Examples with JobClient org.apache.hadoop.mapred.JobClient used on opensource projects

Example 11 with JobClient

use of org.apache.hadoop.mapred.JobClient in project hadoop by apache.

the class TestMultipleOutputs method _testMultipleOutputs.

protected void _testMultipleOutputs(boolean withCounters) throws Exception {
    Path inDir = getDir(IN_DIR);
    Path outDir = getDir(OUT_DIR);
    JobConf conf = createJobConf();
    FileSystem fs = FileSystem.get(conf);
    DataOutputStream file = fs.create(new Path(inDir, "part-0"));
    file.writeBytes("a\nb\n\nc\nd\ne");
    file.close();
    file = fs.create(new Path(inDir, "part-1"));
    file.writeBytes("a\nb\n\nc\nd\ne");
    file.close();
    conf.setJobName("mo");
    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputKeyClass(LongWritable.class);
    conf.setOutputValueClass(Text.class);
    conf.setMapOutputKeyClass(LongWritable.class);
    conf.setMapOutputValueClass(Text.class);
    conf.setOutputFormat(TextOutputFormat.class);
    MultipleOutputs.addNamedOutput(conf, "text", TextOutputFormat.class, LongWritable.class, Text.class);
    MultipleOutputs.addMultiNamedOutput(conf, "sequence", SequenceFileOutputFormat.class, LongWritable.class, Text.class);
    MultipleOutputs.setCountersEnabled(conf, withCounters);
    conf.setMapperClass(MOMap.class);
    conf.setReducerClass(MOReduce.class);
    FileInputFormat.setInputPaths(conf, inDir);
    FileOutputFormat.setOutputPath(conf, outDir);
    JobClient jc = new JobClient(conf);
    RunningJob job = jc.submitJob(conf);
    while (!job.isComplete()) {
        Thread.sleep(100);
    }
    // assert number of named output part files
    int namedOutputCount = 0;
    FileStatus[] statuses = fs.listStatus(outDir);
    for (FileStatus status : statuses) {
        if (status.getPath().getName().equals("text-m-00000") || status.getPath().getName().equals("text-m-00001") || status.getPath().getName().equals("text-r-00000") || status.getPath().getName().equals("sequence_A-m-00000") || status.getPath().getName().equals("sequence_A-m-00001") || status.getPath().getName().equals("sequence_B-m-00000") || status.getPath().getName().equals("sequence_B-m-00001") || status.getPath().getName().equals("sequence_B-r-00000") || status.getPath().getName().equals("sequence_C-r-00000")) {
            namedOutputCount++;
        }
    }
    assertEquals(9, namedOutputCount);
    // assert TextOutputFormat files correctness
    BufferedReader reader = new BufferedReader(new InputStreamReader(fs.open(new Path(FileOutputFormat.getOutputPath(conf), "text-r-00000"))));
    int count = 0;
    String line = reader.readLine();
    while (line != null) {
        assertTrue(line.endsWith("text"));
        line = reader.readLine();
        count++;
    }
    reader.close();
    assertFalse(count == 0);
    // assert SequenceOutputFormat files correctness
    SequenceFile.Reader seqReader = new SequenceFile.Reader(fs, new Path(FileOutputFormat.getOutputPath(conf), "sequence_B-r-00000"), conf);
    assertEquals(LongWritable.class, seqReader.getKeyClass());
    assertEquals(Text.class, seqReader.getValueClass());
    count = 0;
    LongWritable key = new LongWritable();
    Text value = new Text();
    while (seqReader.next(key, value)) {
        assertEquals("sequence", value.toString());
        count++;
    }
    seqReader.close();
    assertFalse(count == 0);
    Counters.Group counters = job.getCounters().getGroup(MultipleOutputs.class.getName());
    if (!withCounters) {
        assertEquals(0, counters.size());
    } else {
        assertEquals(4, counters.size());
        assertEquals(4, counters.getCounter("text"));
        assertEquals(2, counters.getCounter("sequence_A"));
        assertEquals(4, counters.getCounter("sequence_B"));
        assertEquals(2, counters.getCounter("sequence_C"));
    }
}

Example 12 with JobClient

use of org.apache.hadoop.mapred.JobClient in project hive by apache.

the class Driver method getClusterStatus.

/**
   * Return the status information about the Map-Reduce cluster
   */
public ClusterStatus getClusterStatus() throws Exception {
    ClusterStatus cs;
    try {
        JobConf job = new JobConf(conf);
        JobClient jc = new JobClient(job);
        cs = jc.getClusterStatus();
    } catch (Exception e) {
        e.printStackTrace();
        throw e;
    }
    LOG.info("Returning cluster status: " + cs.toString());
    return cs;
}

Example 13 with JobClient

use of org.apache.hadoop.mapred.JobClient in project hive by apache.

the class HCatUtil method getJobTrackerDelegationToken.

public static Token<org.apache.hadoop.mapreduce.security.token.delegation.DelegationTokenIdentifier> getJobTrackerDelegationToken(Configuration conf, String userName) throws Exception {
    // LOG.info("getJobTrackerDelegationToken("+conf+","+userName+")");
    JobClient jcl = new JobClient(new JobConf(conf, HCatOutputFormat.class));
    Token<org.apache.hadoop.mapreduce.security.token.delegation.DelegationTokenIdentifier> t = jcl.getDelegationToken(new Text(userName));
    // LOG.info("got "+t);
    return t;
// return null;
}

Example 14 with JobClient

use of org.apache.hadoop.mapred.JobClient in project whirr by apache.

the class HadoopServiceTest method test.

@Test
public void test() throws Exception {
    Configuration conf = getConfiguration();
    JobConf job = new JobConf(conf, HadoopServiceTest.class);
    JobClient client = new JobClient(job);
    waitForTaskTrackers(client);
    FileSystem fs = FileSystem.get(conf);
    OutputStream os = fs.create(new Path("input"));
    Writer wr = new OutputStreamWriter(os);
    wr.write("b a\n");
    wr.close();
    job.setMapperClass(TokenCountMapper.class);
    job.setReducerClass(LongSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);
    FileInputFormat.setInputPaths(job, new Path("input"));
    FileOutputFormat.setOutputPath(job, new Path("output"));
    JobClient.runJob(job);
    FSDataInputStream in = fs.open(new Path("output/part-00000"));
    BufferedReader reader = new BufferedReader(new InputStreamReader(in));
    assertEquals("a\t1", reader.readLine());
    assertEquals("b\t1", reader.readLine());
    assertNull(reader.readLine());
    reader.close();
}

Example 15 with JobClient

use of org.apache.hadoop.mapred.JobClient in project h2o-2 by h2oai.

the class gen_flatfile method run.

@Override
public int run(String[] args) throws Exception {
    Configuration conf = getConf();
    String trackerIpPort = conf.get("mapred.job.tracker");
    // System.err.println("mapred.job.tracker: " + trackerIpPort);
    String[] arr = trackerIpPort.split(":");
    String host = arr[0];
    int port = Integer.parseInt(arr[1]);
    // System.err.println("host: " + host);
    // System.err.println("port: " + port);
    InetSocketAddress addr = new InetSocketAddress(host, port);
    JobClient client = new JobClient(addr, conf);
    Collection<String> names = client.getClusterStatus(true).getActiveTrackerNames();
    for (String name : names) {
        String n = name.substring("tracker_".length(), name.indexOf(':'));
        String s = InetAddress.getByName(n).getHostAddress();
        System.out.println(s);
    }
    return 0;
}