Java Job.setPartitionerClass方法代码示例

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
	Configuration conf = new Configuration();
	Job job = Job.getInstance(conf, "test");
	
	job.setMapperClass(testMapper.class);
	job.setPartitionerClass(testPartitioner.class);
	job.setReducerClass(testReducer.class);
	job.setNumReduceTasks(10);
	
	job.setOutputKeyClass(Text.class);
	job.setOutputValueClass(IntWritable.class);
	
	FileInputFormat.setInputPaths(job, new Path(args[0]));
	FileOutputFormat.setOutputPath(job, new Path(args[1]));

	if (!job.waitForCompletion(true))
		return;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public Job createJob() 
throws IOException {
  Configuration conf = getConf();
  conf.setInt(MRJobConfig.NUM_MAPS, 1);
  Job job = Job.getInstance(conf, "test");
  job.setNumReduceTasks(1);
  job.setJarByClass(CredentialsTestJob.class);
  job.setNumReduceTasks(1);
  job.setMapperClass(CredentialsTestJob.CredentialsTestMapper.class);
  job.setMapOutputKeyClass(IntWritable.class);
  job.setMapOutputValueClass(NullWritable.class);
  job.setReducerClass(CredentialsTestJob.CredentialsTestReducer.class);
  job.setInputFormatClass(SleepJob.SleepInputFormat.class);
  job.setPartitionerClass(SleepJob.SleepJobPartitioner.class);
  job.setOutputFormatClass(NullOutputFormat.class);
  job.setSpeculativeExecution(false);
  job.setJobName("test job");
  FileInputFormat.addInputPath(job, new Path("ignored"));
  return job;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/** {@inheritDoc} */
@Override
public void init(Job job) {
  // setup mapper
  job.setMapperClass(PartitionMapper.class);
  job.setMapOutputKeyClass(IntWritable.class);
  job.setMapOutputValueClass(SummationWritable.class);

  // setup partitioner
  job.setPartitionerClass(IndexPartitioner.class);

  // setup reducer
  job.setReducerClass(SummingReducer.class);
  job.setOutputKeyClass(NullWritable.class);
  job.setOutputValueClass(TaskResult.class);
  final Configuration conf = job.getConfiguration();
  final int nParts = conf.getInt(N_PARTS, 1);
  job.setNumReduceTasks(nParts);

  // setup input
  job.setInputFormatClass(SummationInputFormat.class);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/**
 * Configure <code>job</code> with a TotalOrderPartitioner, partitioning against
 * <code>splitPoints</code>. Cleans up the partitions file after job exists.
 */
static void configurePartitioner(Job job, List<ImmutableBytesWritable> splitPoints)
    throws IOException {
  Configuration conf = job.getConfiguration();
  // create the partitions file
  FileSystem fs = FileSystem.get(conf);
  String hbaseTmpFsDir =
      conf.get(HConstants.TEMPORARY_FS_DIRECTORY_KEY,
        HConstants.DEFAULT_TEMPORARY_HDFS_DIRECTORY);
  Path partitionsPath = new Path(hbaseTmpFsDir, "partitions_" + UUID.randomUUID());
  fs.makeQualified(partitionsPath);
  writePartitions(conf, partitionsPath, splitPoints);
  fs.deleteOnExit(partitionsPath);

  // configure job to use it
  job.setPartitionerClass(TotalOrderPartitioner.class);
  TotalOrderPartitioner.setPartitionFile(conf, partitionsPath);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
  Configuration conf = new Configuration();
  String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
  if (otherArgs.length != 2) {
    System.err.println("Usage: secondarysort <in> <out>");
    System.exit(2);
  }
  Job job = Job.getInstance(conf, "secondary sort");
  job.setJarByClass(SecondarySort.class);
  job.setMapperClass(MapClass.class);
  job.setReducerClass(Reduce.class);

  // group and partition by the first int in the pair
  job.setPartitionerClass(FirstPartitioner.class);
  job.setGroupingComparatorClass(FirstGroupingComparator.class);

  // the map output is IntPair, IntWritable
  job.setMapOutputKeyClass(IntPair.class);
  job.setMapOutputValueClass(IntWritable.class);

  // the reduce output is Text, IntWritable
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(IntWritable.class);
  
  FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
  FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
  System.exit(job.waitForCompletion(true) ? 0 : 1);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public int run(String[] args) throws Exception {
  LOG.info("starting");
  Job job = Job.getInstance(getConf());
  Path inputDir = new Path(args[0]);
  Path outputDir = new Path(args[1]);
  boolean useSimplePartitioner = getUseSimplePartitioner(job);
  TeraInputFormat.setInputPaths(job, inputDir);
  FileOutputFormat.setOutputPath(job, outputDir);
  job.setJobName("TeraSort");
  job.setJarByClass(TeraSort.class);
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(Text.class);
  job.setInputFormatClass(TeraInputFormat.class);
  job.setOutputFormatClass(TeraOutputFormat.class);
  if (useSimplePartitioner) {
    job.setPartitionerClass(SimplePartitioner.class);
  } else {
    long start = System.currentTimeMillis();
    Path partitionFile = new Path(outputDir, 
                                  TeraInputFormat.PARTITION_FILENAME);
    URI partitionUri = new URI(partitionFile.toString() +
                               "#" + TeraInputFormat.PARTITION_FILENAME);
    try {
      TeraInputFormat.writePartitionFile(job, partitionFile);
    } catch (Throwable e) {
      LOG.error(e.getMessage());
      return -1;
    }
    job.addCacheFile(partitionUri);  
    long end = System.currentTimeMillis();
    System.out.println("Spent " + (end - start) + "ms computing partitions.");
    job.setPartitionerClass(TotalOrderPartitioner.class);
  }
  
  job.getConfiguration().setInt("dfs.replication", getOutputReplication(job));
  TeraOutputFormat.setFinalSync(job, true);
  int ret = job.waitForCompletion(true) ? 0 : 1;
  LOG.info("done");
  return ret;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public Job createSubmittableJob(String[] args) throws IOException {
  Path partitionsPath = new Path(destPath, PARTITIONS_FILE_NAME);
  generatePartitions(partitionsPath);
  
  Job job = Job.getInstance(getConf(),
        getConf().get("mapreduce.job.name", "hashTable_" + tableHash.tableName));
  Configuration jobConf = job.getConfiguration();
  jobConf.setLong(HASH_BATCH_SIZE_CONF_KEY, tableHash.batchSize);
  job.setJarByClass(HashTable.class);

  TableMapReduceUtil.initTableMapperJob(tableHash.tableName, tableHash.initScan(),
      HashMapper.class, ImmutableBytesWritable.class, ImmutableBytesWritable.class, job);
  
  // use a TotalOrderPartitioner and reducers to group region output into hash files
  job.setPartitionerClass(TotalOrderPartitioner.class);
  TotalOrderPartitioner.setPartitionFile(jobConf, partitionsPath);
  job.setReducerClass(Reducer.class);  // identity reducer
  job.setNumReduceTasks(tableHash.numHashFiles);
  job.setOutputKeyClass(ImmutableBytesWritable.class);
  job.setOutputValueClass(ImmutableBytesWritable.class);
  job.setOutputFormatClass(MapFileOutputFormat.class);
  FileOutputFormat.setOutputPath(job, new Path(destPath, HASH_DATA_DIR));
  
  return job;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/**
 * Run small MR job.
 */
@Ignore("Goes zombie too frequently; needs work. See HBASE-14563") @Test
public void testWritingPEData() throws Exception {
  Configuration conf = util.getConfiguration();
  Path testDir = util.getDataTestDirOnTestFS("testWritingPEData");
  FileSystem fs = testDir.getFileSystem(conf);

  // Set down this value or we OOME in eclipse.
  conf.setInt("mapreduce.task.io.sort.mb", 20);
  // Write a few files.
  conf.setLong(HConstants.HREGION_MAX_FILESIZE, 64 * 1024);

  Job job = new Job(conf, "testWritingPEData");
  setupRandomGeneratorMapper(job);
  // This partitioner doesn't work well for number keys but using it anyways
  // just to demonstrate how to configure it.
  byte[] startKey = new byte[RandomKVGeneratingMapper.KEYLEN_DEFAULT];
  byte[] endKey = new byte[RandomKVGeneratingMapper.KEYLEN_DEFAULT];

  Arrays.fill(startKey, (byte)0);
  Arrays.fill(endKey, (byte)0xff);

  job.setPartitionerClass(SimpleTotalOrderPartitioner.class);
  // Set start and end rows for partitioner.
  SimpleTotalOrderPartitioner.setStartKey(job.getConfiguration(), startKey);
  SimpleTotalOrderPartitioner.setEndKey(job.getConfiguration(), endKey);
  job.setReducerClass(KeyValueSortReducer.class);
  job.setOutputFormatClass(HFileOutputFormat2.class);
  job.setNumReduceTasks(4);
  job.getConfiguration().setStrings("io.serializations", conf.get("io.serializations"),
      MutationSerialization.class.getName(), ResultSerialization.class.getName(),
      KeyValueSerialization.class.getName());

  FileOutputFormat.setOutputPath(job, testDir);
  assertTrue(job.waitForCompletion(false));
  FileStatus [] files = fs.listStatus(testDir);
  assertTrue(files.length > 0);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/**
 * Run small MR job.
 */
@Test
public void testWritingPEData() throws Exception {
  Configuration conf = util.getConfiguration();
  Path testDir = util.getDataTestDirOnTestFS("testWritingPEData");
  FileSystem fs = testDir.getFileSystem(conf);

  // Set down this value or we OOME in eclipse.
  conf.setInt("mapreduce.task.io.sort.mb", 20);
  // Write a few files.
  conf.setLong(HConstants.HREGION_MAX_FILESIZE, 64 * 1024);

  Job job = new Job(conf, "testWritingPEData");
  setupRandomGeneratorMapper(job);
  // This partitioner doesn't work well for number keys but using it anyways
  // just to demonstrate how to configure it.
  byte[] startKey = new byte[RandomKVGeneratingMapper.KEYLEN_DEFAULT];
  byte[] endKey = new byte[RandomKVGeneratingMapper.KEYLEN_DEFAULT];

  Arrays.fill(startKey, (byte)0);
  Arrays.fill(endKey, (byte)0xff);

  job.setPartitionerClass(SimpleTotalOrderPartitioner.class);
  // Set start and end rows for partitioner.
  SimpleTotalOrderPartitioner.setStartKey(job.getConfiguration(), startKey);
  SimpleTotalOrderPartitioner.setEndKey(job.getConfiguration(), endKey);
  job.setReducerClass(KeyValueSortReducer.class);
  job.setOutputFormatClass(HFileOutputFormat.class);
  job.setNumReduceTasks(4);
  job.getConfiguration().setStrings("io.serializations", conf.get("io.serializations"),
      MutationSerialization.class.getName(), ResultSerialization.class.getName(),
      KeyValueSerialization.class.getName());

  FileOutputFormat.setOutputPath(job, testDir);
  assertTrue(job.waitForCompletion(false));
  FileStatus [] files = fs.listStatus(testDir);
  assertTrue(files.length > 0);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/**
 * After adding data to the table start a mr job to
 * @throws IOException
 * @throws ClassNotFoundException
 * @throws InterruptedException
 */
private void runCheck() throws IOException, ClassNotFoundException, InterruptedException {
  LOG.info("Running check");
  Configuration conf = getConf();
  String jobName = getTablename() + "_check" + EnvironmentEdgeManager.currentTime();
  Path p = util.getDataTestDirOnTestFS(jobName);

  Job job = new Job(conf);
  job.setJarByClass(getClass());
  job.setJobName(jobName);

  job.setPartitionerClass(NaturalKeyPartitioner.class);
  job.setGroupingComparatorClass(NaturalKeyGroupingComparator.class);
  job.setSortComparatorClass(CompositeKeyComparator.class);

  Scan scan = new Scan();
  scan.addFamily(CHAIN_FAM);
  scan.addFamily(SORT_FAM);
  scan.setMaxVersions(1);
  scan.setCacheBlocks(false);
  scan.setBatch(1000);

  int replicaCount = conf.getInt(NUM_REPLICA_COUNT_KEY, NUM_REPLICA_COUNT_DEFAULT);
  if (replicaCount != NUM_REPLICA_COUNT_DEFAULT) {
    scan.setConsistency(Consistency.TIMELINE);
  }

  TableMapReduceUtil.initTableMapperJob(
      getTablename().getName(),
      scan,
      LinkedListCheckingMapper.class,
      LinkKey.class,
      LinkChain.class,
      job
  );

  job.setReducerClass(LinkedListCheckingReducer.class);
  job.setOutputKeyClass(NullWritable.class);
  job.setOutputValueClass(NullWritable.class);

  FileOutputFormat.setOutputPath(job, p);

  assertEquals(true, job.waitForCompletion(true));

  // Delete the files.
  util.getTestFileSystem().delete(p, true);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
private void testComparator(String keySpec, int expect) 
    throws Exception {
  String root = System.getProperty("test.build.data", "/tmp");
  Path inDir = new Path(root, "test_cmp/in");
  Path outDir = new Path(root, "test_cmp/out");
  
  conf.set("mapreduce.partition.keycomparator.options", keySpec);
  conf.set("mapreduce.partition.keypartitioner.options", "-k1.1,1.1");
  conf.set(MRJobConfig.MAP_OUTPUT_KEY_FIELD_SEPERATOR, " ");

  Job job = MapReduceTestUtil.createJob(conf, inDir, outDir, 1, 1,
              line1 +"\n" + line2 + "\n"); 
  job.setMapperClass(InverseMapper.class);
  job.setReducerClass(Reducer.class);
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(LongWritable.class);
  job.setSortComparatorClass(KeyFieldBasedComparator.class);
  job.setPartitionerClass(KeyFieldBasedPartitioner.class);

  job.waitForCompletion(true);
  assertTrue(job.isSuccessful());

  // validate output
  Path[] outputFiles = FileUtil.stat2Paths(getFileSystem().listStatus(outDir,
      new Utils.OutputFileUtils.OutputFilesFilter()));
  if (outputFiles.length > 0) {
    InputStream is = getFileSystem().open(outputFiles[0]);
    BufferedReader reader = new BufferedReader(new InputStreamReader(is));
    String line = reader.readLine();
    //make sure we get what we expect as the first line, and also
    //that we have two lines (both the lines must end up in the same
    //reducer since the partitioner takes the same key spec for all
    //lines
    if (expect == 1) {
      assertTrue(line.startsWith(line1));
    } else if (expect == 2) {
      assertTrue(line.startsWith(line2));
    }
    line = reader.readLine();
    if (expect == 1) {
      assertTrue(line.startsWith(line2));
    } else if (expect == 2) {
      assertTrue(line.startsWith(line1));
    }
    reader.close();
  }
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/**
 * Use this before submitting a TableReduce job. It will
 * appropriately set up the JobConf.
 *
 * @param table  The output table.
 * @param reducer  The reducer class to use.
 * @param job  The current job to adjust.  Make sure the passed job is
 * carrying all necessary HBase configuration.
 * @param partitioner  Partitioner to use. Pass <code>null</code> to use
 * default partitioner.
 * @param quorumAddress Distant cluster to write to; default is null for
 * output to the cluster that is designated in <code>hbase-site.xml</code>.
 * Set this String to the zookeeper ensemble of an alternate remote cluster
 * when you would have the reduce write a cluster that is other than the
 * default; e.g. copying tables between clusters, the source would be
 * designated by <code>hbase-site.xml</code> and this param would have the
 * ensemble address of the remote cluster.  The format to pass is particular.
 * Pass <code> &lt;hbase.zookeeper.quorum&gt;:&lt;
 *             hbase.zookeeper.client.port&gt;:&lt;zookeeper.znode.parent&gt;
 * </code> such as <code>server,server2,server3:2181:/hbase</code>.
 * @param serverClass redefined hbase.regionserver.class
 * @param serverImpl redefined hbase.regionserver.impl
 * @param addDependencyJars upload HBase jars and jars for any of the configured
 *           job classes via the distributed cache (tmpjars).
 * @throws IOException When determining the region count fails.
 */
public static void initTableReducerJob(String table,
  Class<? extends TableReducer> reducer, Job job,
  Class partitioner, String quorumAddress, String serverClass,
  String serverImpl, boolean addDependencyJars) throws IOException {

  Configuration conf = job.getConfiguration();
  HBaseConfiguration.merge(conf, HBaseConfiguration.create(conf));
  job.setOutputFormatClass(TableOutputFormat.class);
  if (reducer != null) job.setReducerClass(reducer);
  conf.set(TableOutputFormat.OUTPUT_TABLE, table);
  conf.setStrings("io.serializations", conf.get("io.serializations"),
      MutationSerialization.class.getName(), ResultSerialization.class.getName());
  // If passed a quorum/ensemble address, pass it on to TableOutputFormat.
  if (quorumAddress != null) {
    // Calling this will validate the format
    ZKConfig.validateClusterKey(quorumAddress);
    conf.set(TableOutputFormat.QUORUM_ADDRESS,quorumAddress);
  }
  if (serverClass != null && serverImpl != null) {
    conf.set(TableOutputFormat.REGION_SERVER_CLASS, serverClass);
    conf.set(TableOutputFormat.REGION_SERVER_IMPL, serverImpl);
  }
  job.setOutputKeyClass(ImmutableBytesWritable.class);
  job.setOutputValueClass(Writable.class);
  if (partitioner == HRegionPartitioner.class) {
    job.setPartitionerClass(HRegionPartitioner.class);
    int regions = MetaTableAccessor.getRegionCount(conf, TableName.valueOf(table));
    if (job.getNumReduceTasks() > regions) {
      job.setNumReduceTasks(regions);
    }
  } else if (partitioner != null) {
    job.setPartitionerClass(partitioner);
  }

  if (addDependencyJars) {
    addDependencyJars(job);
  }

  initCredentials(job);
}