Merge remote-tracking branch 'upstream/master' into SPARK-1149

core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala

@@ -193,6 +193,7 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)])
   }
 
   /** Alias for reduceByKeyLocally */
+  @deprecated("Use reduceByKeyLocally", "1.0.0")
   def reduceByKeyToDriver(func: (V, V) => V): Map[K, V] = reduceByKeyLocally(func)
 
   /** Count the number of elements for each key, and return the result to the master as a Map. */

docs/configuration.md

@@ -201,6 +201,13 @@ Apart from these, the following properties are also available, and may be useful
     multi-user services.
   </td>
 </tr>
+<tr>
+  <td>spark.scheduler.revive.interval</td>
+  <td>1000</td>
+  <td>
+    The interval length for the scheduler to revive the worker resource offers to run tasks. (in milliseconds)
+  </td>
+</tr>
 <tr>
   <td>spark.reducer.maxMbInFlight</td>
   <td>48</td>

python/pyspark/rdd.py

@@ -163,7 +163,7 @@ def getCheckpointFile(self):
 
     def map(self, f, preservesPartitioning=False):
         """
-        Return a new RDD containing the distinct elements in this RDD.
+        Return a new RDD by applying a function to each element of this RDD.
         """
         def func(split, iterator): return imap(f, iterator)
         return PipelinedRDD(self, func, preservesPartitioning)