Search in sources :

Example 46 with GenericOptionsParser

use of org.apache.hadoop.util.GenericOptionsParser in project hadoop by apache.

the class ResourceManager method main.

public static void main(String[] argv) {
    Thread.setDefaultUncaughtExceptionHandler(new YarnUncaughtExceptionHandler());
    StringUtils.startupShutdownMessage(ResourceManager.class, argv, LOG);
    try {
        Configuration conf = new YarnConfiguration();
        GenericOptionsParser hParser = new GenericOptionsParser(conf, argv);
        argv = hParser.getRemainingArgs();
        // If -format-state-store, then delete RMStateStore; else startup normally
        if (argv.length >= 1) {
            if (argv[0].equals("-format-state-store")) {
                deleteRMStateStore(conf);
            } else if (argv[0].equals("-remove-application-from-state-store") && argv.length == 2) {
                removeApplication(conf, argv[1]);
            } else {
                printUsage(System.err);
            }
        } else {
            ResourceManager resourceManager = new ResourceManager();
            ShutdownHookManager.get().addShutdownHook(new CompositeServiceShutdownHook(resourceManager), SHUTDOWN_HOOK_PRIORITY);
            resourceManager.init(conf);
            resourceManager.start();
        }
    } catch (Throwable t) {
        LOG.fatal("Error starting ResourceManager", t);
        System.exit(-1);
    }
}
Also used : YarnUncaughtExceptionHandler(org.apache.hadoop.yarn.YarnUncaughtExceptionHandler) Configuration(org.apache.hadoop.conf.Configuration) YarnConfiguration(org.apache.hadoop.yarn.conf.YarnConfiguration) YarnConfiguration(org.apache.hadoop.yarn.conf.YarnConfiguration) GenericOptionsParser(org.apache.hadoop.util.GenericOptionsParser)

Example 47 with GenericOptionsParser

use of org.apache.hadoop.util.GenericOptionsParser in project hadoop by apache.

the class ValueAggregatorJob method createValueAggregatorJob.

/**
   * Create an Aggregate based map/reduce job.
   *
   * @param args the arguments used for job creation. Generic hadoop
   * arguments are accepted.
   * @param caller the the caller class.
   * @return a JobConf object ready for submission.
   *
   * @throws IOException
   * @see GenericOptionsParser
   */
@SuppressWarnings("rawtypes")
public static JobConf createValueAggregatorJob(String[] args, Class<?> caller) throws IOException {
    Configuration conf = new Configuration();
    GenericOptionsParser genericParser = new GenericOptionsParser(conf, args);
    args = genericParser.getRemainingArgs();
    if (args.length < 2) {
        System.out.println("usage: inputDirs outDir " + "[numOfReducer [textinputformat|seq [specfile [jobName]]]]");
        GenericOptionsParser.printGenericCommandUsage(System.out);
        System.exit(1);
    }
    String inputDir = args[0];
    String outputDir = args[1];
    int numOfReducers = 1;
    if (args.length > 2) {
        numOfReducers = Integer.parseInt(args[2]);
    }
    Class<? extends InputFormat> theInputFormat = TextInputFormat.class;
    if (args.length > 3 && args[3].compareToIgnoreCase("textinputformat") == 0) {
        theInputFormat = TextInputFormat.class;
    } else {
        theInputFormat = SequenceFileInputFormat.class;
    }
    Path specFile = null;
    if (args.length > 4) {
        specFile = new Path(args[4]);
    }
    String jobName = "";
    if (args.length > 5) {
        jobName = args[5];
    }
    JobConf theJob = new JobConf(conf);
    if (specFile != null) {
        theJob.addResource(specFile);
    }
    String userJarFile = theJob.get("user.jar.file");
    if (userJarFile == null) {
        theJob.setJarByClass(caller != null ? caller : ValueAggregatorJob.class);
    } else {
        theJob.setJar(userJarFile);
    }
    theJob.setJobName("ValueAggregatorJob: " + jobName);
    FileInputFormat.addInputPaths(theJob, inputDir);
    theJob.setInputFormat(theInputFormat);
    theJob.setMapperClass(ValueAggregatorMapper.class);
    FileOutputFormat.setOutputPath(theJob, new Path(outputDir));
    theJob.setOutputFormat(TextOutputFormat.class);
    theJob.setMapOutputKeyClass(Text.class);
    theJob.setMapOutputValueClass(Text.class);
    theJob.setOutputKeyClass(Text.class);
    theJob.setOutputValueClass(Text.class);
    theJob.setReducerClass(ValueAggregatorReducer.class);
    theJob.setCombinerClass(ValueAggregatorCombiner.class);
    theJob.setNumMapTasks(1);
    theJob.setNumReduceTasks(numOfReducers);
    return theJob;
}
Also used : Path(org.apache.hadoop.fs.Path) Configuration(org.apache.hadoop.conf.Configuration) TextInputFormat(org.apache.hadoop.mapred.TextInputFormat) JobConf(org.apache.hadoop.mapred.JobConf) GenericOptionsParser(org.apache.hadoop.util.GenericOptionsParser)

Example 48 with GenericOptionsParser

use of org.apache.hadoop.util.GenericOptionsParser in project Cloud9 by lintool.

the class ClueWebAnchorTextForwardIndexHttpServer method main.

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 3) {
        System.out.println("usage: [index-file] [docno-mapping-data-files] [clue-forward-index-root]");
        //[clue-forward-index-root: /shared/ClueWeb09/collection.compressed.block/
        System.exit(-1);
    }
    String indexFile = otherArgs[0];
    String mappingFile = otherArgs[1];
    String clueIndexRoot = otherArgs[2].endsWith("/") ? otherArgs[2] : otherArgs[2] + "/";
    String cluewebForwardIndex = "";
    for (int i = 1; i < 10; i++) cluewebForwardIndex += clueIndexRoot + "findex.en.0" + i + ".dat" + SEPARATOR + " ";
    cluewebForwardIndex += clueIndexRoot + "findex.en.10.dat";
    LOG.info("Launching DocumentForwardIndexHttpServer");
    LOG.info(" - index file: " + indexFile);
    LOG.info(" - docno mapping data file: " + mappingFile);
    LOG.info(" - ClueWeb09 index root:" + clueIndexRoot);
    FileSystem fs = FileSystem.get(conf);
    Random rand = new Random();
    int r = rand.nextInt();
    // this tmp file as a rendezvous point
    Path tmpPath = new Path("/tmp/" + r);
    if (fs.exists(tmpPath)) {
        fs.delete(tmpPath, true);
    }
    JobConf job = new JobConf(conf, ClueWebAnchorTextForwardIndexHttpServer.class);
    job.setJobName("ForwardIndexServer:" + indexFile);
    job.set("mapred.child.java.opts", "-Xmx2048m");
    job.setNumMapTasks(1);
    job.setNumReduceTasks(0);
    job.setInputFormat(NullInputFormat.class);
    job.setOutputFormat(NullOutputFormat.class);
    job.setMapperClass(ServerMapper.class);
    job.set("IndexFile", indexFile);
    job.set("DocnoMappingDataFile", mappingFile);
    job.set("TmpPath", tmpPath.toString());
    job.set("ClueWebIndexFiles", cluewebForwardIndex);
    JobClient client = new JobClient(job);
    client.submitJob(job);
    LOG.info("Waiting for server to start up...");
    while (!fs.exists(tmpPath)) {
        Thread.sleep(50000);
        LOG.info("...");
    }
    FSDataInputStream in = fs.open(tmpPath);
    String host = in.readUTF();
    in.close();
    LOG.info("host: " + host);
    LOG.info("port: 8888");
}
Also used : Path(org.apache.hadoop.fs.Path) Configuration(org.apache.hadoop.conf.Configuration) Random(java.util.Random) FileSystem(org.apache.hadoop.fs.FileSystem) FSDataInputStream(org.apache.hadoop.fs.FSDataInputStream) JobConf(org.apache.hadoop.mapred.JobConf) JobClient(org.apache.hadoop.mapred.JobClient) GenericOptionsParser(org.apache.hadoop.util.GenericOptionsParser)

Example 49 with GenericOptionsParser

use of org.apache.hadoop.util.GenericOptionsParser in project hadoop by apache.

the class ValueAggregatorJob method createValueAggregatorJob.

/**
   * Create an Aggregate based map/reduce job.
   * 
   * @param conf The configuration for job
   * @param args the arguments used for job creation. Generic hadoop
   * arguments are accepted.
   * @return a Job object ready for submission.
   * 
   * @throws IOException
   * @see GenericOptionsParser
   */
public static Job createValueAggregatorJob(Configuration conf, String[] args) throws IOException {
    GenericOptionsParser genericParser = new GenericOptionsParser(conf, args);
    args = genericParser.getRemainingArgs();
    if (args.length < 2) {
        System.out.println("usage: inputDirs outDir " + "[numOfReducer [textinputformat|seq [specfile [jobName]]]]");
        GenericOptionsParser.printGenericCommandUsage(System.out);
        System.exit(2);
    }
    String inputDir = args[0];
    String outputDir = args[1];
    int numOfReducers = 1;
    if (args.length > 2) {
        numOfReducers = Integer.parseInt(args[2]);
    }
    Class<? extends InputFormat> theInputFormat = null;
    if (args.length > 3 && args[3].compareToIgnoreCase("textinputformat") == 0) {
        theInputFormat = TextInputFormat.class;
    } else {
        theInputFormat = SequenceFileInputFormat.class;
    }
    Path specFile = null;
    if (args.length > 4) {
        specFile = new Path(args[4]);
    }
    String jobName = "";
    if (args.length > 5) {
        jobName = args[5];
    }
    if (specFile != null) {
        conf.addResource(specFile);
    }
    String userJarFile = conf.get(ValueAggregatorJobBase.USER_JAR);
    if (userJarFile != null) {
        conf.set(MRJobConfig.JAR, userJarFile);
    }
    Job theJob = Job.getInstance(conf);
    if (userJarFile == null) {
        theJob.setJarByClass(ValueAggregator.class);
    }
    theJob.setJobName("ValueAggregatorJob: " + jobName);
    FileInputFormat.addInputPaths(theJob, inputDir);
    theJob.setInputFormatClass(theInputFormat);
    theJob.setMapperClass(ValueAggregatorMapper.class);
    FileOutputFormat.setOutputPath(theJob, new Path(outputDir));
    theJob.setOutputFormatClass(TextOutputFormat.class);
    theJob.setMapOutputKeyClass(Text.class);
    theJob.setMapOutputValueClass(Text.class);
    theJob.setOutputKeyClass(Text.class);
    theJob.setOutputValueClass(Text.class);
    theJob.setReducerClass(ValueAggregatorReducer.class);
    theJob.setCombinerClass(ValueAggregatorCombiner.class);
    theJob.setNumReduceTasks(numOfReducers);
    return theJob;
}
Also used : Path(org.apache.hadoop.fs.Path) ControlledJob(org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob) Job(org.apache.hadoop.mapreduce.Job) GenericOptionsParser(org.apache.hadoop.util.GenericOptionsParser)

Example 50 with GenericOptionsParser

use of org.apache.hadoop.util.GenericOptionsParser in project hadoop by apache.

the class WordCount method main.

public static void main(String[] args) throws Exception {
    final Configuration conf = new Configuration();
    final String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);
    }
    final Job job = Job.getInstance(conf, conf.get(MRJobConfig.JOB_NAME, "word count"));
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}
Also used : Path(org.apache.hadoop.fs.Path) Configuration(org.apache.hadoop.conf.Configuration) Job(org.apache.hadoop.mapreduce.Job) GenericOptionsParser(org.apache.hadoop.util.GenericOptionsParser)

Aggregations

GenericOptionsParser (org.apache.hadoop.util.GenericOptionsParser)63 Configuration (org.apache.hadoop.conf.Configuration)44 Job (org.apache.hadoop.mapreduce.Job)26 Path (org.apache.hadoop.fs.Path)22 CommandLine (org.apache.commons.cli.CommandLine)12 HCatSchema (org.apache.hive.hcatalog.data.schema.HCatSchema)10 HBaseConfiguration (org.apache.hadoop.hbase.HBaseConfiguration)8 PosixParser (org.apache.commons.cli.PosixParser)7 YarnConfiguration (org.apache.hadoop.yarn.conf.YarnConfiguration)7 IOException (java.io.IOException)6 Options (org.apache.commons.cli.Options)6 FileSystem (org.apache.hadoop.fs.FileSystem)6 HashMap (java.util.HashMap)5 YarnUncaughtExceptionHandler (org.apache.hadoop.yarn.YarnUncaughtExceptionHandler)5 ArrayList (java.util.ArrayList)4 ParseException (org.apache.commons.cli.ParseException)4 HdfsConfiguration (org.apache.hadoop.hdfs.HdfsConfiguration)4 JobConf (org.apache.hadoop.mapred.JobConf)4 File (java.io.File)3 Random (java.util.Random)3