Example usage for org.apache.hadoop.mapreduce Job waitForCompletion

List of usage examples for org.apache.hadoop.mapreduce Job waitForCompletion

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapreduce.*
  5. Job
  6. waitForCompletion

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce Job waitForCompletion.

Prototype

public boolean waitForCompletion(boolean verbose)
        throws IOException, InterruptedException, ClassNotFoundException

Source Link

Document

Submit the job to the cluster and wait for it to finish.

Usage

From source file:com.cloudera.avro.MapReduceColorCount.java

License:Apache License

public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.println("Usage: MapReduceColorCount <input path> <output path>");
        return -1;
    }/*from ww w  .  j a v  a2  s.c  o  m*/

    Job job = new Job(getConf());
    job.setJarByClass(MapReduceColorCount.class);
    job.setJobName("Color Count");

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

    job.setInputFormatClass(AvroKeyInputFormat.class);
    job.setMapperClass(ColorCountMapper.class);
    AvroJob.setInputKeySchema(job, User.getClassSchema());
    AvroJob.setMapOutputValueSchema(job, User.getClassSchema());

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

    job.setOutputFormatClass(AvroKeyValueOutputFormat.class);
    job.setReducerClass(ColorCountReducer.class);
    AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING));
    AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT));

    return (job.waitForCompletion(true) ? 0 : 1);
}

From source file:com.cloudera.ByteCount.java

License:Apache License

public static void main(String[] args) throws Exception {
    JobConf conf = new JobConf(new Configuration());

    // Trim off the hadoop-specific args
    String[] remArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    // Pull in properties
    Options options = new Options();

    Option property = OptionBuilder.withArgName("property=value").hasArgs(2).withValueSeparator()
            .withDescription("use value for given property").create("D");
    options.addOption(property);/* w w  w.  j a  v a  2  s. c  o m*/

    Option skipChecksums = new Option("skipChecksums", "skip checksums");
    options.addOption(skipChecksums);

    Option profile = new Option("profile", "profile tasks");
    options.addOption(profile);

    CommandLineParser parser = new BasicParser();
    CommandLine line = parser.parse(options, remArgs);

    Properties properties = line.getOptionProperties("D");
    for (Entry<Object, Object> prop : properties.entrySet()) {
        conf.set(prop.getKey().toString(), prop.getValue().toString());
        System.out.println("Set config key " + prop.getKey() + " to " + prop.getValue());
    }

    if (line.hasOption("skipChecksums")) {
        conf.setBoolean("bytecount.skipChecksums", true);
        System.out.println("Skipping checksums");
    }

    if (line.hasOption("profile")) {
        conf.setBoolean("mapred.task.profile", true);
        conf.set("mapred.task.profile.params",
                "-agentlib:hprof=cpu=samples,depth=100,interval=1ms,lineno=y,thread=y,file=%s");
        conf.set(MRJobConfig.NUM_MAP_PROFILES, "0");
        conf.set("mapred.task.profile.maps", "1");
        System.out.println("Profiling map tasks");
    }

    // Get the positional arguments out
    remArgs = line.getArgs();
    if (remArgs.length != 2) {
        System.err.println("Usage: ByteCount <inputBase> <outputBase>");
        System.exit(1);
    }
    String inputBase = remArgs[0];
    String outputBase = remArgs[1];

    Job job = Job.getInstance(conf);

    job.setInputFormatClass(ByteBufferInputFormat.class);

    job.setMapOutputKeyClass(ByteWritable.class);
    job.setMapOutputValueClass(LongWritable.class);

    job.setMapperClass(ByteCountMapper.class);
    job.setReducerClass(ByteCountReducer.class);
    job.setCombinerClass(ByteCountReducer.class);

    job.setOutputKeyClass(ByteWritable.class);
    job.setOutputValueClass(LongWritable.class);

    FileInputFormat.addInputPath(job, new Path(inputBase));
    FileOutputFormat.setOutputPath(job, new Path(outputBase));

    job.setJarByClass(ByteCount.class);

    boolean success = job.waitForCompletion(true);

    Counters counters = job.getCounters();
    System.out.println("\tRead counters");
    printCounter(counters, READ_COUNTER.BYTES_READ);
    printCounter(counters, READ_COUNTER.LOCAL_BYTES_READ);
    printCounter(counters, READ_COUNTER.SCR_BYTES_READ);
    printCounter(counters, READ_COUNTER.ZCR_BYTES_READ);

    System.exit(success ? 0 : 1);
}

From source file:com.cloudera.castagna.logparser.mr.StatusCodesStats.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getName());
        ToolRunner.printGenericCommandUsage(System.err);
        return -1;
    }//from w  w  w . ja v  a2  s.  c o m

    Configuration configuration = getConf();
    boolean useCompression = configuration.getBoolean(Constants.OPTION_USE_COMPRESSION,
            Constants.OPTION_USE_COMPRESSION_DEFAULT);

    if (useCompression) {
        configuration.setBoolean("mapred.compress.map.output", true);
        configuration.set("mapred.output.compression.type", "BLOCK");
        configuration.set("mapred.map.output.compression.codec", "org.apache.hadoop.io.compress.GzipCodec");
    }

    boolean overrideOutput = configuration.getBoolean(Constants.OPTION_OVERWRITE_OUTPUT,
            Constants.OPTION_OVERWRITE_OUTPUT_DEFAULT);
    FileSystem fs = FileSystem.get(new Path(args[1]).toUri(), configuration);
    if (overrideOutput) {
        fs.delete(new Path(args[1]), true);
    }

    Job job = Job.getInstance(configuration);
    job.setJobName(Constants.STATUS_CODES_STATS);
    job.setJarByClass(getClass());

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setInputFormatClass(TextInputFormat.class);

    job.setMapperClass(StatusCodesStatsMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);

    job.setCombinerClass(StatusCodesStatsCombiner.class);

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

    Utils.setReducers(job, configuration, log);

    job.setOutputFormatClass(TextOutputFormat.class);

    if (log.isDebugEnabled())
        Utils.log(job, log);

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.cloudera.castagna.logparser.mr.TranscodeLogs.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getName());
        ToolRunner.printGenericCommandUsage(System.err);
        return -1;
    }//from  ww  w.j  a v  a 2 s. c  o m

    Configuration configuration = getConf();

    boolean overrideOutput = configuration.getBoolean(Constants.OPTION_OVERWRITE_OUTPUT,
            Constants.OPTION_OVERWRITE_OUTPUT_DEFAULT);
    FileSystem fs = FileSystem.get(new Path(args[1]).toUri(), configuration);
    if (overrideOutput) {
        fs.delete(new Path(args[1]), true);
    }

    Job job = Job.getInstance(configuration);
    job.setJobName(Constants.STATUS_CODES_STATS);
    job.setJarByClass(getClass());

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setInputFormatClass(TextInputFormat.class);

    job.setMapperClass(TranscodeLogsMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);

    job.setNumReduceTasks(0);

    job.setOutputFormatClass(TextOutputFormat.class);

    if (log.isDebugEnabled())
        Utils.log(job, log);

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.cloudera.hbase.WordCount.java

License:Open Source License

public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        return 2;
    }/*from   w  w  w. j a va2s  .co m*/

    Configuration conf = getConf();

    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(Map.class);
    job.setCombinerClass(Reduce.class);
    job.setReducerClass(Reduce.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.cloudera.recordservice.avro.mapreduce.ColorCount.java

License:Apache License

/**
 * Run the MR2 color count with generic records, and return a map of favorite colors to
 * the number of users.//from  ww w . ja v  a2s  . c  o m
 */
public static java.util.Map<String, Integer> countColors()
        throws IOException, ClassNotFoundException, InterruptedException {
    String output = TestUtil.getTempDirectory();
    Path outputPath = new Path(output);
    JobConf conf = new JobConf(ColorCount.class);
    conf.setInt("mapreduce.job.reduces", 1);

    Job job = Job.getInstance(conf);
    job.setJarByClass(ColorCount.class);
    job.setJobName("MR2 Color Count With Generic Records");

    RecordServiceConfig.setInputTable(job.getConfiguration(), "rs", "users");
    job.setInputFormatClass(com.cloudera.recordservice.avro.mapreduce.AvroKeyInputFormat.class);
    FileOutputFormat.setOutputPath(job, outputPath);

    job.setMapperClass(Map.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setOutputFormatClass(AvroKeyValueOutputFormat.class);
    job.setReducerClass(Reduce.class);
    AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING));
    AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT));

    job.waitForCompletion(false);

    // Read the result and return it. Since we set the number of reducers to 1,
    // there is always just one file containing the value.
    SeekableInput input = new FsInput(new Path(output + "/part-r-00000.avro"), conf);
    DatumReader<GenericRecord> reader = new GenericDatumReader<GenericRecord>();
    FileReader<GenericRecord> fileReader = DataFileReader.openReader(input, reader);
    java.util.Map<String, Integer> colorMap = new HashMap<String, Integer>();
    for (GenericRecord datum : fileReader) {
        colorMap.put(datum.get(0).toString(), Integer.parseInt(datum.get(1).toString()));
    }
    return colorMap;
}

From source file:com.cloudera.recordservice.examples.mapreduce.MapReduceAgeCount.java

License:Apache License

public int run(String[] args) throws Exception {
    org.apache.log4j.BasicConfigurator.configure();

    if (args.length != 2) {
        System.err.println("Usage: MapReduceAgeCount <input path> <output path>");
        return -1;
    }//www.j  a va  2s . co m

    Job job = Job.getInstance(getConf());
    job.setJarByClass(MapReduceAgeCount.class);
    job.setJobName("Age Count");

    // RECORDSERVICE:
    // To read from a table instead of a path, comment out
    // FileInputFormat.setInputPaths() and instead use:
    // FileInputFormat.setInputPaths(job, new Path(args[0]));
    RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]);

    // RECORDSERVICE:
    // Use the RecordService version of the AvroKeyValueInputFormat
    job.setInputFormatClass(com.cloudera.recordservice.avro.mapreduce.AvroKeyValueInputFormat.class);
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(AgeCountMapper.class);
    // Set schema for input key and value.
    AvroJob.setInputKeySchema(job, UserKey.getClassSchema());
    AvroJob.setInputValueSchema(job, UserValue.getClassSchema());

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

    job.setOutputFormatClass(AvroKeyValueOutputFormat.class);
    job.setReducerClass(AgeCountReducer.class);
    AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING));
    AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT));

    return (job.waitForCompletion(true) ? 0 : 1);
}

From source file:com.cloudera.recordservice.examples.mapreduce.MapReduceColorCount.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    org.apache.log4j.BasicConfigurator.configure();

    if (args.length != 2) {
        System.err.println("Usage: MapReduceColorCount <input path> <output path>");
        return -1;
    }/*from  ww  w. j a  v a 2 s . co m*/

    Job job = Job.getInstance(getConf());
    job.setJarByClass(MapReduceColorCount.class);
    job.setJobName("Color Count");

    // RECORDSERVICE:
    // To read from a table instead of a path, comment out
    // FileInputFormat.setInputPaths() and instead use:
    //FileInputFormat.setInputPaths(job, new Path(args[0]));
    RecordServiceConfig.setInputTable(job.getConfiguration(), "rs", "users");

    // RECORDSERVICE:
    // Use the RecordService version of the AvroKeyInputFormat
    job.setInputFormatClass(com.cloudera.recordservice.avro.mapreduce.AvroKeyInputFormat.class);
    //job.setInputFormatClass(AvroKeyInputFormat.class);

    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(ColorCountMapper.class);
    AvroJob.setInputKeySchema(job, User.getClassSchema());
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setOutputFormatClass(AvroKeyValueOutputFormat.class);
    job.setReducerClass(ColorCountReducer.class);
    AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING));
    AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT));

    return (job.waitForCompletion(true) ? 0 : 1);
}

From source file:com.cloudera.recordservice.examples.mapreduce.RecordCount.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.println("Usage: RecordCount <input_query> <output_path>");
        System.exit(1);/*from w  ww .  j a  va 2 s  .  co  m*/
    }
    String inputQuery = args[0];
    String output = args[1];

    Job job = Job.getInstance(getConf());
    job.setJobName("recordcount");
    job.setJarByClass(RecordCount.class);
    job.setMapperClass(Map.class);
    job.setCombinerClass(Reduce.class);
    job.setReducerClass(Reduce.class);
    job.setNumReduceTasks(1);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(LongWritable.class);

    RecordServiceConfig.setInputQuery(job.getConfiguration(), inputQuery);
    job.setInputFormatClass(RecordServiceInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    FileSystem fs = FileSystem.get(job.getConfiguration());
    Path outputPath = new Path(output);
    if (fs.exists(outputPath))
        fs.delete(outputPath, true);
    FileOutputFormat.setOutputPath(job, outputPath);

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.cloudera.recordservice.examples.terasort.TeraChecksum.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    boolean useRecordService = false;
    Job job = Job.getInstance(getConf());
    if (args.length != 2 && args.length != 3) {
        usage();/*www.  j a v  a 2s .  c o m*/
        return 2;
    }
    if (args.length == 3) {
        useRecordService = Boolean.parseBoolean(args[2]);
    }

    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    job.setJobName("TeraSum");
    job.setJarByClass(TeraChecksum.class);
    job.setMapperClass(ChecksumMapper.class);
    job.setReducerClass(ChecksumReducer.class);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(Unsigned16.class);
    // force a single reducer
    job.setNumReduceTasks(1);
    if (useRecordService) {
        RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]);
        job.setInputFormatClass(RecordServiceTeraInputFormat.class);
    } else {
        TeraInputFormat.setInputPaths(job, new Path(args[0]));
        job.setInputFormatClass(TeraInputFormat.class);
    }
    return job.waitForCompletion(true) ? 0 : 1;
}