Github user MaxGekk commented on a diff in the pull request: https://github.com/apache/spark/pull/21638#discussion_r198243125 --- Diff: core/src/main/scala/org/apache/spark/input/PortableDataStream.scala --- @@ -45,10 +45,9 @@ private[spark] abstract class StreamFileInputFormat[T] * which is set through setMaxSplitSize */ def setMinPartitions(sc: SparkContext, context: JobContext, minPartitions: Int) { - val defaultMaxSplitBytes = Math.max( - sc.getConf.get(config.FILES_MAX_PARTITION_BYTES), minPartitions) + 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 -- Now it makes much more sense.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org