001/**
002 * Licensed to the Apache Software Foundation (ASF) under one
003 * or more contributor license agreements.  See the NOTICE file
004 * distributed with this work for additional information
005 * regarding copyright ownership.  The ASF licenses this file
006 * to you under the Apache License, Version 2.0 (the
007 * "License"); you may not use this file except in compliance
008 * with the License.  You may obtain a copy of the License at
009 *
010 *     http://www.apache.org/licenses/LICENSE-2.0
011 *
012 * Unless required by applicable law or agreed to in writing, software
013 * distributed under the License is distributed on an "AS IS" BASIS,
014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015 * See the License for the specific language governing permissions and
016 * limitations under the License.
017 */
018
019package org.apache.hadoop.mapreduce.lib.partition;
020
021import org.apache.hadoop.classification.InterfaceAudience;
022import org.apache.hadoop.classification.InterfaceStability;
023import org.apache.hadoop.mapreduce.Partitioner;
024
025/**
026  *  This partitioner rehashes values returned by {@link Object#hashCode()}
027  *  to get smoother distribution between partitions which may improve
028  *  reduce reduce time in some cases and should harm things in no cases.
029  *  This partitioner is suggested with Integer and Long keys with simple
030  *  patterns in their distributions.
031  *  @since 2.0.3
032 */
033@InterfaceAudience.Public
034@InterfaceStability.Stable
035public class RehashPartitioner<K, V> extends Partitioner<K, V> {
036
037  /** prime number seed for increasing hash quality */
038  private static final int SEED = 1591267453;
039
040  /** Rehash {@link Object#hashCode()} to partition. */
041  public int getPartition(K key, V value, int numReduceTasks) {
042    int h = SEED ^ key.hashCode();
043    h ^= (h >>> 20) ^ (h >>> 12);
044    h = h ^ (h >>> 7) ^ (h >>> 4);
045
046    return (h & Integer.MAX_VALUE) % numReduceTasks;
047  }
048}