List of usage examples for org.apache.hadoop.mapreduce Job setNumReduceTasks
public void setNumReduceTasks(int tasks) throws IllegalStateException
From source file:com.stride.cartrek.core.hbase.RowKeyDistributorTestBase.java
License:Apache License
private void testMapReduceInternal(long origKeyPrefix, Scan scan, int numValues, int startWithValue, int seekIntervalMinValue, int seekIntervalMaxValue) throws IOException, InterruptedException, ClassNotFoundException { int valuesCountInSeekInterval = writeTestData(origKeyPrefix, numValues, startWithValue, seekIntervalMinValue, seekIntervalMaxValue); // Reading data Configuration conf = testingUtility.getConfiguration(); Job job = new Job(conf, "testMapReduceInternal()-Job"); job.setJarByClass(this.getClass()); TableMapReduceUtil.initTableMapperJob(TABLE_NAME, scan, RowCounterMapper.class, ImmutableBytesWritable.class, Result.class, job); // Substituting standard TableInputFormat which was set in // TableMapReduceUtil.initTableMapperJob(...) job.setInputFormatClass(WdTableInputFormat.class); keyDistributor.addInfo(job.getConfiguration()); job.setOutputFormatClass(NullOutputFormat.class); job.setNumReduceTasks(0); boolean succeeded = job.waitForCompletion(true); Assert.assertTrue(succeeded);/*from w ww .j a v a 2 s.c om*/ long mapInputRecords = job.getCounters().findCounter(RowCounterMapper.Counters.ROWS).getValue(); Assert.assertEquals(valuesCountInSeekInterval, mapInputRecords); }
From source file:com.talis.hadoop.rdf.merge.IndexMerge.java
License:Apache License
public int run(String[] args) throws Exception { 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"); }//w w w . j a v a 2 s . c om boolean overrideOutput = configuration.getBoolean(Constants.OPTION_OVERRIDE_OUTPUT, Constants.OPTION_OVERRIDE_OUTPUT_DEFAULT); FileSystem fs = FileSystem.get(new Path(args[1]).toUri(), configuration); if (overrideOutput) { fs.delete(new Path(args[1]), true); } Job job = new Job(configuration); job.setJobName(JOB_NAME); job.setJarByClass(getClass()); Path input = new Path(args[0]); Path output = new Path(args[1]); FileInputFormat.addInputPath(job, input); FileOutputFormat.setOutputPath(job, output); job.setMapperClass(Mapper.class); job.setReducerClass(IndexMergeReducer.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); job.setOutputFormatClass(TextOutputFormat.class); job.setNumReduceTasks(1); if (LOG.isDebugEnabled()) Utils.log(job, LOG); return job.waitForCompletion(true) ? 0 : -1; }
From source file:com.talis.hadoop.rdf.solr.QuadsIndexer.java
License:Apache License
public int run(String[] args) throws Exception { 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"); }//w w w .ja v a 2 s .c o m boolean overrideOutput = configuration.getBoolean(Constants.OPTION_OVERRIDE_OUTPUT, Constants.OPTION_OVERRIDE_OUTPUT_DEFAULT); FileSystem outputFs = FileSystem.get(new Path(args[1]).toUri(), configuration); if (overrideOutput) { outputFs.delete(new Path(args[1]), true); } Job job = new Job(configuration); job.setJobName(JOB_NAME); job.setJarByClass(getClass()); int shards = -1; boolean compressOutput = false; Path input = new Path(args[0]); Path output = new Path(args[1]); Path solrConfig = new Path(args[2]); FileInputFormat.addInputPath(job, input); FileOutputFormat.setOutputPath(job, output); if (shards > 0) { job.setNumReduceTasks(shards); } job.setMapperClass(Mapper.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(QuadArrayWritable.class); job.setReducerClass(SolrReducer.class); SolrDocumentConverter.setSolrDocumentConverter(LiteralsIndexer.class, job.getConfiguration()); job.setOutputFormatClass(SolrOutputFormat.class); String zipName = "solr.zip"; FileSystem solrConfigFs = FileSystem.get(solrConfig.toUri(), configuration); final URI baseZipUrl = solrConfigFs.getUri().resolve(solrConfig.toString() + '#' + zipName); DistributedCache.addCacheArchive(baseZipUrl, job.getConfiguration()); job.getConfiguration().set(SolrOutputFormat.SETUP_OK, solrConfig.toString()); SolrOutputFormat.setOutputZipFormat(compressOutput, job.getConfiguration()); if (LOG.isDebugEnabled()) Utils.log(job, LOG); return job.waitForCompletion(true) ? 0 : -1; }
From source file:com.talis.labs.pagerank.mapreduce.CheckConvergence.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: CheckConvergence <input path> <output path>"); return -1; }/*from w w w . ja va 2s . c o m*/ FileSystem.get(getConf()).delete(new Path(args[1]), true); Job job = new Job(getConf(), "CheckConvergence"); job.setJarByClass(getClass()); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(CheckConvergenceMapper.class); job.setCombinerClass(CheckConvergenceReducer.class); job.setReducerClass(CheckConvergenceReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(DoubleWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(DoubleWritable.class); job.setNumReduceTasks(1); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.talis.labs.pagerank.mapreduce.CountPages.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: CountPages <input path> <output path>"); return -1; }/*from ww w .jav a 2 s . c om*/ FileSystem.get(getConf()).delete(new Path(args[1]), true); Job job = new Job(getConf(), "CountPages"); job.setJarByClass(getClass()); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(CountPagesMapper.class); job.setCombinerClass(CountPagesReducer.class); job.setReducerClass(CountPagesReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(LongWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); job.setNumReduceTasks(1); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.talis.labs.pagerank.mapreduce.DanglingPages.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: DanglingPages <input path> <output path>"); return -1; }/*from w ww. j a v a 2 s . co m*/ FileSystem.get(getConf()).delete(new Path(args[1]), true); Job job = new Job(getConf(), "DanglingPages"); job.setJarByClass(getClass()); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(DanglingPagesMapper.class); job.setCombinerClass(DanglingPagesReducer.class); job.setReducerClass(DanglingPagesReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(DoubleWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(DoubleWritable.class); job.setNumReduceTasks(1); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.talis.labs.pagerank.mapreduce.SortPageRanks.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: SortPageRanks <input path> <output path>"); return -1; }/*ww w .j ava 2 s. co m*/ FileSystem.get(getConf()).delete(new Path(args[1]), true); Job job = new Job(getConf(), "SortPageRanks"); job.setJarByClass(getClass()); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(SortPageRanksMapper.class); job.setReducerClass(Reducer.class); // i.e. identity reducer job.setSortComparatorClass(DoubleWritableDecreasingComparator.class); job.setMapOutputKeyClass(DoubleWritable.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setNumReduceTasks(1); // TODO: inefficient, use InputSampler with v0.20.x return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.talis.mapreduce.lib.input.TestDriver.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 . j a va 2 s.c om*/ Job job = new Job(getConf(), "test"); job.setJarByClass(getClass()); job.setInputFormatClass(NQuadsInputFormat.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(TestMapper.class); job.setNumReduceTasks(0); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.tdunning.plume.local.lazy.MapRedExecutor.java
License:Apache License
/** * This method returns a Job instance out of a {@link MSCR} entity. It puts the Class of * the {@link PlumeWorkflow} argument and the MSCR id in the hadoop configuration. * /* w ww . j a v a 2 s .c o m*/ * @param mscr The MSCR to convert * @param workflow The workflow whose class will be instantiated by hadoop mappers/reducers * @param outputPath The output path of the MapRed job * @return A hadoop-executable MapRed Job * * @throws IOException */ static Job getMapRed(final MSCR mscr, PlumeWorkflow workFlow, String workFlowOutputPath, String outputPath) throws IOException { Configuration conf = new Configuration(); conf.set(WORKFLOW_NAME, workFlow.getClass().getName()); conf.setInt(MSCR_ID, mscr.getId()); conf.set(TEMP_OUTPUT_PATH, workFlowOutputPath); Job job = new Job(conf, "MSCR"); // TODO deprecation job.setMapOutputKeyClass(PlumeObject.class); job.setMapOutputValueClass(PlumeObject.class); job.setJarByClass(MapRedExecutor.class); /** * Define multiple inputs */ for (PCollection<?> input : mscr.getInputs()) { if (!(input instanceof LazyCollection)) { throw new IllegalArgumentException("Can't create MapRed from MSCR whose inputs are not LazyTable"); } LazyCollection<Text> l = (LazyCollection<Text>) input; if (!(l.isMaterialized() && l.getFile() != null)) { // Collections have plume ID only if they are intermediate results - TODO better naming for this if (l.getPlumeId().length() < 1) { throw new IllegalArgumentException( "Can't create MapRed from MSCR inputs that are not materialized to a file"); } } PCollectionType<?> rType = l.getType(); Class<? extends InputFormat> format = SequenceFileInputFormat.class; if (rType instanceof PTableType) { PTableType<?, ?> tType = (PTableType<?, ?>) rType; if (tType.valueType() instanceof StringType && tType.keyType() instanceof StringType) { format = KeyValueTextInputFormat.class; } MultipleInputs.addInputPath(job, new Path(l.getFile()), format, MSCRMapper.class); } else { if (rType.elementType() instanceof StringType) { format = TextInputFormat.class; } MultipleInputs.addInputPath(job, new Path(l.getFile()), format, MSCRMapper.class); } } /** * Define multiple outputs */ FileOutputFormat.setOutputPath(job, new Path(outputPath)); for (Map.Entry<PCollection<?>, Integer> entry : mscr.getNumberedChannels().entrySet()) { PCollectionType<?> rType = ((LazyCollection<?>) mscr.getOutputChannels().get(entry.getKey()).output) .getType(); if (rType instanceof PTableType) { PTableType<?, ?> tType = (PTableType<?, ?>) rType; Class<? extends OutputFormat> outputFormat = SequenceFileOutputFormat.class; if (tType.keyType() instanceof StringType && tType.valueType() instanceof StringType) { outputFormat = TextOutputFormat.class; } MultipleOutputs.addNamedOutput(job, entry.getValue() + "", outputFormat, getHadoopType(tType.keyType()), getHadoopType(tType.valueType())); } else { Class<? extends OutputFormat> outputFormat = SequenceFileOutputFormat.class; if (rType.elementType() instanceof StringType) { outputFormat = TextOutputFormat.class; } MultipleOutputs.addNamedOutput(job, entry.getValue() + "", outputFormat, NullWritable.class, getHadoopType(rType.elementType())); } } /** * Define Reducer & Combiner */ job.setCombinerClass(MSCRCombiner.class); job.setReducerClass(MSCRReducer.class); job.setNumReduceTasks(1); return job; }
From source file:com.telefonica.iot.tidoop.mrlib.jobs.Filter.java
License:Open Source License
@Override public int run(String[] args) throws Exception { // check the number of arguments, show the usage if it is wrong if (args.length != 3) { showUsage();//from w w w .j a v a 2 s. com return -1; } // if // get the arguments String input = args[0]; String output = args[1]; String regex = args[2]; // create and configure a MapReduce job Configuration conf = this.getConf(); conf.set(Constants.PARAM_REGEX, regex); Job job = Job.getInstance(conf, "tidoop-mr-lib-filter"); job.setNumReduceTasks(1); job.setJarByClass(Filter.class); job.setMapperClass(LineFilter.class); job.setCombinerClass(LinesCombiner.class); job.setReducerClass(LinesJoiner.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(input)); FileOutputFormat.setOutputPath(job, new Path(output)); // run the MapReduce job return job.waitForCompletion(true) ? 0 : 1; }