From 205566e56e2891245b2d7820bfb3629945a2dcd9 Mon Sep 17 00:00:00 2001 From: Mark Hamstra Date: Wed, 20 Nov 2013 14:49:09 -0800 Subject: [PATCH] Improved comment --- .../scala/org/apache/spark/scheduler/DAGScheduler.scala | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala index be46f74f7c..6f9d4d52a4 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala @@ -243,10 +243,9 @@ class DAGScheduler( } /** - * Create a Stage for the given RDD, either as a shuffle map stage (for a ShuffleDependency) or - * as a result stage for the final RDD used directly in an action. The stage will also be - * associated with the provided jobId.. Shuffle map stages, whose shuffleId may have previously - * been registered in the MapOutputTracker, should be (re)-created using newOrUsedStage. + * Create a Stage -- either directly for use as a result stage, or as part of the (re)-creation + * of a shuffle map stage in newOrUsedStage. The stage will be associated with the provided + * jobId. Production of shuffle map stages should always use newOrUsedStage, not newStage directly. */ private def newStage( rdd: RDD[_],