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.mapred;
020
021import org.apache.hadoop.classification.InterfaceAudience;
022import org.apache.hadoop.classification.InterfaceStability;
023
024/** 
025 * Partitions the key space.
026 * 
027 * <p><code>Partitioner</code> controls the partitioning of the keys of the 
028 * intermediate map-outputs. The key (or a subset of the key) is used to derive
029 * the partition, typically by a hash function. The total number of partitions
030 * is the same as the number of reduce tasks for the job. Hence this controls
031 * which of the <code>m</code> reduce tasks the intermediate key (and hence the 
032 * record) is sent for reduction.</p>
033 *
034 * <p>Note: A <code>Partitioner</code> is created only when there are multiple
035 * reducers.</p>
036 * 
037 * @see Reducer
038 */
039@InterfaceAudience.Public
040@InterfaceStability.Stable
041public interface Partitioner<K2, V2> extends JobConfigurable {
042  
043  /** 
044   * Get the paritition number for a given key (hence record) given the total 
045   * number of partitions i.e. number of reduce-tasks for the job.
046   *   
047   * <p>Typically a hash function on a all or a subset of the key.</p>
048   *
049   * @param key the key to be paritioned.
050   * @param value the entry value.
051   * @param numPartitions the total number of partitions.
052   * @return the partition number for the <code>key</code>.
053   */
054  int getPartition(K2 key, V2 value, int numPartitions);
055}