Response to Matei's feedback

Author: pwendell

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

@@ -331,8 +331,10 @@ abstract class RDD[T: ClassTag](
       /** Distributes elements evenly across output partitions, starting from a random partition. */
       def distributePartition(index: Int, items: Iterator[T]): Iterator[(Int, T)] = {
         var position = (new Random(index)).nextInt(numPartitions)
-        items.map{ t =>
-          position = position + 1 % numPartitions
+        items.map { t =>
+          // Note that the hash code of the key will just be the key itself. The HashPartitioner 
+          // will mod it with the number of total partitions.
+          position = position + 1
           (position, t)
         }
       }

core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala

@@ -219,7 +219,7 @@ class RDDSuite extends FunSuite with SharedSparkContext {
     def testSplitPartitions(input: Seq[Int], initialPartitions: Int, finalPartitions: Int) {
       val data = sc.parallelize(input, initialPartitions)
       val repartitioned = data.repartition(finalPartitions)
-      assert(repartitioned.partitions.size == finalPartitions)
+      assert(repartitioned.partitions.size === finalPartitions)
       val partitions = repartitioned.glom().collect()
       // assert all elements are present
       assert(repartitioned.collect().sortWith(_ > _).toSeq === input.toSeq.sortWith(_ > _).toSeq)