Example usage for org.apache.hadoop.mapred JobConf JobConf

List of usage examples for org.apache.hadoop.mapred JobConf JobConf

Introduction

In this page you can find the example usage for org.apache.hadoop.mapred JobConf JobConf.

Prototype

public JobConf() 

Source Link

Document

Construct a map/reduce job configuration.

Usage

From source file:com.google.mr4c.hadoop.ClusterTest.java

License:Open Source License

@Test
public void testRoundTrip() throws Exception {
    JobConf conf = new JobConf();
    conf.clear();/*from  ww  w .j  a  v a  2  s.c  o  m*/
    m_cluster1.applyToConfig(conf);
    Cluster cluster = Cluster.extractFromConfig(conf);
    assertEquals(m_cluster1, cluster);
}

From source file:com.google.mr4c.hadoop.HadoopAlgoRunner.java

License:Open Source License

protected HadoopAlgoRunner(String[] args, Logger log) {
    m_fullArgs = args;/*www . ja v  a  2s .  c  om*/
    m_log = log;
    m_jobConf = new JobConf();
    m_bbJob = new MR4CMRJob(false); // not on cluster
}

From source file:com.google.mr4c.hadoop.yarn.YarnTestBinding.java

License:Open Source License

private void startMrCluster() throws IOException {
    Configuration conf = new JobConf();
    FileSystem.setDefaultUri(conf, HadoopTestUtils.getTestDFS().getUri());
    conf.setBoolean(YarnConfiguration.YARN_MINICLUSTER_FIXED_PORTS, true);
    conf.setBoolean(JHAdminConfig.MR_HISTORY_MINICLUSTER_FIXED_PORTS, true);
    String addr = MiniYARNCluster.getHostname() + ":0";
    conf.set(YarnConfiguration.RM_ADDRESS, addr);
    conf.set(JHAdminConfig.MR_HISTORY_ADDRESS, addr);
    m_mrCluster = MiniMRClientClusterFactory.create(HadoopTestUtils.class, "MR4CTests", 1, // num node managers
            conf);//  ww  w  .  j a v  a2 s  .c o  m

    // make sure startup is finished
    for (int i = 0; i < 60; i++) {
        String newAddr = m_mrCluster.getConfig().get(YarnConfiguration.RM_ADDRESS);
        if (newAddr.equals(addr)) {
            s_log.warn("MiniYARNCluster startup not complete");
            try {
                Thread.sleep(1000);
            } catch (InterruptedException ie) {
                throw new IOException(ie);
            }
        } else {
            s_log.info("MiniYARNCluster now available at {}", newAddr);
            return;
        }
    }
    throw new IOException("MiniYARNCluster taking too long to startup");

}

From source file:com.hadoop.mapreduce.TestLzoLazyLoading.java

License:Open Source License

public void testWithLocal() throws Exception {
    MiniMRCluster mr = null;//  ww  w.  j a v a  2s . c  om
    try {
        JobConf jconf = new JobConf();
        jconf.set("mapred.queue.names", "default");
        mr = new MiniMRCluster(2, "file:///", 3, null, null, jconf);
        Configuration cf = mr.createJobConf();
        cf.set("io.compression.codecs", LzoCodec.class.getName());
        runWordCount(cf, false, false);
        runWordCount(cf, false, true);
        runWordCount(cf, true, false);
    } finally {
        if (mr != null) {
            mr.shutdown();
        }
    }
}

From source file:com.hazelcast.jet.benchmark.wordcount.HdfsToMap.java

License:Open Source License

private static void fillMap(JetInstance client, String name, String inputPath, int parallelism)
        throws Exception {
    DAG dag = new DAG();
    JobConf conf = new JobConf();
    conf.setInputFormat(TextInputFormat.class);
    TextInputFormat.addInputPath(conf, new Path(inputPath));

    Vertex reader = dag.newVertex("reader", readHdfsP(conf, Util::entry));
    Vertex mapper = dag.newVertex("mapper",
            mapP((Map.Entry<LongWritable, Text> e) -> entry(e.getKey().get(), e.getValue().toString())));
    Vertex writer = dag.newVertex("writer", writeMapP(name));

    reader.localParallelism(parallelism);
    mapper.localParallelism(parallelism);
    writer.localParallelism(parallelism);

    dag.edge(between(reader, mapper));// ww  w  . jav  a 2s. c o  m
    dag.edge(between(mapper, writer));

    JobConfig jobConfig = new JobConfig();
    jobConfig.addClass(HdfsToMap.class);

    client.newJob(dag, jobConfig).join();
}

From source file:com.hazelcast.jet.hadoop.impl.ReadHdfsPTest.java

License:Open Source License

@Before
public void setup() throws IOException {
    instance = createJetMember();/*from w  ww.  j  a  v a 2  s .c o m*/
    jobConf = new JobConf();
    jobConf.setInputFormat(inputFormatClass);

    writeToFile();
    for (Path path : paths) {
        FileInputFormat.addInputPath(jobConf, path);
    }
}

From source file:com.hazelcast.jet.hadoop.impl.WriteHdfsPTest.java

License:Open Source License

@Test
public void testWriteFile() throws Exception {
    int messageCount = 320;
    String mapName = randomMapName();
    JetInstance instance = createJetMember();
    createJetMember();/*from  w ww  .ja v a  2 s .  c  o  m*/

    Map<IntWritable, IntWritable> map = IntStream.range(0, messageCount).boxed()
            .collect(toMap(IntWritable::new, IntWritable::new));
    instance.getMap(mapName).putAll(map);

    Path path = getPath();

    JobConf conf = new JobConf();
    conf.setOutputFormat(outputFormatClass);
    conf.setOutputCommitter(FileOutputCommitter.class);
    conf.setOutputKeyClass(IntWritable.class);
    conf.setOutputValueClass(IntWritable.class);

    if (outputFormatClass.equals(LazyOutputFormat.class)) {
        LazyOutputFormat.setOutputFormatClass(conf, TextOutputFormat.class);
    }

    FileOutputFormat.setOutputPath(conf, path);

    Pipeline p = Pipeline.create();
    p.drawFrom(Sources.map(mapName)).drainTo(HdfsSinks.hdfs(conf))
            // we use higher value to increase the race chance for LazyOutputFormat
            .setLocalParallelism(8);

    Future<Void> future = instance.newJob(p).getFuture();
    assertCompletesEventually(future);

    JobConf readJobConf = new JobConf();
    readJobConf.setInputFormat(inputFormatClass);
    FileInputFormat.addInputPath(readJobConf, path);

    p = Pipeline.create();
    p.drawFrom(HdfsSources.hdfs(readJobConf)).drainTo(Sinks.list("results"));

    future = instance.newJob(p).getFuture();
    assertCompletesEventually(future);

    IList<Object> results = instance.getList("results");
    assertEquals(messageCount, results.size());
}

From source file:com.hazelcast.jet.impl.connector.hadoop.WriteHdfsPTest.java

License:Open Source License

@Test
public void testWriteFile() throws Exception {
    int messageCount = 20;
    String mapName = randomMapName();
    JetInstance instance = createJetMember();
    createJetMember();/*from  w  w w .j a  va 2  s .  c o  m*/

    Map<IntWritable, IntWritable> map = IntStream.range(0, messageCount).boxed()
            .collect(toMap(IntWritable::new, IntWritable::new));
    instance.getMap(mapName).putAll(map);

    DAG dag = new DAG();
    Vertex producer = dag.newVertex("producer", readMap(mapName)).localParallelism(1);

    Path path = getPath();

    JobConf conf = new JobConf();
    conf.setOutputFormat(outputFormatClass);
    conf.setOutputCommitter(FileOutputCommitter.class);
    conf.setOutputKeyClass(IntWritable.class);
    conf.setOutputValueClass(IntWritable.class);

    FileOutputFormat.setOutputPath(conf, path);

    Vertex consumer = dag.newVertex("consumer", writeHdfs(conf)).localParallelism(4);

    dag.edge(between(producer, consumer));

    Future<Void> future = instance.newJob(dag).execute();
    assertCompletesEventually(future);

    dag = new DAG();
    JobConf readJobConf = new JobConf();
    readJobConf.setInputFormat(inputFormatClass);
    FileInputFormat.addInputPath(readJobConf, path);
    producer = dag.newVertex("producer", readHdfs(readJobConf)).localParallelism(8);

    consumer = dag.newVertex("consumer", writeList("results")).localParallelism(1);

    dag.edge(between(producer, consumer));
    future = instance.newJob(dag).execute();
    assertCompletesEventually(future);

    IList<Object> results = instance.getList("results");
    assertEquals(messageCount, results.size());
}

From source file:com.hotels.corc.cascading.OrcFileSourcePerformanceTest.java

License:Apache License

@Before
public void before() throws IOException {
    structTypeInfo = createTypeInfo();//from   www.  java2 s .  c om
    writeOrcFile();
    tap = createTap();

    when(flowProcess.getConfigCopy()).thenReturn(new JobConf());
}

From source file:com.hotels.plunger.TapDataReader.java

License:Apache License

private TupleEntryIterator getHadoopTupleEntryIterator() throws IOException {
    @SuppressWarnings("unchecked")
    Tap<JobConf, ?, ?> hadoopTap = (Tap<JobConf, ?, ?>) source;
    JobConf conf = new JobConf();
    FlowProcess<JobConf> flowProcess = new HadoopFlowProcess(conf);
    hadoopTap.sourceConfInit(flowProcess, conf);
    return hadoopTap.openForRead(flowProcess);
}