SPARK-1129: use a predefined seed when seed is zero in XORShiftRandom

If the seed is zero, XORShift generates all zeros, which would create unexpected result.

JIRA: https://spark-project.atlassian.net/browse/SPARK-1129

Author: Xiangrui Meng <meng@databricks.com>

Closes #645 from mengxr/xor and squashes the following commits:

1b086ab [Xiangrui Meng] use MurmurHash3 to set seed in XORShiftRandom
45c6f16 [Xiangrui Meng] minor style change
51f4050 [Xiangrui Meng] use a predefined seed when seed is zero in XORShiftRandom

2 files changed, 16 insertions, 3 deletions

diff --git a/core/src/main/scala/org/apache/spark/util/random/XORShiftRandom.scala b/core/src/main/scala/org/apache/spark/util/random/XORShiftRandom.scala
index ca611b67ed..8a4cdea2fa 100644
--- a/core/src/main/scala/org/apache/spark/util/random/XORShiftRandom.scala
+++ b/core/src/main/scala/org/apache/spark/util/random/XORShiftRandom.scala
@@ -17,8 +17,11 @@
 
 package org.apache.spark.util.random
 
+import java.nio.ByteBuffer
 import java.util.{Random => JavaRandom}
 
+import scala.util.hashing.MurmurHash3
+
 import org.apache.spark.util.Utils.timeIt
 
 /**
@@ -36,8 +39,8 @@ private[spark] class XORShiftRandom(init: Long) extends JavaRandom(init) {
   
   def this() = this(System.nanoTime)
 
-  private var seed = init
-  
+  private var seed = XORShiftRandom.hashSeed(init)
+
   // we need to just override next - this will be called by nextInt, nextDouble,
   // nextGaussian, nextLong, etc.
   override protected def next(bits: Int): Int = {    
@@ -49,13 +52,19 @@ private[spark] class XORShiftRandom(init: Long) extends JavaRandom(init) {
   }
 
   override def setSeed(s: Long) {
-    seed = s
+    seed = XORShiftRandom.hashSeed(s)
   }
 }
 
 /** Contains benchmark method and main method to run benchmark of the RNG */
 private[spark] object XORShiftRandom {
 
+  /** Hash seeds to have 0/1 bits throughout. */
+  private def hashSeed(seed: Long): Long = {
+    val bytes = ByteBuffer.allocate(java.lang.Long.SIZE).putLong(seed).array()
+    MurmurHash3.bytesHash(bytes)
+  }
+
   /**
    * Main method for running benchmark
    * @param args takes one argument - the number of random numbers to generate
diff --git a/core/src/test/scala/org/apache/spark/util/random/XORShiftRandomSuite.scala b/core/src/test/scala/org/apache/spark/util/random/XORShiftRandomSuite.scala
index c51d12bfe0..757476efdb 100644
--- a/core/src/test/scala/org/apache/spark/util/random/XORShiftRandomSuite.scala
+++ b/core/src/test/scala/org/apache/spark/util/random/XORShiftRandomSuite.scala
@@ -72,4 +72,8 @@ class XORShiftRandomSuite extends FunSuite with ShouldMatchers {
 
   }
 
+  test ("XORShift with zero seed") {
+    val random = new XORShiftRandom(0L)
+    assert(random.nextInt() != 0)
+  }
 }