[120] | 1 | /** |
---|
| 2 | * Licensed to the Apache Software Foundation (ASF) under one |
---|
| 3 | * or more contributor license agreements. See the NOTICE file |
---|
| 4 | * distributed with this work for additional information |
---|
| 5 | * regarding copyright ownership. The ASF licenses this file |
---|
| 6 | * to you under the Apache License, Version 2.0 (the |
---|
| 7 | * "License"); you may not use this file except in compliance |
---|
| 8 | * with the License. You may obtain a copy of the License at |
---|
| 9 | * |
---|
| 10 | * http://www.apache.org/licenses/LICENSE-2.0 |
---|
| 11 | * |
---|
| 12 | * Unless required by applicable law or agreed to in writing, software |
---|
| 13 | * distributed under the License is distributed on an "AS IS" BASIS, |
---|
| 14 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
---|
| 15 | * See the License for the specific language governing permissions and |
---|
| 16 | * limitations under the License. |
---|
| 17 | */ |
---|
| 18 | package org.apache.hadoop.mapred; |
---|
| 19 | |
---|
| 20 | import junit.framework.TestCase; |
---|
| 21 | import org.apache.hadoop.hdfs.MiniDFSCluster; |
---|
| 22 | import org.apache.hadoop.fs.FileSystem; |
---|
| 23 | import org.apache.hadoop.fs.Path; |
---|
| 24 | |
---|
| 25 | import java.io.IOException; |
---|
| 26 | import java.util.Map; |
---|
| 27 | import java.util.Properties; |
---|
| 28 | |
---|
| 29 | /** |
---|
| 30 | * Test case to run a MapReduce job. |
---|
| 31 | * <p/> |
---|
| 32 | * It runs a 2 node cluster Hadoop with a 2 node DFS. |
---|
| 33 | * <p/> |
---|
| 34 | * The JobConf to use must be obtained via the creatJobConf() method. |
---|
| 35 | * <p/> |
---|
| 36 | * It creates a temporary directory -accessible via getTestRootDir()- |
---|
| 37 | * for both input and output. |
---|
| 38 | * <p/> |
---|
| 39 | * The input directory is accesible via getInputDir() and the output |
---|
| 40 | * directory via getOutputDir() |
---|
| 41 | * <p/> |
---|
| 42 | * The DFS filesystem is formated before the testcase starts and after it ends. |
---|
| 43 | */ |
---|
| 44 | public abstract class ClusterMapReduceTestCase extends TestCase { |
---|
| 45 | private MiniDFSCluster dfsCluster = null; |
---|
| 46 | private MiniMRCluster mrCluster = null; |
---|
| 47 | |
---|
| 48 | /** |
---|
| 49 | * Creates Hadoop Cluster and DFS before a test case is run. |
---|
| 50 | * |
---|
| 51 | * @throws Exception |
---|
| 52 | */ |
---|
| 53 | protected void setUp() throws Exception { |
---|
| 54 | super.setUp(); |
---|
| 55 | |
---|
| 56 | startCluster(true, null); |
---|
| 57 | } |
---|
| 58 | |
---|
| 59 | /** |
---|
| 60 | * Starts the cluster within a testcase. |
---|
| 61 | * <p/> |
---|
| 62 | * Note that the cluster is already started when the testcase method |
---|
| 63 | * is invoked. This method is useful if as part of the testcase the |
---|
| 64 | * cluster has to be shutdown and restarted again. |
---|
| 65 | * <p/> |
---|
| 66 | * If the cluster is already running this method does nothing. |
---|
| 67 | * |
---|
| 68 | * @param reformatDFS indicates if DFS has to be reformated |
---|
| 69 | * @param props configuration properties to inject to the mini cluster |
---|
| 70 | * @throws Exception if the cluster could not be started |
---|
| 71 | */ |
---|
| 72 | protected synchronized void startCluster(boolean reformatDFS, Properties props) |
---|
| 73 | throws Exception { |
---|
| 74 | if (dfsCluster == null) { |
---|
| 75 | JobConf conf = new JobConf(); |
---|
| 76 | if (props != null) { |
---|
| 77 | for (Map.Entry entry : props.entrySet()) { |
---|
| 78 | conf.set((String) entry.getKey(), (String) entry.getValue()); |
---|
| 79 | } |
---|
| 80 | } |
---|
| 81 | dfsCluster = new MiniDFSCluster(conf, 2, reformatDFS, null); |
---|
| 82 | |
---|
| 83 | ConfigurableMiniMRCluster.setConfiguration(props); |
---|
| 84 | //noinspection deprecation |
---|
| 85 | mrCluster = new ConfigurableMiniMRCluster(2, getFileSystem().getName(), 1); |
---|
| 86 | } |
---|
| 87 | } |
---|
| 88 | |
---|
| 89 | private static class ConfigurableMiniMRCluster extends MiniMRCluster { |
---|
| 90 | private static Properties config; |
---|
| 91 | |
---|
| 92 | public static void setConfiguration(Properties props) { |
---|
| 93 | config = props; |
---|
| 94 | } |
---|
| 95 | |
---|
| 96 | public ConfigurableMiniMRCluster(int numTaskTrackers, String namenode, |
---|
| 97 | int numDir) throws Exception { |
---|
| 98 | super(numTaskTrackers, namenode, numDir); |
---|
| 99 | } |
---|
| 100 | |
---|
| 101 | public JobConf createJobConf() { |
---|
| 102 | JobConf conf = super.createJobConf(); |
---|
| 103 | if (config != null) { |
---|
| 104 | for (Map.Entry entry : config.entrySet()) { |
---|
| 105 | conf.set((String) entry.getKey(), (String) entry.getValue()); |
---|
| 106 | } |
---|
| 107 | } |
---|
| 108 | return conf; |
---|
| 109 | } |
---|
| 110 | } |
---|
| 111 | |
---|
| 112 | /** |
---|
| 113 | * Stops the cluster within a testcase. |
---|
| 114 | * <p/> |
---|
| 115 | * Note that the cluster is already started when the testcase method |
---|
| 116 | * is invoked. This method is useful if as part of the testcase the |
---|
| 117 | * cluster has to be shutdown. |
---|
| 118 | * <p/> |
---|
| 119 | * If the cluster is already stopped this method does nothing. |
---|
| 120 | * |
---|
| 121 | * @throws Exception if the cluster could not be stopped |
---|
| 122 | */ |
---|
| 123 | protected void stopCluster() throws Exception { |
---|
| 124 | if (mrCluster != null) { |
---|
| 125 | mrCluster.shutdown(); |
---|
| 126 | mrCluster = null; |
---|
| 127 | } |
---|
| 128 | if (dfsCluster != null) { |
---|
| 129 | dfsCluster.shutdown(); |
---|
| 130 | dfsCluster = null; |
---|
| 131 | } |
---|
| 132 | } |
---|
| 133 | |
---|
| 134 | /** |
---|
| 135 | * Destroys Hadoop Cluster and DFS after a test case is run. |
---|
| 136 | * |
---|
| 137 | * @throws Exception |
---|
| 138 | */ |
---|
| 139 | protected void tearDown() throws Exception { |
---|
| 140 | stopCluster(); |
---|
| 141 | super.tearDown(); |
---|
| 142 | } |
---|
| 143 | |
---|
| 144 | /** |
---|
| 145 | * Returns a preconfigured Filesystem instance for test cases to read and |
---|
| 146 | * write files to it. |
---|
| 147 | * <p/> |
---|
| 148 | * TestCases should use this Filesystem instance. |
---|
| 149 | * |
---|
| 150 | * @return the filesystem used by Hadoop. |
---|
| 151 | * @throws IOException |
---|
| 152 | */ |
---|
| 153 | protected FileSystem getFileSystem() throws IOException { |
---|
| 154 | return dfsCluster.getFileSystem(); |
---|
| 155 | } |
---|
| 156 | |
---|
| 157 | protected MiniMRCluster getMRCluster() { |
---|
| 158 | return mrCluster; |
---|
| 159 | } |
---|
| 160 | |
---|
| 161 | /** |
---|
| 162 | * Returns the path to the root directory for the testcase. |
---|
| 163 | * |
---|
| 164 | * @return path to the root directory for the testcase. |
---|
| 165 | */ |
---|
| 166 | protected Path getTestRootDir() { |
---|
| 167 | return new Path("x").getParent(); |
---|
| 168 | } |
---|
| 169 | |
---|
| 170 | /** |
---|
| 171 | * Returns a path to the input directory for the testcase. |
---|
| 172 | * |
---|
| 173 | * @return path to the input directory for the tescase. |
---|
| 174 | */ |
---|
| 175 | protected Path getInputDir() { |
---|
| 176 | return new Path("input"); |
---|
| 177 | } |
---|
| 178 | |
---|
| 179 | /** |
---|
| 180 | * Returns a path to the output directory for the testcase. |
---|
| 181 | * |
---|
| 182 | * @return path to the output directory for the tescase. |
---|
| 183 | */ |
---|
| 184 | protected Path getOutputDir() { |
---|
| 185 | return new Path("output"); |
---|
| 186 | } |
---|
| 187 | |
---|
| 188 | /** |
---|
| 189 | * Returns a job configuration preconfigured to run against the Hadoop |
---|
| 190 | * managed by the testcase. |
---|
| 191 | * |
---|
| 192 | * @return configuration that works on the testcase Hadoop instance |
---|
| 193 | */ |
---|
| 194 | protected JobConf createJobConf() { |
---|
| 195 | return mrCluster.createJobConf(); |
---|
| 196 | } |
---|
| 197 | |
---|
| 198 | } |
---|