From c7600c24221d29fde31dca921d9d5863af2666e9 Mon Sep 17 00:00:00 2001
From: Xingbo Jiang <xingbo.jiang@databricks.com>
Date: Thu, 26 Jul 2018 11:24:01 +0800
Subject: [PATCH] update

---
 .../scala/org/apache/spark/rdd/MapPartitionsRDD.scala    | 9 +++++++++
 core/src/main/scala/org/apache/spark/rdd/RDD.scala       | 5 ++++-
 .../scala/org/apache/spark/scheduler/ActiveJob.scala     | 2 +-
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/core/src/main/scala/org/apache/spark/rdd/MapPartitionsRDD.scala b/core/src/main/scala/org/apache/spark/rdd/MapPartitionsRDD.scala
index d4ad09143e80d..904d9c025629f 100644
--- a/core/src/main/scala/org/apache/spark/rdd/MapPartitionsRDD.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/MapPartitionsRDD.scala
@@ -23,6 +23,15 @@ import org.apache.spark.{Partition, TaskContext}
 
 /**
  * An RDD that applies the provided function to every partition of the parent RDD.
+ *
+ * @param prev the parent RDD.
+ * @param f The function used to map a tuple of (TaskContext, partition index, input iterator) to
+ *          an output iterator.
+ * @param preservesPartitioning Whether the input function preserves the partitioner, which should
+ *                              be `false` unless `prev` is a pair RDD and the input function
+ *                              doesn't modify the keys.
+ * @param isFromBarrier Indicates whether this RDD is transformed from an RDDBarrier, a stage
+ *                      containing at least one RDDBarrier shall be turned into a barrier stage.
  */
 private[spark] class MapPartitionsRDD[U: ClassTag, T: ClassTag](
     var prev: RDD[T],
diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
index 04698132adf83..cbc1143126d8e 100644
--- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
@@ -1853,8 +1853,11 @@ abstract class RDD[T: ClassTag](
    * barrier stage.
    *
    * An RDD is in a barrier stage, if at least one of its parent RDD(s), or itself, are mapped from
-   * a RDDBarrier. This function always returns false for a [[ShuffledRDD]], since a
+   * an [[RDDBarrier]]. This function always returns false for a [[ShuffledRDD]], since a
    * [[ShuffledRDD]] indicates start of a new stage.
+   *
+   * A [[MapPartitionsRDD]] can be transformed from an [[RDDBarrier]], under that case the
+   * [[MapPartitionsRDD]] shall be marked as barrier.
    */
   private[spark] def isBarrier(): Boolean = isBarrier_
 
diff --git a/core/src/main/scala/org/apache/spark/scheduler/ActiveJob.scala b/core/src/main/scala/org/apache/spark/scheduler/ActiveJob.scala
index b3bbfb1683c5c..6e4d062749d5f 100644
--- a/core/src/main/scala/org/apache/spark/scheduler/ActiveJob.scala
+++ b/core/src/main/scala/org/apache/spark/scheduler/ActiveJob.scala
@@ -61,7 +61,7 @@ private[spark] class ActiveJob(
 
   var numFinished = 0
 
-  // Mark all the partitions of the stage to be not finished.
+  /** Resets the status of all partitions in this stage so they are marked as not finished. */
   def resetAllPartitions(): Unit = {
     (0 until numPartitions).foreach(finished.update(_, false))
     numFinished = 0