Example usage for org.apache.hadoop.fs FileSystem delete

List of usage examples for org.apache.hadoop.fs FileSystem delete

Introduction

In this page you can find the example usage for org.apache.hadoop.fs FileSystem delete.

Prototype

public abstract boolean delete(Path f, boolean recursive) throws IOException;

Source Link

Document

Delete a file.

Usage

From source file:Text2FormatStorageMR.java

License:Open Source License

@SuppressWarnings("deprecation")
public static void main(String[] args) throws Exception {

    if (args.length != 2) {
        System.out.println("FormatFileMR <input> <output>");
        System.exit(-1);//w  w w. j a va  2  s.c o  m
    }

    JobConf conf = new JobConf(FormatStorageMR.class);

    conf.setJobName("Text2FormatMR");

    conf.setNumMapTasks(1);
    conf.setNumReduceTasks(4);

    conf.setOutputKeyClass(LongWritable.class);
    conf.setOutputValueClass(Unit.Record.class);

    conf.setMapperClass(TextFileTestMapper.class);
    conf.setReducerClass(FormatFileTestReducer.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(FormatStorageOutputFormat.class);
    conf.set("mapred.output.compress", "flase");

    Head head = new Head();
    initHead(head);

    head.toJobConf(conf);

    FileInputFormat.setInputPaths(conf, args[0]);
    Path outputPath = new Path(args[1]);
    FileOutputFormat.setOutputPath(conf, outputPath);

    FileSystem fs = outputPath.getFileSystem(conf);
    fs.delete(outputPath, true);

    JobClient jc = new JobClient(conf);
    RunningJob rj = null;
    rj = jc.submitJob(conf);

    String lastReport = "";
    SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss,SSS");
    long reportTime = System.currentTimeMillis();
    long maxReportInterval = 3 * 1000;
    while (!rj.isComplete()) {
        try {
            Thread.sleep(1000);
        } catch (InterruptedException e) {
        }

        int mapProgress = Math.round(rj.mapProgress() * 100);
        int reduceProgress = Math.round(rj.reduceProgress() * 100);

        String report = " map = " + mapProgress + "%,  reduce = " + reduceProgress + "%";

        if (!report.equals(lastReport) || System.currentTimeMillis() >= reportTime + maxReportInterval) {

            String output = dateFormat.format(Calendar.getInstance().getTime()) + report;
            System.out.println(output);
            lastReport = report;
            reportTime = System.currentTimeMillis();
        }
    }

    System.exit(0);

}

From source file:ComRoughSetApproInputSampler.java

License:Apache License

/**
 * Write a partition file for the given job, using the Sampler provided.
 * Queries the sampler for a sample keyset, sorts by the output key
 * comparator, selects the keys for each rank, and writes to the destination
 * returned from {@link TotalOrderPartitioner#getPartitionFile}.
 *//*from w  w w.  j  a v a 2 s.  co  m*/
@SuppressWarnings("unchecked") // getInputFormat, getOutputKeyComparator
public static <K, V> void writePartitionFile(Job job, Sampler<K, V> sampler)
        throws IOException, ClassNotFoundException, InterruptedException {
    Configuration conf = job.getConfiguration();
    final InputFormat inf = ReflectionUtils.newInstance(job.getInputFormatClass(), conf);
    int numPartitions = job.getNumReduceTasks();
    K[] samples = (K[]) sampler.getSample(inf, job);
    LOG.info("Using " + samples.length + " samples");
    RawComparator<K> comparator = (RawComparator<K>) job.getSortComparator();
    Arrays.sort(samples, comparator);
    Path dst = new Path(TotalOrderPartitioner.getPartitionFile(conf));
    FileSystem fs = dst.getFileSystem(conf);
    if (fs.exists(dst)) {
        fs.delete(dst, false);
    }
    SequenceFile.Writer writer = SequenceFile.createWriter(fs, conf, dst, job.getMapOutputKeyClass(),
            NullWritable.class);
    NullWritable nullValue = NullWritable.get();
    float stepSize = samples.length / (float) numPartitions;
    int last = -1;
    for (int i = 1; i < numPartitions; ++i) {
        int k = Math.round(stepSize * i);
        while (last >= k && comparator.compare(samples[last], samples[k]) == 0) {
            ++k;
        }
        writer.append(samples[k], nullValue);
        last = k;
    }
    writer.close();
}

From source file:TestIndexMergeMR.java

License:Open Source License

public void testIndexMergeMR() throws IOException {
    Configuration conf = new Configuration();
    FileSystem fs = FileSystem.get(conf);
    String indexdir = "indexdir";
    String indexdir1 = "indexdir1";
    int filenum = 10;
    int recnum = 1000;
    short idx = 0;
    TestUtil.genifdfindex(indexdir, filenum, recnum, idx, true);
    StringBuffer sb = new StringBuffer();
    FileStatus[] ss = fs.listStatus(new Path(indexdir));
    for (FileStatus fileStatus : ss) {
        sb.append(fileStatus.getPath().toString()).append(",");
    }/*from ww  w .j  ava  2s  . co m*/
    IndexMergeMR.running(sb.substring(0, sb.length() - 1), indexdir1, conf);

    IFormatDataFile ifdf = new IFormatDataFile(conf);
    ifdf.open(indexdir1 + "/part-00000");
    for (int i = 0; i < 100; i++) {
        ifdf.next().show();
    }

    ifdf.close();

    fs.delete(new Path(indexdir), true);
    fs.delete(new Path(indexdir1), true);

}

From source file:Eggshell.java

License:Open Source License

/** In charge of setting up and submitting the Hadoop job
 *  The method receives the remaining command-line arguments
 *  after first being processed by Hadoop.
 *
 * @param args        Hadoop processed command-line arguments
 * @return            Returns 0 for sucess
 *///from  w  w  w  . ja  v a  2  s .  c o m
public int run(String[] args) throws Exception {
    String name = args[0];
    String[] params = Arrays.copyOfRange(args, 1, args.length);
    Object[] arguments = Arrays.copyOf(params, params.length, Object[].class);

    script = new Script(); // start the Javascript interpreter
    script.putProperty("arguments", script.newArray(arguments));

    EggGlobal.script = script;
    Egg.script = script;
    Egg.name = name;
    Egg.conf = getConf();

    Scriptable global = script.newObject("EggGlobal", null);
    script.setGlobalScope(global);

    script.evalLibrary(); // load the Eggshell Javascript library
    script.evalFile(name); // load the javascript job file

    /* create a temporary directory in hdfs to hold the seralized functions */
    FileSystem fs = FileSystem.get(getConf());
    Path dir = new Path(SCRIPT_DIR);
    if (fs.exists(dir))
        fs.delete(dir, true);
    fs.mkdirs(dir);

    /* call the 'eggshell' function */
    Object o = script.getProperty("eggshell");
    if (o instanceof Function) {
        Scriptable thisObj = script.newObject("Egg", null);
        Function f = (Function) o;
        o = script.callFunction(f, thisObj, params);
        script.exit();

        /* return the result of the 'eggshell' function */
        if (o instanceof NativeJavaObject)
            o = ((NativeJavaObject) o).unwrap();
        if (o instanceof Boolean)
            return (Boolean) o ? 0 : 1;
        if (o instanceof Integer)
            return (Integer) o;
        if (o instanceof Double)
            return ((Double) o).intValue();
    }
    return 0;
}

From source file:LungDriver.java

License:Creative Commons License

private void cleanOutputPath(Configuration conf, String outputPath) {
    try {//from   www .j  av  a2 s.  co  m
        FileSystem fs = FileSystem.get(conf);
        Path output = new Path(outputPath);
        fs.delete(output, true);
    } catch (IOException e) {
        System.err.println("Failed to delete temporary path");
        e.printStackTrace();
    }

    System.out.println("[DONE]\n");
}

From source file:TestDistinct.java

License:Apache License

public void testDistinct() throws IOException {
    FileSystem fs = FileSystem.get(new Configuration());
    fs.delete(new Path("/tmp/test_distinct_file"), true);
    fs.delete(new Path("/tmp/test_distinct_file_results"), true);

    FSDataOutputStream out = fs.create(new Path("/tmp/test_distinct_file"));
    PrintWriter pw = new PrintWriter(out);
    pw.println("distinct1");
    pw.println("distinct2");
    pw.println("distinct2");
    pw.println("distinct3");
    pw.println("distinct2");
    pw.flush();/*from   w  w  w  . j a  v  a  2  s . c o m*/
    out.close();

    Map<String, Tap> sources = new HashMap<String, Tap>();
    Map<String, Tap> sinks = new HashMap<String, Tap>();

    Tap inTap = new Hfs(new TextLine(new Fields("line")), "/tmp/test_distinct_file");
    Pipe inPipe = new Pipe("inPipe");
    sources.put("inPipe", inTap);

    Distinct distinct = new Distinct(inPipe);

    Tap outTap = new Hfs(new TextLine(new Fields("line")), "/tmp/test_distinct_file_results");
    Pipe outPipe = new Pipe("outPipe", distinct);
    sinks.put("outPipe", outTap);

    Flow flow = new FlowConnector().connect(sources, sinks, inPipe, outPipe);
    flow.complete();

    FSDataInputStream in = fs.open(new Path("/tmp/test_distinct_file_results/part-00000"));
    BufferedReader reader = new BufferedReader(new InputStreamReader(in));

    ArrayList<String> results = new ArrayList<String>();
    results.add("distinct1");
    results.add("distinct2");
    results.add("distinct3");

    try {
        while (true) {
            String s = reader.readLine();
            if (s == null) {
                break;
            }

            assertEquals(results.remove(0), s);
        }
    } catch (Exception e) {
        fail("Got an exception while trying to verify the results: " + e.toString());
    }

    assertEquals("All results must be consumed!", 0, results.size());
}

From source file:MRDriver.java

License:Apache License

public int run(String args[]) throws Exception {
    FileSystem fs = null;
    Path samplesMapPath = null;//from  w w  w  .jav  a2  s  . c  o m

    float epsilon = Float.parseFloat(args[0]);
    double delta = Double.parseDouble(args[1]);
    int minFreqPercent = Integer.parseInt(args[2]);
    int d = Integer.parseInt(args[3]);
    int datasetSize = Integer.parseInt(args[4]);
    int numSamples = Integer.parseInt(args[5]);
    double phi = Double.parseDouble(args[6]);
    Random rand;

    /************************ Job 1 (local FIM) Configuration ************************/

    JobConf conf = new JobConf(getConf());

    /*
     * Compute the number of required "votes" for an itemsets to be
     * declared frequent    
     */
    // The +1 at the end is needed to ensure reqApproxNum > numsamples / 2.
    int reqApproxNum = (int) Math
            .floor((numSamples * (1 - phi)) - Math.sqrt(numSamples * (1 - phi) * 2 * Math.log(1 / delta))) + 1;
    int sampleSize = (int) Math.ceil((2 / Math.pow(epsilon, 2)) * (d + Math.log(1 / phi)));
    //System.out.println("reducersNum: " + numSamples + " reqApproxNum: " + reqApproxNum);

    conf.setInt("PARMM.reducersNum", numSamples);
    conf.setInt("PARMM.datasetSize", datasetSize);
    conf.setInt("PARMM.minFreqPercent", minFreqPercent);
    conf.setInt("PARMM.sampleSize", sampleSize);
    conf.setFloat("PARMM.epsilon", epsilon);

    // Set the number of reducers equal to the number of samples, to
    // maximize parallelism. Required by our Partitioner.
    conf.setNumReduceTasks(numSamples);

    // XXX: why do we disable the speculative execution? MR
    conf.setBoolean("mapred.reduce.tasks.speculative.execution", false);
    conf.setInt("mapred.task.timeout", MR_TIMEOUT_MILLI);

    /* 
     * Enable compression of map output.
     *
     * We do it for this job and not for the aggregation one because
     * each mapper there only print out one record for each itemset,
     * so there isn't much to compress, I'd say. MR
     *
     * In Amazon MapReduce compression of the map output seems to be
     * happen by default and the Snappy codec is used, which is
     * extremely fast.
     */
    conf.setBoolean("mapred.compress.map.output", true);
    //conf.setMapOutputCompressorClass(com.hadoop.compression.lzo.LzoCodec.class);

    conf.setJarByClass(MRDriver.class);

    conf.setMapOutputKeyClass(IntWritable.class);
    conf.setMapOutputValueClass(Text.class);

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(DoubleWritable.class);

    conf.setInputFormat(SequenceFileInputFormat.class);
    // We write the collections found in a reducers as a SequenceFile 
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    SequenceFileOutputFormat.setOutputPath(conf, new Path(args[9]));

    // set the mapper class based on command line option
    switch (Integer.parseInt(args[7])) {
    case 1:
        System.out.println("running partition mapper...");
        SequenceFileInputFormat.addInputPath(conf, new Path(args[8]));
        conf.setMapperClass(PartitionMapper.class);
        break;
    case 2:
        System.out.println("running binomial mapper...");
        SequenceFileInputFormat.addInputPath(conf, new Path(args[8]));
        conf.setMapperClass(BinomialSamplerMapper.class);
        break;
    case 3:
        System.out.println("running coin mapper...");
        SequenceFileInputFormat.addInputPath(conf, new Path(args[8]));
        conf.setMapperClass(CoinFlipSamplerMapper.class);
    case 4:
        System.out.println("running sampler mapper...");
        SequenceFileInputFormat.addInputPath(conf, new Path(args[8]));
        conf.setMapperClass(InputSamplerMapper.class);

        // create a random sample of size T*m
        rand = new Random();
        long sampling_start_time = System.nanoTime();
        int[] samples = new int[numSamples * sampleSize];
        for (int i = 0; i < numSamples * sampleSize; i++) {
            samples[i] = rand.nextInt(datasetSize);
        }

        // for each key in the sample, create a list of all T samples to which this key belongs
        Hashtable<LongWritable, ArrayList<IntWritable>> hashTable = new Hashtable<LongWritable, ArrayList<IntWritable>>();
        for (int i = 0; i < numSamples * sampleSize; i++) {
            ArrayList<IntWritable> sampleIDs = null;
            LongWritable key = new LongWritable(samples[i]);
            if (hashTable.containsKey(key))
                sampleIDs = hashTable.get(key);
            else
                sampleIDs = new ArrayList<IntWritable>();
            sampleIDs.add(new IntWritable(i % numSamples));
            hashTable.put(key, sampleIDs);
        }

        /*
         * Convert the Hastable to a MapWritable which we will
         * write to HDFS and distribute to all Mappers using
         * DistributedCache
         */
        MapWritable map = new MapWritable();
        for (LongWritable key : hashTable.keySet()) {
            ArrayList<IntWritable> sampleIDs = hashTable.get(key);
            IntArrayWritable sampleIDsIAW = new IntArrayWritable();
            sampleIDsIAW.set(sampleIDs.toArray(new IntWritable[sampleIDs.size()]));
            map.put(key, sampleIDsIAW);
        }

        fs = FileSystem.get(URI.create("samplesMap.ser"), conf);
        samplesMapPath = new Path("samplesMap.ser");
        FSDataOutputStream out = fs.create(samplesMapPath, true);
        map.write(out);
        out.sync();
        out.close();
        DistributedCache.addCacheFile(new URI(fs.getWorkingDirectory() + "/samplesMap.ser#samplesMap.ser"),
                conf);
        // stop the sampling timer   
        long sampling_end_time = System.nanoTime();
        long sampling_runtime = (sampling_end_time - sampling_start_time) / 1000000;
        System.out.println("sampling runtime (milliseconds): " + sampling_runtime);
        break; // end switch case
    case 5:
        System.out.println("running random integer partition mapper...");
        conf.setInputFormat(WholeSplitInputFormat.class);
        Path inputFilePath = new Path(args[8]);
        WholeSplitInputFormat.addInputPath(conf, inputFilePath);
        conf.setMapperClass(RandIntPartSamplerMapper.class);
        // Compute number of map tasks.
        fs = inputFilePath.getFileSystem(conf);
        FileStatus inputFileStatus = fs.getFileStatus(inputFilePath);
        long len = inputFileStatus.getLen();
        long blockSize = inputFileStatus.getBlockSize();
        conf.setLong("mapred.min.split.size", blockSize);
        conf.setLong("mapred.max.split.size", blockSize);
        int mapTasksNum = ((int) (len / blockSize)) + 1;
        conf.setNumMapTasks(mapTasksNum);
        //System.out.println("len: " + len + " blockSize: " 
        //      + blockSize + " mapTasksNum: " + mapTasksNum);
        // Extract random integer partition of total sample
        // size into up to mapTasksNum partitions.
        // XXX I'm not sure this is a correct way to do
        // it.
        rand = new Random();
        IntWritable[][] toSampleArr = new IntWritable[mapTasksNum][numSamples];
        for (int j = 0; j < numSamples; j++) {
            IntWritable[] tempToSampleArr = new IntWritable[mapTasksNum];
            int sum = 0;
            int i;
            for (i = 0; i < mapTasksNum - 1; i++) {
                int size = rand.nextInt(sampleSize - sum);
                tempToSampleArr[i] = new IntWritable(size);
                sum += size;
                if (sum > numSamples * sampleSize) {
                    System.out.println("Something went wrong generating the sample Sizes");
                    System.exit(1);
                }
                if (sum == sampleSize) {
                    break;
                }
            }
            if (i == mapTasksNum - 1) {
                tempToSampleArr[i] = new IntWritable(sampleSize - sum);
            } else {
                for (; i < mapTasksNum; i++) {
                    tempToSampleArr[i] = new IntWritable(0);
                }
            }
            Collections.shuffle(Arrays.asList(tempToSampleArr));
            for (i = 0; i < mapTasksNum; i++) {
                toSampleArr[i][j] = tempToSampleArr[i];
            }
        }

        for (int i = 0; i < mapTasksNum; i++) {
            DefaultStringifier.storeArray(conf, toSampleArr[i], "PARMM.toSampleArr_" + i);
        }
        break;
    default:
        System.err.println("Wrong Mapper ID. Can only be in [1,5]");
        System.exit(1);
        break;
    }

    /*
     * We don't use the default hash partitioner because we want to
     * maximize the parallelism. That's why we also fix the number
     * of reducers.
     */
    conf.setPartitionerClass(FIMPartitioner.class);

    conf.setReducerClass(FIMReducer.class);

    /************************ Job 2 (aggregation) Configuration ************************/

    JobConf confAggr = new JobConf(getConf());

    confAggr.setInt("PARMM.reducersNum", numSamples);
    confAggr.setInt("PARMM.reqApproxNum", reqApproxNum);
    confAggr.setInt("PARMM.sampleSize", sampleSize);
    confAggr.setFloat("PARMM.epsilon", epsilon);

    // XXX: Why do we disable speculative execution? MR
    confAggr.setBoolean("mapred.reduce.tasks.speculative.execution", false);
    confAggr.setInt("mapred.task.timeout", MR_TIMEOUT_MILLI);

    confAggr.setJarByClass(MRDriver.class);

    confAggr.setMapOutputKeyClass(Text.class);
    confAggr.setMapOutputValueClass(DoubleWritable.class);

    confAggr.setOutputKeyClass(Text.class);
    confAggr.setOutputValueClass(Text.class);

    confAggr.setMapperClass(AggregateMapper.class);
    confAggr.setReducerClass(AggregateReducer.class);

    confAggr.setInputFormat(CombineSequenceFileInputFormat.class);
    SequenceFileInputFormat.addInputPath(confAggr, new Path(args[9]));

    FileOutputFormat.setOutputPath(confAggr, new Path(args[10]));

    long FIMjob_start_time = System.currentTimeMillis();
    RunningJob FIMjob = JobClient.runJob(conf);
    long FIMjob_end_time = System.currentTimeMillis();

    RunningJob aggregateJob = JobClient.runJob(confAggr);
    long aggrJob_end_time = System.currentTimeMillis();

    long FIMjob_runtime = FIMjob_end_time - FIMjob_start_time;

    long aggrJob_runtime = aggrJob_end_time - FIMjob_end_time;

    if (args[7].equals("4")) {
        // Remove samplesMap file 
        fs.delete(samplesMapPath, false);
    }

    Counters counters = FIMjob.getCounters();
    Counters.Group FIMMapperStartTimesCounters = counters.getGroup("FIMMapperStart");
    long[] FIMMapperStartTimes = new long[FIMMapperStartTimesCounters.size()];
    int i = 0;
    for (Counters.Counter counter : FIMMapperStartTimesCounters) {
        FIMMapperStartTimes[i++] = counter.getCounter();
    }

    Counters.Group FIMMapperEndTimesCounters = counters.getGroup("FIMMapperEnd");
    long[] FIMMapperEndTimes = new long[FIMMapperEndTimesCounters.size()];
    i = 0;
    for (Counters.Counter counter : FIMMapperEndTimesCounters) {
        FIMMapperEndTimes[i++] = counter.getCounter();
    }

    Counters.Group FIMReducerStartTimesCounters = counters.getGroup("FIMReducerStart");
    long[] FIMReducerStartTimes = new long[FIMReducerStartTimesCounters.size()];
    i = 0;
    for (Counters.Counter counter : FIMReducerStartTimesCounters) {
        FIMReducerStartTimes[i++] = counter.getCounter();
    }

    Counters.Group FIMReducerEndTimesCounters = counters.getGroup("FIMReducerEnd");
    long[] FIMReducerEndTimes = new long[FIMReducerEndTimesCounters.size()];
    i = 0;
    for (Counters.Counter counter : FIMReducerEndTimesCounters) {
        FIMReducerEndTimes[i++] = counter.getCounter();
    }

    Counters countersAggr = aggregateJob.getCounters();
    Counters.Group AggregateMapperStartTimesCounters = countersAggr.getGroup("AggregateMapperStart");
    long[] AggregateMapperStartTimes = new long[AggregateMapperStartTimesCounters.size()];
    i = 0;
    for (Counters.Counter counter : AggregateMapperStartTimesCounters) {
        AggregateMapperStartTimes[i++] = counter.getCounter();
    }

    Counters.Group AggregateMapperEndTimesCounters = countersAggr.getGroup("AggregateMapperEnd");
    long[] AggregateMapperEndTimes = new long[AggregateMapperEndTimesCounters.size()];
    i = 0;
    for (Counters.Counter counter : AggregateMapperEndTimesCounters) {
        AggregateMapperEndTimes[i++] = counter.getCounter();
    }

    Counters.Group AggregateReducerStartTimesCounters = countersAggr.getGroup("AggregateReducerStart");
    long[] AggregateReducerStartTimes = new long[AggregateReducerStartTimesCounters.size()];
    i = 0;
    for (Counters.Counter counter : AggregateReducerStartTimesCounters) {
        AggregateReducerStartTimes[i++] = counter.getCounter();
    }

    Counters.Group AggregateReducerEndTimesCounters = countersAggr.getGroup("AggregateReducerEnd");
    long[] AggregateReducerEndTimes = new long[AggregateReducerEndTimesCounters.size()];
    i = 0;
    for (Counters.Counter counter : AggregateReducerEndTimesCounters) {
        AggregateReducerEndTimes[i++] = counter.getCounter();
    }

    long FIMMapperStartMin = FIMMapperStartTimes[0];
    for (long l : FIMMapperStartTimes) {
        if (l < FIMMapperStartMin) {
            FIMMapperStartMin = l;
        }
    }
    long FIMMapperEndMax = FIMMapperEndTimes[0];
    for (long l : FIMMapperEndTimes) {
        if (l > FIMMapperEndMax) {
            FIMMapperEndMax = l;
        }
    }
    System.out.println("FIM job setup time (milliseconds): " + (FIMMapperStartMin - FIMjob_start_time));
    System.out.println("FIMMapper total runtime (milliseconds): " + (FIMMapperEndMax - FIMMapperStartMin));
    long[] FIMMapperRunTimes = new long[FIMMapperStartTimes.length];
    long FIMMapperRunTimesSum = 0;
    for (int l = 0; l < FIMMapperStartTimes.length; l++) {
        FIMMapperRunTimes[l] = FIMMapperEndTimes[l] - FIMMapperStartTimes[l];
        FIMMapperRunTimesSum += FIMMapperRunTimes[l];
    }
    System.out.println("FIMMapper average task runtime (milliseconds): "
            + FIMMapperRunTimesSum / FIMMapperStartTimes.length);
    long FIMMapperRunTimesMin = FIMMapperRunTimes[0];
    long FIMMapperRunTimesMax = FIMMapperRunTimes[0];
    for (long l : FIMMapperRunTimes) {
        if (l < FIMMapperRunTimesMin) {
            FIMMapperRunTimesMin = l;
        }
        if (l > FIMMapperRunTimesMax) {
            FIMMapperRunTimesMax = l;
        }
    }
    System.out.println("FIMMapper minimum task runtime (milliseconds): " + FIMMapperRunTimesMin);
    System.out.println("FIMMapper maximum task runtime (milliseconds): " + FIMMapperRunTimesMax);

    long FIMReducerStartMin = FIMReducerStartTimes[0];
    for (long l : FIMReducerStartTimes) {
        if (l < FIMReducerStartMin) {
            FIMReducerStartMin = l;
        }
    }
    long FIMReducerEndMax = FIMReducerEndTimes[0];
    for (long l : FIMReducerEndTimes) {
        if (l > FIMReducerEndMax) {
            FIMReducerEndMax = l;
        }
    }
    System.out
            .println("FIM job shuffle phase runtime (milliseconds): " + (FIMReducerStartMin - FIMMapperEndMax));
    System.out.println("FIMReducer total runtime (milliseconds): " + (FIMReducerEndMax - FIMReducerStartMin));
    long[] FIMReducerRunTimes = new long[FIMReducerStartTimes.length];
    long FIMReducerRunTimesSum = 0;
    for (int l = 0; l < FIMReducerStartTimes.length; l++) {
        FIMReducerRunTimes[l] = FIMReducerEndTimes[l] - FIMReducerStartTimes[l];
        FIMReducerRunTimesSum += FIMReducerRunTimes[l];
    }
    System.out.println("FIMReducer average task runtime (milliseconds): "
            + FIMReducerRunTimesSum / FIMReducerStartTimes.length);
    long FIMReducerRunTimesMin = FIMReducerRunTimes[0];
    long FIMReducerRunTimesMax = FIMReducerRunTimes[0];
    for (long l : FIMReducerRunTimes) {
        if (l < FIMReducerRunTimesMin) {
            FIMReducerRunTimesMin = l;
        }
        if (l > FIMReducerRunTimesMax) {
            FIMReducerRunTimesMax = l;
        }
    }
    System.out.println("FIMReducer minimum task runtime (milliseconds): " + FIMReducerRunTimesMin);
    System.out.println("FIMReducer maximum task runtime (milliseconds): " + FIMReducerRunTimesMax);
    System.out.println("FIM job cooldown time (milliseconds): " + (FIMjob_end_time - FIMReducerEndMax));

    long AggregateMapperStartMin = AggregateMapperStartTimes[0];
    for (long l : AggregateMapperStartTimes) {
        if (l < AggregateMapperStartMin) {
            AggregateMapperStartMin = l;
        }
    }
    long AggregateMapperEndMax = AggregateMapperEndTimes[0];
    for (long l : AggregateMapperEndTimes) {
        if (l > AggregateMapperEndMax) {
            AggregateMapperEndMax = l;
        }
    }
    System.out.println(
            "Aggregation job setup time (milliseconds): " + (AggregateMapperStartMin - FIMjob_end_time));
    System.out.println("AggregateMapper total runtime (milliseconds): "
            + (AggregateMapperEndMax - AggregateMapperStartMin));
    long[] AggregateMapperRunTimes = new long[AggregateMapperStartTimes.length];
    long AggregateMapperRunTimesSum = 0;
    for (int l = 0; l < AggregateMapperStartTimes.length; l++) {
        AggregateMapperRunTimes[l] = AggregateMapperEndTimes[l] - AggregateMapperStartTimes[l];
        AggregateMapperRunTimesSum += AggregateMapperRunTimes[l];
    }
    System.out.println("AggregateMapper average task runtime (milliseconds): "
            + AggregateMapperRunTimesSum / AggregateMapperStartTimes.length);
    long AggregateMapperRunTimesMin = AggregateMapperRunTimes[0];
    long AggregateMapperRunTimesMax = AggregateMapperRunTimes[0];
    for (long l : AggregateMapperRunTimes) {
        if (l < AggregateMapperRunTimesMin) {
            AggregateMapperRunTimesMin = l;
        }
        if (l > AggregateMapperRunTimesMax) {
            AggregateMapperRunTimesMax = l;
        }
    }
    System.out.println("AggregateMapper minimum task runtime (milliseconds): " + AggregateMapperRunTimesMin);
    System.out.println("AggregateMapper maximum task runtime (milliseconds): " + AggregateMapperRunTimesMax);

    long AggregateReducerStartMin = AggregateReducerStartTimes[0];
    for (long l : AggregateReducerStartTimes) {
        if (l < AggregateReducerStartMin) {
            AggregateReducerStartMin = l;
        }
    }
    long AggregateReducerEndMax = AggregateReducerEndTimes[0];
    for (long l : AggregateReducerEndTimes) {
        if (l > AggregateReducerEndMax) {
            AggregateReducerEndMax = l;
        }
    }
    System.out.println("Aggregate job round shuffle phase runtime (milliseconds): "
            + (AggregateReducerStartMin - AggregateMapperEndMax));
    System.out.println("AggregateReducer total runtime (milliseconds): "
            + (AggregateReducerEndMax - AggregateReducerStartMin));
    long[] AggregateReducerRunTimes = new long[AggregateReducerStartTimes.length];
    long AggregateReducerRunTimesSum = 0;
    for (int l = 0; l < AggregateReducerStartTimes.length; l++) {
        AggregateReducerRunTimes[l] = AggregateReducerEndTimes[l] - AggregateReducerStartTimes[l];
        AggregateReducerRunTimesSum += AggregateReducerRunTimes[l];
    }
    System.out.println("AggregateReducer average task runtime (milliseconds): "
            + AggregateReducerRunTimesSum / AggregateReducerStartTimes.length);
    long AggregateReducerRunTimesMin = AggregateReducerRunTimes[0];
    long AggregateReducerRunTimesMax = AggregateReducerRunTimes[0];
    for (long l : AggregateReducerRunTimes) {
        if (l < AggregateReducerRunTimesMin) {
            AggregateReducerRunTimesMin = l;
        }
        if (l > AggregateReducerRunTimesMax) {
            AggregateReducerRunTimesMax = l;
        }
    }
    System.out.println("AggregateReducer minimum task runtime (milliseconds): " + AggregateReducerRunTimesMin);
    System.out.println("AggregateReducer maximum task runtime (milliseconds): " + AggregateReducerRunTimesMax);

    System.out.println(
            "Aggregation job cooldown time (milliseconds): " + (aggrJob_end_time - AggregateReducerEndMax));

    System.out
            .println("total runtime (all inclusive) (milliseconds): " + (aggrJob_end_time - FIMjob_start_time));
    System.out.println("total runtime (no FIM job setup, no aggregation job cooldown) (milliseconds): "
            + (AggregateReducerEndMax - FIMMapperStartMin));
    System.out.println("total runtime (no setups, no cooldowns) (milliseconds): "
            + (FIMReducerEndMax - FIMMapperStartMin + AggregateReducerEndMax - AggregateMapperStartMin));
    System.out.println("FIM job runtime (including setup and cooldown) (milliseconds): " + FIMjob_runtime);
    System.out.println("FIM job runtime (no setup, no cooldown) (milliseconds): "
            + (FIMReducerEndMax - FIMMapperStartMin));
    System.out.println(
            "Aggregation job runtime (including setup and cooldown) (milliseconds): " + aggrJob_runtime);
    System.out.println("Aggregation job runtime (no setup, no cooldown) (milliseconds): "
            + (AggregateReducerEndMax - AggregateMapperStartMin));

    return 0;
}

From source file:Text2ColumntStorageMR.java

License:Open Source License

@SuppressWarnings("deprecation")
public static void main(String[] args) throws Exception {

    if (args.length != 3) {
        System.out.println("Text2ColumnStorageMR <input> <output> <columnStorageMode>");
        System.exit(-1);// ww  w .j a  v  a 2s.c  o m
    }

    JobConf conf = new JobConf(Text2ColumntStorageMR.class);

    conf.setJobName("Text2ColumnStorageMR");

    conf.setNumMapTasks(1);
    conf.setNumReduceTasks(4);

    conf.setOutputKeyClass(LongWritable.class);
    conf.setOutputValueClass(Unit.Record.class);

    conf.setMapperClass(TextFileMapper.class);
    conf.setReducerClass(ColumnStorageReducer.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat((Class<? extends OutputFormat>) ColumnStorageHiveOutputFormat.class);
    conf.set("mapred.output.compress", "flase");

    Head head = new Head();
    initHead(head);

    head.toJobConf(conf);

    int bt = Integer.valueOf(args[2]);

    FileInputFormat.setInputPaths(conf, args[0]);
    Path outputPath = new Path(args[1]);
    FileOutputFormat.setOutputPath(conf, outputPath);

    FileSystem fs = outputPath.getFileSystem(conf);
    fs.delete(outputPath, true);

    JobClient jc = new JobClient(conf);
    RunningJob rj = null;
    rj = jc.submitJob(conf);

    String lastReport = "";
    SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss,SSS");
    long reportTime = System.currentTimeMillis();
    long maxReportInterval = 3 * 1000;
    while (!rj.isComplete()) {
        try {
            Thread.sleep(1000);
        } catch (InterruptedException e) {
        }

        int mapProgress = Math.round(rj.mapProgress() * 100);
        int reduceProgress = Math.round(rj.reduceProgress() * 100);

        String report = " map = " + mapProgress + "%,  reduce = " + reduceProgress + "%";

        if (!report.equals(lastReport) || System.currentTimeMillis() >= reportTime + maxReportInterval) {

            String output = dateFormat.format(Calendar.getInstance().getTime()) + report;
            System.out.println(output);
            lastReport = report;
            reportTime = System.currentTimeMillis();
        }
    }

    System.exit(0);

}

From source file:BwaInterpreter.java

License:Open Source License

private void createOutputFolder() {
    try {/*  w  ww.ja  v a  2  s . c om*/
        FileSystem fs = FileSystem.get(this.conf);

        // Path variable
        Path outputDir = new Path(options.getOutputPath());

        // Directory creation
        if (!fs.exists(outputDir)) {
            fs.mkdirs(outputDir);
        } else {
            fs.delete(outputDir, true);
            fs.mkdirs(outputDir);
        }

        fs.close();
    } catch (IOException e) {
        LOG.error(e.toString());
        e.printStackTrace();
    }
}

From source file:BwaInterpreter.java

License:Open Source License

private void combineOutputSamFiles(String outputHdfsDir, List<String> returnedValues) {
    try {/*from  w ww  .  jav  a  2s  . co  m*/
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(conf);

        Path finalHdfsOutputFile = new Path(outputHdfsDir + "/FullOutput.sam");
        FSDataOutputStream outputFinalStream = fs.create(finalHdfsOutputFile, true);

        // We iterate over the resulting files in HDFS and agregate them into only one file.
        for (int i = 0; i < returnedValues.size(); i++) {
            LOG.info("JMAbuin:: SparkBWA :: Returned file ::" + returnedValues.get(i));
            BufferedReader br = new BufferedReader(
                    new InputStreamReader(fs.open(new Path(returnedValues.get(i)))));

            String line;
            line = br.readLine();

            while (line != null) {
                if (i == 0 || !line.startsWith("@")) {
                    //outputFinalStream.writeBytes(line+"\n");
                    outputFinalStream.write((line + "\n").getBytes());
                }

                line = br.readLine();
            }
            br.close();

            fs.delete(new Path(returnedValues.get(i)), true);
        }

        outputFinalStream.close();
        fs.close();
    } catch (IOException e) {
        e.printStackTrace();
        LOG.error(e.toString());
    }
}