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

Introduction

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

Prototype

public void setNumReduceTasks(int n) 

Source Link

Document

Set the requisite number of reduce tasks for this job.

Usage

From source file:fr.ens.biologie.genomique.eoulsan.modules.mgmt.hadoop.DistCp.java

License:LGPL

private static JobConf createJobConf(final Configuration conf) {
    JobConf jobconf = new JobConf(conf, DistCp.class);
    jobconf.setJobName(NAME);//w ww . java2 s.c om

    // turn off speculative execution, because DFS doesn't handle
    // multiple writers to the same file.
    jobconf.setMapSpeculativeExecution(false);

    jobconf.setInputFormat(CopyInputFormat.class);
    jobconf.setOutputKeyClass(Text.class);
    jobconf.setOutputValueClass(Text.class);

    jobconf.setMapperClass(CopyFilesMapper.class);
    jobconf.setNumReduceTasks(0);
    return jobconf;
}

---

From source file:fr.mines_nantes.atlanmod.monitoring.frameworks.TeraGen.java

License:Apache License

/**
 * @param args the cli arguments//w  w  w.  jav  a2  s.co  m
 */
public int run(String[] args) throws IOException {

    JobConf job = (JobConf) getConf();
    setNumberOfRows(job, Long.parseLong(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    job.setJobName("TeraGen");
    job.setJarByClass(TeraGen.class);
    job.setMapperClass(SortGenMapper.class);
    job.setNumReduceTasks(0);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    job.setInputFormat(RangeInputFormat.class);
    //job.setOutputFormat(TeraOutputFormat.class);
    JobClient.runJob(job);
    return 0;
}

---

From source file:gaffer.accumulostore.operation.hdfs.handler.job.factory.SampleDataForSplitPointsJobFactory.java

License:Apache License

protected void setupJobConf(final JobConf jobConf, final SampleDataForSplitPoints operation, final Store store)
        throws IOException {
    jobConf.set(SCHEMA, new String(store.getSchema().toJson(false), CommonConstants.UTF_8));
    jobConf.set(MAPPER_GENERATOR, operation.getMapperGeneratorClassName());
    jobConf.set(VALIDATE, String.valueOf(operation.isValidate()));
    jobConf.set(PROPORTION_TO_SAMPLE, String.valueOf(operation.getProportionToSample()));
    jobConf.set(AccumuloStoreConstants.ACCUMULO_ELEMENT_CONVERTER_CLASS,
            ((AccumuloStore) store).getKeyPackage().getKeyConverter().getClass().getName());
    Integer numTasks = operation.getNumMapTasks();
    if (null != numTasks) {
        jobConf.setNumMapTasks(numTasks);
    }//from w  w  w. j a  v a2 s  . co m
    jobConf.setNumReduceTasks(1);
}

---

From source file:gaffer.accumulostore.operation.hdfs.handler.job.SampleDataForSplitPointsJobFactory.java

License:Apache License

protected void setupJobConf(final JobConf jobConf, final SampleDataForSplitPoints operation, final Store store)
        throws IOException {
    jobConf.set(SCHEMA, new String(store.getSchema().toJson(false), CommonConstants.UTF_8));
    jobConf.set(MAPPER_GENERATOR, operation.getMapperGeneratorClassName());
    jobConf.set(VALIDATE, String.valueOf(operation.isValidate()));
    jobConf.set(PROPORTION_TO_SAMPLE, String.valueOf(operation.getProportionToSample()));
    Integer numTasks = operation.getNumMapTasks();
    if (null != numTasks) {
        jobConf.setNumMapTasks(numTasks);
    }//ww  w.  ja  v a  2  s .  co  m
    numTasks = operation.getNumReduceTasks();
    if (null != numTasks) {
        jobConf.setNumReduceTasks(numTasks);
    }
}

---

From source file:gaffer.operation.simple.hdfs.handler.AbstractAddElementsFromHdfsJobFactory.java

License:Apache License

protected void setupJobConf(final JobConf jobConf, final AddElementsFromHdfs operation, final Store store)
        throws IOException {
    jobConf.set(DATA_SCHEMA, new String(store.getDataSchema().toJson(false), UTF_8_CHARSET));
    jobConf.set(STORE_SCHEMA, new String(store.getStoreSchema().toJson(false), UTF_8_CHARSET));
    jobConf.set(MAPPER_GENERATOR, operation.getMapperGeneratorClassName());
    jobConf.set(VALIDATE, String.valueOf(operation.isValidate()));
    Integer numTasks = operation.getNumMapTasks();
    if (null != numTasks) {
        jobConf.setNumMapTasks(numTasks);
    }/*from   w w  w .  j a  v a2  s. c  om*/
    numTasks = operation.getNumReduceTasks();
    if (null != numTasks) {
        jobConf.setNumReduceTasks(numTasks);
    }
}

---

From source file:gaffer.operation.simple.hdfs.handler.job.factory.AbstractAddElementsFromHdfsJobFactory.java

License:Apache License

protected void setupJobConf(final JobConf jobConf, final AddElementsFromHdfs operation, final Store store)
        throws IOException {
    LOGGER.info("Setting up job conf");
    jobConf.set(SCHEMA, new String(store.getSchema().toJson(false), CommonConstants.UTF_8));
    LOGGER.info("Added {} {} to job conf", SCHEMA,
            new String(store.getSchema().toJson(false), CommonConstants.UTF_8));
    jobConf.set(MAPPER_GENERATOR, operation.getMapperGeneratorClassName());
    LOGGER.info("Added {} of {} to job conf", MAPPER_GENERATOR, operation.getMapperGeneratorClassName());
    jobConf.set(VALIDATE, String.valueOf(operation.isValidate()));
    LOGGER.info("Added {} option of {} to job conf", VALIDATE, operation.isValidate());
    Integer numTasks = operation.getNumMapTasks();
    if (null != numTasks) {
        jobConf.setNumMapTasks(numTasks);
        LOGGER.info("Set number of map tasks to {} on job conf", numTasks);
    }/*  www.  j av a  2  s .  c  o  m*/
    numTasks = operation.getNumReduceTasks();
    if (null != numTasks) {
        jobConf.setNumReduceTasks(numTasks);
        LOGGER.info("Set number of reduce tasks to {} on job conf", numTasks);
    }
}

---

From source file:gr.forth.ics.isl.grouprecsmr.multiuser.MultiUserMain.java

public static void main(String[] args) {
    //paths and input handling
    Path inputRatingsPath = new Path(args[0]); //movieid, userid, rating (text files)
    Path job1OutputPath = new Path("/user/hduser/partialResults");
    Path partialDistancesPath = new Path("/user/hduser/partialResults/part-*"); //member_nonMember \t partialDistance (sequence files)
    Path candidateMoviesPath = new Path("/user/hduser/partialResults/candidateMovies-*"); //candidateMovieId, nonMemberUserId_rating (text files)
    Path userSimilaritiesPath = new Path("/user/hduser/userSimilarities"); //similarity of each group member to his friends (text files)
    Path finalScoresPath = new Path(args[1]); //movieId \t outputScore

    int numReduceTasks = 56; //defaultValue
    if (args.length == 3) {
        numReduceTasks = Integer.parseInt(args[2]);
    }/*w w w  . jav  a 2s .  com*/

    final float friendsSimThresh = 0.8f;

    String groupFilePath = "/user/hduser/group.txt"; //one-line csv file with user ids (text file)

    if (args.length < 2 || args.length > 3) {
        System.err.println(
                "Incorrect input. Example usage: hadoop jar ~/GroupRecs/MultiUser.jar inputPath outputPath [numReduceTasks]");
        return;
    }

    //JOB 1//
    JobClient client = new JobClient();
    JobConf conf = new JobConf(gr.forth.ics.isl.grouprecsmr.multiuser.MultiUserMain.class);

    try {
        FileSystem fs = FileSystem.get(conf);
        if (fs.exists(job1OutputPath)) {
            fs.delete(job1OutputPath, true);
        }
        if (fs.exists(userSimilaritiesPath)) {
            fs.delete(userSimilaritiesPath, true);
        }
        if (fs.exists(finalScoresPath)) {
            fs.delete(finalScoresPath, true);
        }
    } catch (IOException ex) {
        Logger.getLogger(MultiUserMain.class.getName()).log(Level.SEVERE, null, ex);
    }

    conf.setJobName("Multi-user approach - Job 1");
    System.out.println("Starting Job 1 (Multi-user approach)...");

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

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

    conf.setInputFormat(TextInputFormat.class);
    //conf.setOutputFormat(TextOutputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    SequenceFileOutputFormat.setOutputCompressionType(conf, SequenceFile.CompressionType.BLOCK);

    FileInputFormat.setInputPaths(conf, inputRatingsPath); //user ratings
    FileOutputFormat.setOutputPath(conf, job1OutputPath); //partial distances

    MultipleOutputs.addNamedOutput(conf, "candidateMovies", SequenceFileOutputFormat.class, VIntWritable.class,
            Text.class); //movieId, userId_rating

    conf.setMapperClass(gr.forth.ics.isl.grouprecsmr.job1.Job1Mapper.class);
    conf.setReducerClass(gr.forth.ics.isl.grouprecsmr.job1.Job1Reducer.class);

    conf.setNumReduceTasks(numReduceTasks);

    try {
        DistributedCache.addCacheFile(new URI(groupFilePath), conf); // group   
    } catch (URISyntaxException e1) {
        System.err.println(e1.toString());
    }

    conf.setInt("mapred.task.timeout", 6000000);

    client.setConf(conf);
    RunningJob job;
    try {
        job = JobClient.runJob(conf);
        job.waitForCompletion();
    } catch (Exception e) {
        System.err.println(e);
    }

    //JOB 2//
    System.out.println("Starting Job 2 (Multi-user approach)...");
    JobClient client2 = new JobClient();
    JobConf conf2 = new JobConf(gr.forth.ics.isl.grouprecsmr.multiuser.MultiUserMain.class);

    conf2.setJobName("Multi-user approach - Job 2");

    conf2.setMapOutputKeyClass(Text.class); //user pair (member_nonMember), where nonMember is in friends
    conf2.setMapOutputValueClass(ByteWritable.class);//similarity part unsquared

    conf2.setOutputKeyClass(Text.class); //user pair (member_nonMember), where nonMember is in friends
    conf2.setOutputValueClass(DoubleWritable.class);//similarity

    conf2.setInputFormat(SequenceFileInputFormat.class);
    //conf2.setInputFormat(TextInputFormat.class);
    conf2.setOutputFormat(TextOutputFormat.class);
    //conf2.setOutputFormat(SequenceFileOutputFormat.class);
    //SequenceFileOutputFormat.setOutputCompressionType(conf2, SequenceFile.CompressionType.BLOCK);

    FileInputFormat.setInputPaths(conf2, partialDistancesPath); //Job 1 output
    FileOutputFormat.setOutputPath(conf2, userSimilaritiesPath); //Job 2 output (similarity of each group member to his friends)

    conf2.setMapperClass(IdentityMapper.class);
    conf2.setReducerClass(gr.forth.ics.isl.grouprecsmr.job2.Job2ReducerMulti.class);

    int numSimilaritiesPartitions = numReduceTasks;
    conf2.setNumReduceTasks(numSimilaritiesPartitions);

    conf2.setFloat("friendsSimThreshold", friendsSimThresh);

    conf2.setInt("mapred.task.timeout", 6000000);
    conf2.set("io.sort.mb", "500");

    client2.setConf(conf2);
    RunningJob job2;
    try {
        job2 = JobClient.runJob(conf2);
        job2.waitForCompletion();
    } catch (Exception e) {
        System.err.println(e);
    }

    //JOB 3//
    System.out.println("Starting Job 3 (Multi-user approach)...");
    JobClient client3 = new JobClient();
    JobConf conf3 = new JobConf(gr.forth.ics.isl.grouprecsmr.multiuser.MultiUserMain.class);

    conf3.setJobName("Multi-user approach - Job 3");

    conf3.setMapOutputKeyClass(VIntWritable.class);
    conf3.setMapOutputValueClass(Text.class);

    conf3.setOutputKeyClass(VIntWritable.class);
    conf3.setOutputValueClass(DoubleWritable.class);

    conf3.setInputFormat(SequenceFileInputFormat.class);
    //conf3.setInputFormat(TextInputFormat.class);
    conf3.setOutputFormat(TextOutputFormat.class);
    //conf3.setOutputFormat(SequenceFileOutputFormat.class);
    //SequenceFileOutputFormat.setOutputCompressionType(conf3,SequenceFile.CompressionType.BLOCK);

    try {
        DistributedCache.addCacheFile(new URI(groupFilePath), conf3);
    } catch (URISyntaxException ex) {
        System.err.println("Could not add group file to distributed cache. " + ex);
    }
    for (int i = 0; i < numSimilaritiesPartitions; i++) {
        String reduceId = String.format("%05d", i); //5-digit int with leading
        try {
            DistributedCache.addCacheFile(new URI(userSimilaritiesPath.toString() + "/part-" + reduceId),
                    conf3);
        } catch (URISyntaxException ex) {
            System.err.println("Could not add similarities files to distributed cache. " + ex);
        }

    }

    FileInputFormat.setInputPaths(conf3, candidateMoviesPath); //Job 1 output (candidate movies)
    FileOutputFormat.setOutputPath(conf3, finalScoresPath); //Job 3 output (movie \t outputScore)

    //        conf3.setMapperClass(IdentityMapper.class);      
    conf3.setMapperClass(gr.forth.ics.isl.grouprecsmr.job3.Job3MapperMulti.class); //filtering out ratings from non-Friends
    conf3.setReducerClass(gr.forth.ics.isl.grouprecsmr.job3.Job3ReducerMulti.class);

    conf3.setInt("mapred.task.timeout", 6000000);
    conf3.set("io.sort.mb", "500");

    conf3.setNumReduceTasks(numReduceTasks);

    client3.setConf(conf3);
    RunningJob job3;
    try {
        job3 = JobClient.runJob(conf3);
        job3.waitForCompletion();
    } catch (Exception e) {
        System.err.println(e);
    }
}

---

From source file:graphbuilding.GenomixDriver.java

License:Apache License

public void run(String inputPath, String outputPath, int numReducers, int sizeKmer, String defaultConfPath)
        throws IOException {

    JobConf conf = new JobConf(GenomixDriver.class);
    conf.setInt("sizeKmer", sizeKmer);

    if (defaultConfPath != null) {
        conf.addResource(new Path(defaultConfPath));
    }//from   w  w  w  .ja v  a  2  s . co m

    conf.setJobName("Genomix Graph Building");
    conf.setMapperClass(GenomixMapper.class);
    conf.setReducerClass(GenomixReducer.class);
    conf.setCombinerClass(GenomixCombiner.class);

    conf.setMapOutputKeyClass(Kmer.class);
    conf.setMapOutputValueClass(KmerCountValue.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    conf.setOutputKeyClass(Kmer.class);
    conf.setOutputValueClass(KmerCountValue.class);
    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));
    conf.setNumReduceTasks(numReducers);

    FileSystem dfs = FileSystem.get(conf);
    dfs.delete(new Path(outputPath), true);
    JobClient.runJob(conf);
}

---

From source file:hadoop.UIUCWikifierAppHadoop.java

@Override
public int run(String[] args) throws Exception {
    Configuration conf = getConf();
    JobConf job = new JobConf(conf, UIUCWikifierAppHadoop.class);

    //      System.out.println("Run.. Envinronment Variables");
    //      java.util.Map<String,String> env = System.getenv();
    //// w w w. j  a  va  2s.  c  o  m
    //      System.out.println("Printing environment variables");
    //      for(String k : env.keySet()){
    //         System.out.println(k + "\t" + env.get(k));
    //      }
    //      String jlpValue = System.getProperty("java.library.path");
    //      System.out.println("java.library.path=" + jlpValue);
    //      System.setProperty("java.library.path", jlpValue + ":" + "/home/jgilme1/bin/gurobi550/linux64/lib");

    //process command line options
    Path in = new Path(args[0]);
    Path out = new Path(args[1]);

    //change current working directory to hdfs path..
    job.setJobName("entitylinker");
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    job.setInputFormat(DistributeInputFormat.class);
    job.setOutputFormat(TextOutputFormat.class);
    job.setMapperClass(Map.class);
    FileInputFormat.setInputPaths(job, in);
    FileOutputFormat.setOutputPath(job, out);
    job.setNumReduceTasks(0);
    job.setNumMapTasks(Integer.parseInt(args[2]));
    job.set("mapreduce.input.fileinputformat.split.minsize", "0");
    job.set("mapred.child.java.opts", "-Xmx16g");
    job.setNumTasksToExecutePerJvm(-1);
    //job.setMemoryForMapTask(new Long(12288));
    //job.set(JobConf.MAPRED_MAP_TASK_ULIMIT, "12582912");

    String gurobiHomeVariable = "GUROBI_HOME";
    String gurobiHomeValue = "/home/jgilme1/bin/gurobi560/linux64";
    String pathVariable = "PATH";
    String newPathValue = gurobiHomeValue + "/bin";
    String ldLibraryPathVariable = "LD_LIBRARY_PATH";
    String ldLibraryPathValue = gurobiHomeValue + "/lib";
    String grbLicenseFileVariable = "GRB_LICENSE_FILE";
    String grbLicenseFileValue = "/scratch6/usr/jgilme1/gurobiLicense/gurobi.lic";

    StringBuilder newEnvironment = new StringBuilder();
    newEnvironment.append(gurobiHomeVariable);
    newEnvironment.append("=");
    newEnvironment.append(gurobiHomeValue);
    newEnvironment.append(",");
    newEnvironment.append(pathVariable);
    newEnvironment.append("=");
    newEnvironment.append("$" + pathVariable + ":");
    newEnvironment.append(newPathValue);
    newEnvironment.append(",");
    newEnvironment.append(ldLibraryPathVariable);
    newEnvironment.append("=$" + ldLibraryPathVariable + ":");
    newEnvironment.append(ldLibraryPathValue);
    newEnvironment.append(",");
    newEnvironment.append(grbLicenseFileVariable);
    newEnvironment.append("=");
    newEnvironment.append(grbLicenseFileValue);

    //System.out.println(newEnvironment.toString());
    job.set(JobConf.MAPRED_MAP_TASK_ENV, newEnvironment.toString());

    DistributedCache.addCacheArchive(new URI("/user/jgilme1/entitylinking/Wikifier2013.tar.gz"), job);

    JobClient.runJob(job);
    return 0;
}

---

From source file:hibench.DataGenerator.java

License:Apache License

public void sumUpZipf(Path fin, Path fout, ZipfRandom zipf) throws IOException {
    LOG.info("Summing up Zipfian Id Distirubtion...");

    JobConf job = new JobConf(WebDataGen.class);
    String jobname = fin.getName() + " -> " + fout.getName();
    job.setJobName(jobname);//from w  w w.j a va 2 s  . co m

    zipf.setJobConf(job);

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

    job.setMapperClass(SumUpZipfMapper.class);
    job.setReducerClass(SumUpZipfReducer.class);

    job.setNumReduceTasks(1); // Important to sequentially accumulate the required space

    job.setInputFormat(NLineInputFormat.class);
    job.setOutputFormat(TextOutputFormat.class);

    DataPaths.checkHdfsFile(fout, false);

    FileInputFormat.setInputPaths(job, fin);
    FileOutputFormat.setOutputPath(job, fout);

    LOG.info("Running Job: " + jobname);
    LOG.info("Dummy file: " + fin);
    LOG.info("Zipfian sum up file as Ouput: " + fout);
    JobClient.runJob(job);
    LOG.info("Finished Running Job: " + jobname);
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• »