List of usage examples for org.apache.hadoop.mapred JobConf setOutputKeyComparatorClass
public void setOutputKeyComparatorClass(Class<? extends RawComparator> theClass)
From source file:com.ibm.bi.dml.runtime.matrix.MMRJMR.java
License:Open Source License
public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String instructionsInMapper, String aggInstructionsInReducer, String aggBinInstrctions, String otherInstructionsInReducer, int numReducers, int replication, byte[] resultIndexes, String[] outputs, OutputInfo[] outputInfos) throws Exception { JobConf job = new JobConf(MMRJMR.class); job.setJobName("MMRJ-MR"); if (numReducers <= 0) throw new Exception("MMRJ-MR has to have at least one reduce task!"); // TODO: check w/ yuanyuan. This job always runs in blocked mode, and hence derivation is not necessary. boolean inBlockRepresentation = MRJobConfiguration.deriveRepresentation(inputInfos); //whether use block representation or cell representation MRJobConfiguration.setMatrixValueClass(job, inBlockRepresentation); byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;/*from w w w. j a v a 2 s . c o m*/ //set up the input files and their format information MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, true, inBlockRepresentation ? ConvertTarget.BLOCK : ConvertTarget.CELL); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); //set up unary instructions that will perform in the mapper MRJobConfiguration.setInstructionsInMapper(job, instructionsInMapper); //set up the aggregate instructions that will happen in the combiner and reducer MRJobConfiguration.setAggregateInstructions(job, aggInstructionsInReducer); //set up the aggregate binary operation for the mmcj job MRJobConfiguration.setAggregateBinaryInstructions(job, aggBinInstrctions); //set up the instructions that will happen in the reducer, after the aggregation instrucions MRJobConfiguration.setInstructionsInReducer(job, otherInstructionsInReducer); //set up the replication factor for the results job.setInt("dfs.replication", replication); //set up map/reduce memory configurations (if in AM context) DMLConfig config = ConfigurationManager.getConfig(); DMLAppMasterUtils.setupMRJobRemoteMaxMemory(job, config); // byte[] resultIndexes=new byte[]{AggregateBinaryInstruction.parseMRInstruction(aggBinInstrction).output}; //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, aggBinInstrctions, resultIndexes); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, aggBinInstrctions, otherInstructionsInReducer, resultIndexes, mapoutputIndexes, false); MatrixCharacteristics[] stats = ret.stats; //set up the number of reducers MRJobConfiguration.setNumReducers(job, ret.numReducerGroups, numReducers); // Print the complete instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); byte[] dimsUnknown = new byte[resultIndexes.length]; for (int i = 0; i < resultIndexes.length; i++) { if (stats[i].getRows() == -1 || stats[i].getCols() == -1) { dimsUnknown[i] = (byte) 1; } else { dimsUnknown[i] = (byte) 0; } } //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, dimsUnknown, outputs, outputInfos, inBlockRepresentation); // configure mapper job.setMapperClass(MMRJMRMapper.class); job.setMapOutputKeyClass(TripleIndexes.class); if (inBlockRepresentation) job.setMapOutputValueClass(TaggedMatrixBlock.class); else job.setMapOutputValueClass(TaggedMatrixCell.class); job.setOutputKeyComparatorClass(TripleIndexes.Comparator.class); job.setPartitionerClass(TripleIndexes.FirstTwoIndexesPartitioner.class); //configure combiner //TODO: cannot set up combiner, because it will destroy the stable numerical algorithms // for sum or for central moments // if(aggInstructionsInReducer!=null && !aggInstructionsInReducer.isEmpty()) // job.setCombinerClass(MMCJMRCombiner.class); //configure reducer job.setReducerClass(MMRJMRReducer.class); // By default, the job executes in "cluster" mode. // Determine if we can optimize and run it in "local" mode. MatrixCharacteristics[] inputStats = new MatrixCharacteristics[inputs.length]; for (int i = 0; i < inputs.length; i++) { inputStats[i] = new MatrixCharacteristics(rlens[i], clens[i], brlens[i], bclens[i]); } //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); RunningJob runjob = JobClient.runJob(job); /* Process different counters */ Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i].setNonZeros(group.getCounter(Integer.toString(i))); } return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:com.ibm.bi.dml.runtime.matrix.WriteCSVMR.java
License:Open Source License
public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String csvWriteInstructions, int numReducers, int replication, byte[] resultIndexes, String[] outputs) throws Exception { JobConf job = new JobConf(WriteCSVMR.class); job.setJobName("WriteCSV-MR"); byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;//from w w w. j a v a2s.c om //set up the input files and their format information MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, true, ConvertTarget.CSVWRITE); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); MRJobConfiguration.setCSVWriteInstructions(job, csvWriteInstructions); //set up the replication factor for the results job.setInt("dfs.replication", replication); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); long maxRlen = 0; for (long rlen : rlens) if (rlen > maxRlen) maxRlen = rlen; //set up the number of reducers (according to output size) int numRed = determineNumReducers(rlens, clens, ConfigurationManager.getConfig().getIntValue(DMLConfig.NUM_REDUCERS), (int) maxRlen); job.setNumReduceTasks(numRed); byte[] resultDimsUnknown = new byte[resultIndexes.length]; MatrixCharacteristics[] stats = new MatrixCharacteristics[resultIndexes.length]; OutputInfo[] outputInfos = new OutputInfo[outputs.length]; HashMap<Byte, Integer> indexmap = new HashMap<Byte, Integer>(); for (int i = 0; i < stats.length; i++) { indexmap.put(resultIndexes[i], i); resultDimsUnknown[i] = (byte) 0; stats[i] = new MatrixCharacteristics(); outputInfos[i] = OutputInfo.CSVOutputInfo; } CSVWriteInstruction[] ins = MRInstructionParser.parseCSVWriteInstructions(csvWriteInstructions); for (CSVWriteInstruction in : ins) stats[indexmap.get(in.output)].set(rlens[in.input], clens[in.input], -1, -1); // Print the complete instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); //set up what matrices are needed to pass from the mapper to reducer MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, "", "", csvWriteInstructions, resultIndexes); //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, true, true); // configure mapper and the mapper output key value pairs job.setMapperClass(CSVWriteMapper.class); job.setMapOutputKeyClass(TaggedFirstSecondIndexes.class); job.setMapOutputValueClass(MatrixBlock.class); //configure reducer job.setReducerClass(CSVWriteReducer.class); job.setOutputKeyComparatorClass(TaggedFirstSecondIndexes.Comparator.class); job.setPartitionerClass(TaggedFirstSecondIndexes.FirstIndexRangePartitioner.class); //job.setOutputFormat(UnPaddedOutputFormat.class); MatrixCharacteristics[] inputStats = new MatrixCharacteristics[inputs.length]; for (int i = 0; i < inputs.length; i++) { inputStats[i] = new MatrixCharacteristics(rlens[i], clens[i], brlens[i], bclens[i]); } //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); RunningJob runjob = JobClient.runJob(job); /* Process different counters */ Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i].setNonZeros(group.getCounter(Integer.toString(i))); } return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:com.ibm.jaql.io.hbase.TableOutputConfigurator.java
License:Apache License
public void setParallel(JobConf conf) throws Exception { conf.set(TableOutputFormat.OUTPUT_TABLE, location); conf.setOutputKeyClass(JsonHolderDefault.class); conf.setOutputValueClass(JsonHolderDefault.class); HadoopSerializationDefault.register(conf); conf.setOutputKeyComparatorClass(DefaultJsonComparator.class); }
From source file:com.manning.hip.ch4.joins.improved.impl.OptimizedDataJoinJob.java
License:Apache License
public static JobConf createDataJoinJob(String args[]) throws IOException { String inputDir = args[0];/* w w w . j a v a 2 s. co m*/ String outputDir = args[1]; Class inputFormat = SequenceFileInputFormat.class; if (args[2].compareToIgnoreCase("text") != 0) { System.out.println("Using SequenceFileInputFormat: " + args[2]); } else { System.out.println("Using TextInputFormat: " + args[2]); inputFormat = TextInputFormat.class; } int numOfReducers = Integer.parseInt(args[3]); Class mapper = getClassByName(args[4]); Class reducer = getClassByName(args[5]); Class mapoutputValueClass = getClassByName(args[6]); Class outputFormat = TextOutputFormat.class; Class outputValueClass = Text.class; if (args[7].compareToIgnoreCase("text") != 0) { System.out.println("Using SequenceFileOutputFormat: " + args[7]); outputFormat = SequenceFileOutputFormat.class; outputValueClass = getClassByName(args[7]); } else { System.out.println("Using TextOutputFormat: " + args[7]); } long maxNumOfValuesPerGroup = 100; String jobName = ""; if (args.length > 8) { maxNumOfValuesPerGroup = Long.parseLong(args[8]); } if (args.length > 9) { jobName = args[9]; } Configuration defaults = new Configuration(); JobConf job = new JobConf(defaults, OptimizedDataJoinJob.class); job.setJobName("DataJoinJob: " + jobName); FileSystem fs = FileSystem.get(defaults); fs.delete(new Path(outputDir)); FileInputFormat.setInputPaths(job, inputDir); job.setInputFormat(inputFormat); job.setMapperClass(mapper); FileOutputFormat.setOutputPath(job, new Path(outputDir)); job.setOutputFormat(outputFormat); SequenceFileOutputFormat.setOutputCompressionType(job, SequenceFile.CompressionType.BLOCK); job.setMapOutputKeyClass(CompositeKey.class); job.setMapOutputValueClass(mapoutputValueClass); job.setOutputKeyClass(Text.class); job.setOutputValueClass(outputValueClass); job.setReducerClass(reducer); job.setPartitionerClass(CompositeKeyPartitioner.class); job.setOutputKeyComparatorClass(CompositeKeyComparator.class); job.setOutputValueGroupingComparator(CompositeKeyOnlyComparator.class); job.setNumMapTasks(1); job.setNumReduceTasks(numOfReducers); job.setLong("datajoin.maxNumOfValuesPerGroup", maxNumOfValuesPerGroup); return job; }
From source file:com.TCG.Nutch_DNS.Generator.java
License:Apache License
/** * Generate fetchlists in one or more segments. Whether to filter URLs or not * is read from the crawl.generate.filter property in the configuration files. * If the property is not found, the URLs are filtered. Same for the * normalisation./* www . j a va2s .c o m*/ * * @param dbDir * Crawl database directory * @param segments * Segments directory * @param numLists * Number of reduce tasks * @param topN * Number of top URLs to be selected * @param curTime * Current time in milliseconds * * @return Path to generated segment or null if no entries were selected * * @throws IOException * When an I/O error occurs */ public Path[] generate(Path dbDir, Path segments, int numLists, long topN, long curTime, boolean filter, boolean norm, boolean force, int maxNumSegments) throws IOException { Path tempDir = new Path( getConf().get("mapred.temp.dir", ".") + "/generate-temp-" + UUID.randomUUID().toString()); Path lock = new Path(dbDir, CrawlDb.LOCK_NAME); FileSystem fs = FileSystem.get(getConf()); LockUtil.createLockFile(fs, lock, force); SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); long start = System.currentTimeMillis(); LOG.info("Generator: starting at " + sdf.format(start)); LOG.info("Generator: Selecting best-scoring urls due for fetch."); LOG.info("Generator: filtering: " + filter); LOG.info("Generator: normalizing: " + norm); if (topN != Long.MAX_VALUE) { LOG.info("Generator: topN: " + topN); } // map to inverted subset due for fetch, sort by score JobConf job = new NutchJob(getConf()); job.setJobName("generate: select from " + dbDir); if (numLists == -1) { // for politeness make numLists = job.getNumMapTasks(); // a partition per fetch task } if ("local".equals(job.get("mapred.job.tracker")) && numLists != 1) { // override LOG.info("Generator: jobtracker is 'local', generating exactly one partition."); numLists = 1; } job.setLong(GENERATOR_CUR_TIME, curTime); // record real generation time long generateTime = System.currentTimeMillis(); job.setLong(Nutch.GENERATE_TIME_KEY, generateTime); job.setLong(GENERATOR_TOP_N, topN); job.setBoolean(GENERATOR_FILTER, filter); job.setBoolean(GENERATOR_NORMALISE, norm); job.setInt(GENERATOR_MAX_NUM_SEGMENTS, maxNumSegments); FileInputFormat.addInputPath(job, new Path(dbDir, CrawlDb.CURRENT_NAME)); job.setInputFormat(SequenceFileInputFormat.class); job.setMapperClass(Selector.class); job.setPartitionerClass(Selector.class); job.setReducerClass(Selector.class); FileOutputFormat.setOutputPath(job, tempDir); job.setOutputFormat(SequenceFileOutputFormat.class); job.setOutputKeyClass(FloatWritable.class); job.setOutputKeyComparatorClass(DecreasingFloatComparator.class); job.setOutputValueClass(SelectorEntry.class); job.setOutputFormat(GeneratorOutputFormat.class); try { JobClient.runJob(job); } catch (IOException e) { LockUtil.removeLockFile(fs, lock); fs.delete(tempDir, true); throw e; } // read the subdirectories generated in the temp // output and turn them into segments List<Path> generatedSegments = new ArrayList<Path>(); FileStatus[] status = fs.listStatus(tempDir); try { for (FileStatus stat : status) { Path subfetchlist = stat.getPath(); if (!subfetchlist.getName().startsWith("fetchlist-")) continue; // start a new partition job for this segment Path newSeg = partitionSegment(fs, segments, subfetchlist, numLists); generatedSegments.add(newSeg); } } catch (Exception e) { LOG.warn("Generator: exception while partitioning segments, exiting ..."); fs.delete(tempDir, true); return null; } if (generatedSegments.size() == 0) { LOG.warn("Generator: 0 records selected for fetching, exiting ..."); LockUtil.removeLockFile(fs, lock); fs.delete(tempDir, true); return null; } if (getConf().getBoolean(GENERATE_UPDATE_CRAWLDB, false)) { // update the db from tempDir Path tempDir2 = new Path( getConf().get("mapred.temp.dir", ".") + "/generate-temp-" + UUID.randomUUID().toString()); job = new NutchJob(getConf()); job.setJobName("generate: updatedb " + dbDir); job.setLong(Nutch.GENERATE_TIME_KEY, generateTime); for (Path segmpaths : generatedSegments) { Path subGenDir = new Path(segmpaths, CrawlDatum.GENERATE_DIR_NAME); FileInputFormat.addInputPath(job, subGenDir); } FileInputFormat.addInputPath(job, new Path(dbDir, CrawlDb.CURRENT_NAME)); job.setInputFormat(SequenceFileInputFormat.class); job.setMapperClass(CrawlDbUpdater.class); job.setReducerClass(CrawlDbUpdater.class); job.setOutputFormat(MapFileOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(CrawlDatum.class); FileOutputFormat.setOutputPath(job, tempDir2); try { JobClient.runJob(job); CrawlDb.install(job, dbDir); } catch (IOException e) { LockUtil.removeLockFile(fs, lock); fs.delete(tempDir, true); fs.delete(tempDir2, true); throw e; } fs.delete(tempDir2, true); } LockUtil.removeLockFile(fs, lock); fs.delete(tempDir, true); long end = System.currentTimeMillis(); LOG.info("Generator: finished at " + sdf.format(end) + ", elapsed: " + TimingUtil.elapsedTime(start, end)); Path[] patharray = new Path[generatedSegments.size()]; return generatedSegments.toArray(patharray); }
From source file:com.trace.hadoop.examples.Grep.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length < 3) { System.out.println("Grep <inDir> <outDir> <regex> [<group>]"); ToolRunner.printGenericCommandUsage(System.out); return -1; }// www. j av a 2 s . co m Path tempDir = new Path("grep-temp-" + Integer.toString(new Random().nextInt(Integer.MAX_VALUE))); JobConf grepJob = new JobConf(getConf(), Grep.class); try { grepJob.setJobName("grep-search"); FileInputFormat.setInputPaths(grepJob, args[0]); grepJob.setMapperClass(RegexMapper.class); grepJob.set("mapred.mapper.regex", args[2]); if (args.length == 4) grepJob.set("mapred.mapper.regex.group", args[3]); grepJob.setCombinerClass(LongSumReducer.class); grepJob.setReducerClass(LongSumReducer.class); FileOutputFormat.setOutputPath(grepJob, tempDir); grepJob.setOutputFormat(SequenceFileOutputFormat.class); grepJob.setOutputKeyClass(Text.class); grepJob.setOutputValueClass(LongWritable.class); JobClient.runJob(grepJob); JobConf sortJob = new JobConf(getConf(), Grep.class); sortJob.setJobName("grep-sort"); FileInputFormat.setInputPaths(sortJob, tempDir); sortJob.setInputFormat(SequenceFileInputFormat.class); sortJob.setMapperClass(InverseMapper.class); sortJob.setNumReduceTasks(1); // write a single file FileOutputFormat.setOutputPath(sortJob, new Path(args[1])); sortJob.setOutputKeyComparatorClass // sort by decreasing freq (LongWritable.DecreasingComparator.class); JobClient.runJob(sortJob); } finally { FileSystem.get(grepJob).delete(tempDir, true); } return 0; }
From source file:crunch.MaxTemperature.java
License:Apache License
@Override
public int run(String[] args) throws IOException {
JobConf conf = JobBuilder.parseInputAndOutput(this, getConf(), args);
if (conf == null) {
return -1;
}/*w ww.ja v a 2 s.c om*/
conf.setMapperClass(MaxTemperatureMapper.class);
/*[*/conf.setPartitionerClass(FirstPartitioner.class);
/*]*/
/*[*/conf.setOutputKeyComparatorClass(KeyComparator.class);
/*]*/
/*[*/conf.setOutputValueGroupingComparator(GroupComparator.class);/*]*/
conf.setReducerClass(MaxTemperatureReducer.class);
conf.setOutputKeyClass(IntPair.class);
conf.setOutputValueClass(NullWritable.class);
JobClient.runJob(conf);
return 0;
}
From source file:de.l3s.streamcorpus.mapreduce.TerrierIndexing.java
License:Mozilla Public License
/** Starts the MapReduce indexing. * @param args//from ww w . j av a 2s . c om * @throws Exception */ public int run(String[] args) throws Exception { long time = System.currentTimeMillis(); // For the moment: Hard-code the terrier home to quick test System.setProperty("terrier.home", "/home/tuan.tran/executable/StreamCorpusIndexer"); boolean docPartitioned = false; int numberOfReducers = Integer .parseInt(ApplicationSetup.getProperty("terrier.hadoop.indexing.reducers", "26")); final HadoopPlugin.JobFactory jf = HadoopPlugin.getJobFactory("HOD-TerrierIndexing"); if (args.length == 2 && args[0].equals("-p")) { logger.debug("Document-partitioned Mode, " + numberOfReducers + " output indices."); numberOfReducers = Integer.parseInt(args[1]); docPartitioned = true; } else if (args.length == 1 && args[0].equals("--merge")) { if (numberOfReducers > 1) mergeLexiconInvertedFiles(ApplicationSetup.TERRIER_INDEX_PATH, numberOfReducers); else logger.error("No point merging 1 reduce task output"); return 0; } else if (args.length == 0) { logger.debug("Term-partitioned Mode, " + numberOfReducers + " reducers creating one inverted index."); docPartitioned = false; if (numberOfReducers > MAX_REDUCE) { logger.warn("Excessive reduce tasks (" + numberOfReducers + ") in use " + "- SplitEmittedTerm.SETPartitionerLowercaseAlphaTerm can use " + MAX_REDUCE + " at most"); } } /*else { logger.fatal(usage()); return 0; }*/ if (!(CompressionFactory.getCompressionConfiguration("inverted", new String[0], false) instanceof BitCompressionConfiguration)) { logger.error("Sorry, only default BitCompressionConfiguration is supported by HadoopIndexing" + " - you can recompress the inverted index later using IndexRecompressor"); return 0; } if (jf == null) throw new Exception("Could not get JobFactory from HadoopPlugin"); final JobConf conf = jf.newJob(); conf.setJarByClass(TerrierIndexing.class); conf.setJobName("StreamCorpusIndexer: Terrier Indexing"); if (Files.exists(ApplicationSetup.TERRIER_INDEX_PATH) && Index.existsIndex(ApplicationSetup.TERRIER_INDEX_PATH, ApplicationSetup.TERRIER_INDEX_PREFIX)) { logger.fatal("Cannot index while index exists at " + ApplicationSetup.TERRIER_INDEX_PATH + "," + ApplicationSetup.TERRIER_INDEX_PREFIX); return 0; } // boolean blockIndexing = ApplicationSetup.BLOCK_INDEXING; boolean blockIndexing = true; if (blockIndexing) { conf.setMapperClass(Hadoop_BlockSinglePassIndexer.class); conf.setReducerClass(Hadoop_BlockSinglePassIndexer.class); } else { conf.setMapperClass(Hadoop_BasicSinglePassIndexer.class); conf.setReducerClass(Hadoop_BasicSinglePassIndexer.class); } FileOutputFormat.setOutputPath(conf, new Path(ApplicationSetup.TERRIER_INDEX_PATH)); conf.set("indexing.hadoop.prefix", ApplicationSetup.TERRIER_INDEX_PREFIX); conf.setMapOutputKeyClass(SplitEmittedTerm.class); conf.setMapOutputValueClass(MapEmittedPostingList.class); conf.setBoolean("indexing.hadoop.multiple.indices", docPartitioned); if (!conf.get("mapred.job.tracker").equals("local")) { conf.setMapOutputCompressorClass(GzipCodec.class); conf.setCompressMapOutput(true); } else { conf.setCompressMapOutput(false); } conf.setInputFormat(MultiFileCollectionInputFormat.class); conf.setOutputFormat(NullOutputFormat.class); conf.setOutputKeyComparatorClass(SplitEmittedTerm.SETRawComparatorTermSplitFlush.class); conf.setOutputValueGroupingComparator(SplitEmittedTerm.SETRawComparatorTerm.class); conf.setReduceSpeculativeExecution(false); //parse the collection.spec BufferedReader specBR = Files.openFileReader(ApplicationSetup.COLLECTION_SPEC); String line = null; List<Path> paths = new ArrayList<Path>(); while ((line = specBR.readLine()) != null) { if (line.startsWith("#")) continue; paths.add(new Path(line)); } specBR.close(); FileInputFormat.setInputPaths(conf, paths.toArray(new Path[paths.size()])); // not sure if this is effective in YARN conf.setNumMapTasks(2000); // increase the heap usage conf.set("mapreduce.map.memory.mb", "6100"); conf.set("mapred.job.map.memory.mb", "6100"); conf.set("mapreduce.reduce.memory.mb", "6144"); conf.set("mapred.job.reduce.memory.mb", "6144"); conf.set("mapreduce.map.java.opts", "-Xmx6100m"); conf.set("mapred.map.child.java.opts", "-Xmx6100m"); conf.set("mapreduce.reduce.java.opts", "-Xmx6144m"); conf.set("mapred.reduce.child.opts", "-Xmx6144m"); //conf.setBoolean("mapred.used.genericoptionsparser", true) ; // This is the nasty thing in MapReduce v2 and YARN: They always prefer their ancient jars first. Set this on to say you don't like it conf.set("mapreduce.job.user.classpath.first", "true"); // increase the yarn memory to 10 GB conf.set("yarn.nodemanager.resource.memory-mb", "12288"); conf.set("yarn.nodemanager.resource.cpu-vcores", "16"); conf.set("yarn.scheduler.minimum-allocation-mb", "4096"); conf.setNumReduceTasks(numberOfReducers); if (numberOfReducers > 1) { if (docPartitioned) conf.setPartitionerClass(SplitEmittedTerm.SETPartitioner.class); else conf.setPartitionerClass(SplitEmittedTerm.SETPartitionerLowercaseAlphaTerm.class); } else { //for JUnit tests, we seem to need to restore the original partitioner class conf.setPartitionerClass(HashPartitioner.class); } /*JobID jobId = null; boolean ranOK = true; try{ RunningJob rj = JobClient.runJob(conf); jobId = rj.getID(); HadoopUtility.finishTerrierJob(conf); } catch (Exception e) { logger.error("Problem running job", e); e.printStackTrace(); ranOK = false; } if (jobId != null) { deleteTaskFiles(ApplicationSetup.TERRIER_INDEX_PATH, jobId); } */ //if (ranOK) //{ System.out.println("Merging indices"); if (!docPartitioned) { if (numberOfReducers > 1) mergeLexiconInvertedFiles(ApplicationSetup.TERRIER_INDEX_PATH, numberOfReducers); } Hadoop_BasicSinglePassIndexer.finish(ApplicationSetup.TERRIER_INDEX_PATH, docPartitioned ? numberOfReducers : 1, jf); //} System.out.println("Time Taken = " + ((System.currentTimeMillis() - time) / 1000) + " seconds"); jf.close(); return 0; }
From source file:de.l3s.streamcorpus.StreamCorpusIndexing.java
License:Mozilla Public License
/** Starts the MapReduce indexing. * @param args//from w w w . j av a2 s. c o m * @throws Exception */ public int run(String[] args) throws Exception { long time = System.currentTimeMillis(); // For the moment: Hard-code the terrier home to quick test System.setProperty("terrier.home", "/home/tuan.tran/executable/StreamCorpusIndexer"); boolean docPartitioned = false; int numberOfReducers = Integer .parseInt(ApplicationSetup.getProperty("terrier.hadoop.indexing.reducers", "26")); final HadoopPlugin.JobFactory jf = HadoopPlugin.getJobFactory("HOD-TerrierIndexing"); if (args.length == 2 && args[0].equals("-p")) { logger.debug("Document-partitioned Mode, " + numberOfReducers + " output indices."); numberOfReducers = Integer.parseInt(args[1]); docPartitioned = true; } else if (args.length == 1 && args[0].equals("--merge")) { if (numberOfReducers > 1) mergeLexiconInvertedFiles(ApplicationSetup.TERRIER_INDEX_PATH, numberOfReducers); else logger.error("No point merging 1 reduce task output"); return 0; } else if (args.length == 0) { logger.debug("Term-partitioned Mode, " + numberOfReducers + " reducers creating one inverted index."); docPartitioned = false; if (numberOfReducers > MAX_REDUCE) { logger.warn("Excessive reduce tasks (" + numberOfReducers + ") in use " + "- SplitEmittedTerm.SETPartitionerLowercaseAlphaTerm can use " + MAX_REDUCE + " at most"); } } /*else { logger.fatal(usage()); return 0; }*/ if (!(CompressionFactory.getCompressionConfiguration("inverted", new String[0], false) instanceof BitCompressionConfiguration)) { logger.error("Sorry, only default BitCompressionConfiguration is supported by HadoopIndexing" + " - you can recompress the inverted index later using IndexRecompressor"); return 0; } if (jf == null) throw new Exception("Could not get JobFactory from HadoopPlugin"); final JobConf conf = jf.newJob(); conf.setJarByClass(StreamCorpusIndexing.class); conf.setJobName("StreamCorpusIndexer: Terrier Indexing"); if (Files.exists(ApplicationSetup.TERRIER_INDEX_PATH) && Index.existsIndex(ApplicationSetup.TERRIER_INDEX_PATH, ApplicationSetup.TERRIER_INDEX_PREFIX)) { logger.fatal("Cannot index while index exists at " + ApplicationSetup.TERRIER_INDEX_PATH + "," + ApplicationSetup.TERRIER_INDEX_PREFIX); return 0; } // boolean blockIndexing = ApplicationSetup.BLOCK_INDEXING; boolean blockIndexing = true; if (blockIndexing) { conf.setMapperClass(Hadoop_BlockSinglePassIndexer.class); conf.setReducerClass(Hadoop_BlockSinglePassIndexer.class); } else { conf.setMapperClass(Hadoop_BasicSinglePassIndexer.class); conf.setReducerClass(Hadoop_BasicSinglePassIndexer.class); } FileOutputFormat.setOutputPath(conf, new Path(ApplicationSetup.TERRIER_INDEX_PATH)); conf.set("indexing.hadoop.prefix", ApplicationSetup.TERRIER_INDEX_PREFIX); conf.setMapOutputKeyClass(SplitEmittedTerm.class); conf.setMapOutputValueClass(MapEmittedPostingList.class); conf.setBoolean("indexing.hadoop.multiple.indices", docPartitioned); if (!conf.get("mapred.job.tracker").equals("local")) { conf.setMapOutputCompressorClass(GzipCodec.class); conf.setCompressMapOutput(true); } else { conf.setCompressMapOutput(false); } conf.setInputFormat(MultiFileCollectionInputFormat.class); conf.setOutputFormat(NullOutputFormat.class); conf.setOutputKeyComparatorClass(SplitEmittedTerm.SETRawComparatorTermSplitFlush.class); conf.setOutputValueGroupingComparator(SplitEmittedTerm.SETRawComparatorTerm.class); conf.setReduceSpeculativeExecution(false); //parse the collection.spec BufferedReader specBR = Files.openFileReader(ApplicationSetup.COLLECTION_SPEC); String line = null; List<Path> paths = new ArrayList<Path>(); while ((line = specBR.readLine()) != null) { if (line.startsWith("#")) continue; paths.add(new Path(line)); } specBR.close(); FileInputFormat.setInputPaths(conf, paths.toArray(new Path[paths.size()])); // not sure if this is effective in YARN conf.setNumMapTasks(2000); // increase the heap usage conf.set("mapreduce.map.memory.mb", "6100"); conf.set("mapred.job.map.memory.mb", "6100"); conf.set("mapreduce.reduce.memory.mb", "6144"); conf.set("mapred.job.reduce.memory.mb", "6144"); conf.set("mapreduce.map.java.opts", "-Xmx6100m"); conf.set("mapred.map.child.java.opts", "-Xmx6100m"); conf.set("mapreduce.reduce.java.opts", "-Xmx6144m"); conf.set("mapred.reduce.child.opts", "-Xmx6144m"); //conf.setBoolean("mapred.used.genericoptionsparser", true) ; // This is the nasty thing in MapReduce v2 and YARN: They always prefer their ancient jars first. Set this on to say you don't like it conf.set("mapreduce.job.user.classpath.first", "true"); // increase the yarn memory to 10 GB conf.set("yarn.nodemanager.resource.memory-mb", "12288"); conf.set("yarn.nodemanager.resource.cpu-vcores", "16"); conf.set("yarn.scheduler.minimum-allocation-mb", "4096"); conf.setNumReduceTasks(numberOfReducers); if (numberOfReducers > 1) { if (docPartitioned) conf.setPartitionerClass(SplitEmittedTerm.SETPartitioner.class); else conf.setPartitionerClass(SplitEmittedTerm.SETPartitionerLowercaseAlphaTerm.class); } else { //for JUnit tests, we seem to need to restore the original partitioner class conf.setPartitionerClass(HashPartitioner.class); } /*JobID jobId = null; boolean ranOK = true; try{ RunningJob rj = JobClient.runJob(conf); jobId = rj.getID(); HadoopUtility.finishTerrierJob(conf); } catch (Exception e) { logger.error("Problem running job", e); e.printStackTrace(); ranOK = false; } if (jobId != null) { deleteTaskFiles(ApplicationSetup.TERRIER_INDEX_PATH, jobId); } */ //if (ranOK) //{ System.out.println("Merging indices"); if (!docPartitioned) { if (numberOfReducers > 1) mergeLexiconInvertedFiles(ApplicationSetup.TERRIER_INDEX_PATH, numberOfReducers); } Hadoop_BasicSinglePassIndexer.finish(ApplicationSetup.TERRIER_INDEX_PATH, docPartitioned ? numberOfReducers : 1, jf); //} System.out.println("Time Taken = " + ((System.currentTimeMillis() - time) / 1000) + " seconds"); jf.close(); return 0; }
From source file:drivers.FinishPageRank.java
@Override public int run(String[] args) throws Exception { Configuration conf = getConf(); JobConf job = new JobConf(conf, this.getClass()); Path in = new Path(args[0]); Path out = new Path(args[1]); FileInputFormat.setInputPaths(job, in); FileOutputFormat.setOutputPath(job, out); job.setJobName("Fiqie|Finish"); job.setOutputKeyComparatorClass(DecreasingComparator.class); job.setMapperClass(SortingPageRankMapper.class); job.setReducerClass(SortingPageRankReducer.class); job.setInputFormat(KeyValueTextInputFormat.class); job.setOutputFormat(TextOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); JobClient.runJob(job);// w w w .j a v a 2s. c om return 0; }