Added better docs for RDDCheckpointData

2 files changed, 13 insertions, 1 deletions

diff --git a/core/src/main/scala/spark/RDDCheckpointData.scala b/core/src/main/scala/spark/RDDCheckpointData.scala
index e270b6312e..d845a522e4 100644
--- a/core/src/main/scala/spark/RDDCheckpointData.scala
+++ b/core/src/main/scala/spark/RDDCheckpointData.scala
@@ -14,15 +14,23 @@ private[spark] object CheckpointState extends Enumeration {
 }
 
 /**
- * This class contains all the information of the regarding RDD checkpointing.
+ * This class contains all the information related to RDD checkpointing. Each instance of this class
+ * is associated with a RDD. It manages process of checkpointing of the associated RDD, as well as,
+ * manages the post-checkpoint state by providing the updated splits, iterator and preferred locations
+ * of the checkpointed RDD.
  */
 private[spark] class RDDCheckpointData[T: ClassManifest](rdd: RDD[T])
 extends Logging with Serializable {
 
   import CheckpointState._
 
+  // The checkpoint state of the associated RDD.
   var cpState = Initialized
+
+  // The file to which the associated RDD has been checkpointed to
   @transient var cpFile: Option[String] = None
+
+  // The CheckpointRDD created from the checkpoint file, that is, the new parent the associated RDD.
   @transient var cpRDD: Option[RDD[T]] = None
 
   // Mark the RDD for checkpointing
diff --git a/core/src/main/scala/spark/rdd/CheckpointRDD.scala b/core/src/main/scala/spark/rdd/CheckpointRDD.scala
index 1a88d402c3..86c63ca2f4 100644
--- a/core/src/main/scala/spark/rdd/CheckpointRDD.scala
+++ b/core/src/main/scala/spark/rdd/CheckpointRDD.scala
@@ -13,6 +13,10 @@ private[spark] class CheckpointRDDSplit(idx: Int, val splitFile: String) extends
   override val index: Int = idx
 }
 
+/**
+ * This RDD represents a RDD checkpoint file (similar to HadoopRDD).
+ */
+private[spark]
 class CheckpointRDD[T: ClassManifest](sc: SparkContext, checkpointPath: String)
   extends RDD[T](sc, Nil) {