Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/21638#discussion_r214581076 --- Diff: core/src/main/scala/org/apache/spark/input/PortableDataStream.scala --- @@ -47,7 +47,7 @@ private[spark] abstract class StreamFileInputFormat[T] def setMinPartitions(sc: SparkContext, context: JobContext, minPartitions: Int) { val defaultMaxSplitBytes = sc.getConf.get(config.FILES_MAX_PARTITION_BYTES) val openCostInBytes = sc.getConf.get(config.FILES_OPEN_COST_IN_BYTES) - val defaultParallelism = sc.defaultParallelism + val defaultParallelism = Math.max(sc.defaultParallelism, minPartitions) --- End diff -- We should have a test case; otherwise, we could hit the same issue again.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org