Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-10494

Multiple Python UDFs together with aggregation or sort merge join may cause OOM (failed to acquire memory)

    XMLWordPrintableJSON

    Details

    • Type: Bug
    • Status: Resolved
    • Priority: Critical
    • Resolution: Fixed
    • Affects Version/s: 1.5.0
    • Fix Version/s: 1.5.1, 1.6.0
    • Component/s: PySpark, SQL
    • Labels:
      None

      Description

      The RDD cache for Python UDF is removed in 1.4, then N Python UDFs in one query stage could end up evaluate upstream (SparkPlan) 2^N times.

      In 1.5, If there is aggregation or sort merge join in upstream SparkPlan, they will cause OOM (failed to acquire memory).

        Attachments

          Issue Links

            Activity

              People

              • Assignee:
                rxin Reynold Xin
                Reporter:
                davies Davies Liu
              • Votes:
                0 Vote for this issue
                Watchers:
                2 Start watching this issue

                Dates

                • Created:
                  Updated:
                  Resolved: