'PROCESS_LOCAL' first for Spark-Streaming

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • 2.3.1
    • 2.4.0
    • Block Manager, Spark Core
    • None

    Description

      Currently, `BlockRDD.getPreferredLocations`  only get hosts info of blocks, which results in subsequent schedule level is not better than 'NODE_LOCAL'. We can just make a small changes, the schedule level can be improved to 'PROCESS_LOCAL'

       

      Attachments

        Activity

          People

            sharkd sharkd tu
            sharkd sharkd tu
            Votes:
            0 Vote for this issue
            Watchers:
            3 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: