Package org.apache.hadoop.mapred

Examples of org.apache.hadoop.mapred.ClusterStatus


  static class GenDataFormat extends InputFormat<NullWritable,LongWritable> {

    @Override
    public List<InputSplit> getSplits(JobContext jobCtxt) throws IOException {
      final JobClient client = new JobClient(jobCtxt.getConfiguration());
      ClusterStatus stat = client.getClusterStatus(true);
      final long toGen =
        jobCtxt.getConfiguration().getLong(GRIDMIX_GEN_BYTES, -1);
      if (toGen < 0) {
        throw new IOException("Invalid/missing generation bytes: " + toGen);
      }
      final int nTrackers = stat.getTaskTrackers();
      final long bytesPerTracker = toGen / nTrackers;
      final ArrayList<InputSplit> splits = new ArrayList<InputSplit>(nTrackers);
      final Pattern trackerPattern = Pattern.compile("tracker_([^:]*):.*");
      final Matcher m = trackerPattern.matcher("");
      for (String tracker : stat.getActiveTrackerNames()) {
        m.reset(tracker);
        if (!m.find()) {
          System.err.println("Skipping node: " + tracker);
          continue;
        }
View Full Code Here


      if (numMaps > MAX_NUM_MAPS) { numMaps = MAX_NUM_MAPS; }
      if (numMaps > (int) (totalBytes / MIN_BYTES_PER_MAP)) {
        numMaps = (int) (totalBytes / MIN_BYTES_PER_MAP);
      }
      JobClient client = new JobClient(jobConf);
      ClusterStatus cluster = client.getClusterStatus();
      int tmpMaps = cluster.getTaskTrackers() * MAX_MAPS_PER_NODE;
      if (numMaps > tmpMaps) { numMaps = tmpMaps; }
      if (numMaps == 0) { numMaps = 1; }
      jobConf.setNumMapTasks(numMaps);
     
      for(int idx=0; idx < numMaps; ++idx) {
View Full Code Here

      // amount of data per map.
      int nFiles = srcPaths.length;
      int numMaps = nFiles;
      if (numMaps > MAX_NUM_MAPS) { numMaps = MAX_NUM_MAPS; }
      JobClient client = new JobClient(jobConf);
      ClusterStatus cluster = client.getClusterStatus();
      int tmpMaps = cluster.getTaskTrackers() * MAX_MAPS_PER_NODE;
      if (numMaps > tmpMaps) { numMaps = tmpMaps; }
      if (numMaps == 0) { numMaps = 1; }
      jobConf.setNumMapTasks(numMaps);
     
      jobConf.setBoolean(readFailuresAttribute, ignoreReadFailures);
View Full Code Here

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

      HiveClusterStatus hcs;
      try {
        Driver drv = new Driver();
        drv.init();

        ClusterStatus cs = drv.getClusterStatus();
        JobTrackerState state = JobTrackerState.valueOf(ShimLoader.getHadoopShims().getJobTrackerState(cs).name());

        hcs = new HiveClusterStatus(cs.getTaskTrackers(), cs.getMapTasks(), cs
            .getReduceTasks(), cs.getMaxMapTasks(), cs.getMaxReduceTasks(),
            state);
      } catch (Exception e) {
        LOG.error(e.toString());
        e.printStackTrace();
        HiveServerException ex = new HiveServerException();
View Full Code Here

        waitTaskTrackers();

        JobClient client;
        try {
            client = new JobClient(job);
            ClusterStatus status = client.getClusterStatus();
            while (status.getTaskTrackers() + numTrackerToExclude
                    < taskTrackerList.size()) {
                for (TaskTrackerRunner runner : taskTrackerList) {
                    if (runner.isDead) {
                        throw new RuntimeException("TaskTracker is dead");
                    }
View Full Code Here

            } catch (InterruptedException e) {
            }
        }

        // is the jobtracker has started then wait for it to init
        ClusterStatus status = null;
        if (jobTracker.isUp()) {
            status = jobTracker.getJobTracker().getClusterStatus(false);
            while (jobTracker.isActive() && status.getJobTrackerStatus()
                    == JobTrackerStatus.INITIALIZING) {
                try {
                    LOG.info("JobTracker still initializing. Waiting.");
                    Thread.sleep(1000);
                } catch (InterruptedException e) {
View Full Code Here

   */
  public int run(String[] args) throws Exception {

    Configuration conf = getConf();
    JobClient client = new JobClient(conf);
    ClusterStatus cluster = client.getClusterStatus();
    int num_reduces = (int) (cluster.getMaxReduceTasks() * 0.9);
    String sort_reduces = conf.get(REDUCES_PER_HOST);
    if (sort_reduces != null) {
       num_reduces = cluster.getTaskTrackers() *
                       Integer.parseInt(sort_reduces);
    }
    Class<? extends InputFormat> inputFormatClass =
      SequenceFileInputFormat.class;
    Class<? extends OutputFormat> outputFormatClass =
      SequenceFileOutputFormat.class;
    Class<? extends WritableComparable> outputKeyClass = BytesWritable.class;
    Class<? extends Writable> outputValueClass = BytesWritable.class;
    List<String> otherArgs = new ArrayList<String>();
    InputSampler.Sampler<K,V> sampler = null;
    for(int i=0; i < args.length; ++i) {
      try {
        if ("-r".equals(args[i])) {
          num_reduces = Integer.parseInt(args[++i]);
        } else if ("-inFormat".equals(args[i])) {
          inputFormatClass =
            Class.forName(args[++i]).asSubclass(InputFormat.class);
        } else if ("-outFormat".equals(args[i])) {
          outputFormatClass =
            Class.forName(args[++i]).asSubclass(OutputFormat.class);
        } else if ("-outKey".equals(args[i])) {
          outputKeyClass =
            Class.forName(args[++i]).asSubclass(WritableComparable.class);
        } else if ("-outValue".equals(args[i])) {
          outputValueClass =
            Class.forName(args[++i]).asSubclass(Writable.class);
        } else if ("-totalOrder".equals(args[i])) {
          double pcnt = Double.parseDouble(args[++i]);
          int numSamples = Integer.parseInt(args[++i]);
          int maxSplits = Integer.parseInt(args[++i]);
          if (0 >= maxSplits) maxSplits = Integer.MAX_VALUE;
          sampler =
            new InputSampler.RandomSampler<K,V>(pcnt, numSamples, maxSplits);
        } else {
          otherArgs.add(args[i]);
        }
      } catch (NumberFormatException except) {
        System.out.println("ERROR: Integer expected instead of " + args[i]);
        return printUsage();
      } catch (ArrayIndexOutOfBoundsException except) {
        System.out.println("ERROR: Required parameter missing from " +
            args[i-1]);
        return printUsage(); // exits
      }
    }
    // Set user-supplied (possibly default) job configs
    job = new Job(conf);
    job.setJobName("sorter");
    job.setJarByClass(Sort.class);

    job.setMapperClass(Mapper.class);       
    job.setReducerClass(Reducer.class);

    job.setNumReduceTasks(num_reduces);

    job.setInputFormatClass(inputFormatClass);
    job.setOutputFormatClass(outputFormatClass);

    job.setOutputKeyClass(outputKeyClass);
    job.setOutputValueClass(outputValueClass);

    // Make sure there are exactly 2 parameters left.
    if (otherArgs.size() != 2) {
      System.out.println("ERROR: Wrong number of parameters: " +
          otherArgs.size() + " instead of 2.");
      return printUsage();
    }
    FileInputFormat.setInputPaths(job, otherArgs.get(0));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs.get(1)));
   
    if (sampler != null) {
      System.out.println("Sampling input to effect total-order sort...");
      job.setPartitionerClass(TotalOrderPartitioner.class);
      Path inputDir = FileInputFormat.getInputPaths(job)[0];
      inputDir = inputDir.makeQualified(inputDir.getFileSystem(conf));
      Path partitionFile = new Path(inputDir, "_sortPartitioning");
      TotalOrderPartitioner.setPartitionFile(conf, partitionFile);
      InputSampler.<K,V>writePartitionFile(job, sampler);
      URI partitionUri = new URI(partitionFile.toString() +
                                 "#" + "_sortPartitioning");
      DistributedCache.addCacheFile(partitionUri, conf);
    }

    System.out.println("Running on " +
        cluster.getTaskTrackers() +
        " nodes to sort from " +
        FileInputFormat.getInputPaths(job)[0] + " into " +
        FileOutputFormat.getOutputPath(job) +
        " with " + num_reduces + " reduces.");
    Date startTime = new Date();
View Full Code Here

      HiveClusterStatus hcs;
      try {
        Driver drv = new Driver();
        drv.init();

        ClusterStatus cs = drv.getClusterStatus();
        JobTrackerState state = JobTrackerState.valueOf(ShimLoader.getHadoopShims().getJobTrackerState(cs).name());

        hcs = new HiveClusterStatus(cs.getTaskTrackers(), cs.getMapTasks(), cs
            .getReduceTasks(), cs.getMaxMapTasks(), cs.getMaxReduceTasks(),
            state);
      } catch (Exception e) {
        LOG.error(e.toString());
        e.printStackTrace();
        HiveServerException ex = new HiveServerException();
View Full Code Here

      if (numMaps > MAX_NUM_MAPS) { numMaps = MAX_NUM_MAPS; }
      if (numMaps > (int) (totalBytes / MIN_BYTES_PER_MAP)) {
        numMaps = (int) (totalBytes / MIN_BYTES_PER_MAP);
      }
      JobClient client = new JobClient(jobConf);
      ClusterStatus cluster = client.getClusterStatus();
      int tmpMaps = cluster.getTaskTrackers() * MAX_MAPS_PER_NODE;
      if (numMaps > tmpMaps) { numMaps = tmpMaps; }
      if (numMaps == 0) { numMaps = 1; }
      jobConf.setNumMapTasks(numMaps);
     
      for(int idx=0; idx < numMaps; ++idx) {
View Full Code Here

TOP

Related Classes of org.apache.hadoop.mapred.ClusterStatus

Copyright © 2018 www.massapicom. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.