List of usage examples for org.apache.hadoop.mapred JobConf setJarByClass
public void setJarByClass(Class cls)
From source file:DistribCountingDriver.java
License:Apache License
public int run(String args[]) throws Exception { long job_start_time, job_end_time; long job_runtime; JobConf conf = new JobConf(getConf()); int minFreqPercent = Integer.parseInt(args[0]); int datasetSize = Integer.parseInt(args[1]); conf.setInt("DISTRCOUNT.datasetSize", datasetSize); conf.setInt("DISTRCOUNT.minFreqPercent", minFreqPercent); conf.setBoolean("mapred.reduce.tasks.speculative.execution", false); conf.setInt("mapred.task.timeout", 60000000); conf.setJarByClass(DistribCountingDriver.class); conf.setMapOutputKeyClass(Text.class); conf.setMapOutputValueClass(IntWritable.class); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); conf.setMapperClass(DistribCountingMapper.class); conf.setCombinerClass(DistribCountingCombiner.class); conf.setReducerClass(DistribCountingReducer.class); conf.setInputFormat(SequenceFileInputFormat.class); SequenceFileInputFormat.addInputPath(conf, new Path(args[2])); FileOutputFormat.setOutputPath(conf, new Path(args[3])); job_start_time = System.currentTimeMillis(); JobClient.runJob(conf);/*from ww w . java2 s . c o m*/ job_end_time = System.currentTimeMillis(); job_runtime = (job_end_time - job_start_time) / 1000; System.out.println("total job runtime (seconds): " + job_runtime); return 0; }
From source file:MRDriver.java
License:Apache License
public int run(String args[]) throws Exception { FileSystem fs = null;/*from w ww. j a v a2s . c o m*/ Path samplesMapPath = null; float epsilon = Float.parseFloat(args[0]); double delta = Double.parseDouble(args[1]); int minFreqPercent = Integer.parseInt(args[2]); int d = Integer.parseInt(args[3]); int datasetSize = Integer.parseInt(args[4]); int numSamples = Integer.parseInt(args[5]); double phi = Double.parseDouble(args[6]); Random rand; /************************ Job 1 (local FIM) Configuration ************************/ JobConf conf = new JobConf(getConf()); /* * Compute the number of required "votes" for an itemsets to be * declared frequent */ // The +1 at the end is needed to ensure reqApproxNum > numsamples / 2. int reqApproxNum = (int) Math .floor((numSamples * (1 - phi)) - Math.sqrt(numSamples * (1 - phi) * 2 * Math.log(1 / delta))) + 1; int sampleSize = (int) Math.ceil((2 / Math.pow(epsilon, 2)) * (d + Math.log(1 / phi))); //System.out.println("reducersNum: " + numSamples + " reqApproxNum: " + reqApproxNum); conf.setInt("PARMM.reducersNum", numSamples); conf.setInt("PARMM.datasetSize", datasetSize); conf.setInt("PARMM.minFreqPercent", minFreqPercent); conf.setInt("PARMM.sampleSize", sampleSize); conf.setFloat("PARMM.epsilon", epsilon); // Set the number of reducers equal to the number of samples, to // maximize parallelism. Required by our Partitioner. conf.setNumReduceTasks(numSamples); // XXX: why do we disable the speculative execution? MR conf.setBoolean("mapred.reduce.tasks.speculative.execution", false); conf.setInt("mapred.task.timeout", MR_TIMEOUT_MILLI); /* * Enable compression of map output. * * We do it for this job and not for the aggregation one because * each mapper there only print out one record for each itemset, * so there isn't much to compress, I'd say. MR * * In Amazon MapReduce compression of the map output seems to be * happen by default and the Snappy codec is used, which is * extremely fast. */ conf.setBoolean("mapred.compress.map.output", true); //conf.setMapOutputCompressorClass(com.hadoop.compression.lzo.LzoCodec.class); conf.setJarByClass(MRDriver.class); conf.setMapOutputKeyClass(IntWritable.class); conf.setMapOutputValueClass(Text.class); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(DoubleWritable.class); conf.setInputFormat(SequenceFileInputFormat.class); // We write the collections found in a reducers as a SequenceFile conf.setOutputFormat(SequenceFileOutputFormat.class); SequenceFileOutputFormat.setOutputPath(conf, new Path(args[9])); // set the mapper class based on command line option switch (Integer.parseInt(args[7])) { case 1: System.out.println("running partition mapper..."); SequenceFileInputFormat.addInputPath(conf, new Path(args[8])); conf.setMapperClass(PartitionMapper.class); break; case 2: System.out.println("running binomial mapper..."); SequenceFileInputFormat.addInputPath(conf, new Path(args[8])); conf.setMapperClass(BinomialSamplerMapper.class); break; case 3: System.out.println("running coin mapper..."); SequenceFileInputFormat.addInputPath(conf, new Path(args[8])); conf.setMapperClass(CoinFlipSamplerMapper.class); case 4: System.out.println("running sampler mapper..."); SequenceFileInputFormat.addInputPath(conf, new Path(args[8])); conf.setMapperClass(InputSamplerMapper.class); // create a random sample of size T*m rand = new Random(); long sampling_start_time = System.nanoTime(); int[] samples = new int[numSamples * sampleSize]; for (int i = 0; i < numSamples * sampleSize; i++) { samples[i] = rand.nextInt(datasetSize); } // for each key in the sample, create a list of all T samples to which this key belongs Hashtable<LongWritable, ArrayList<IntWritable>> hashTable = new Hashtable<LongWritable, ArrayList<IntWritable>>(); for (int i = 0; i < numSamples * sampleSize; i++) { ArrayList<IntWritable> sampleIDs = null; LongWritable key = new LongWritable(samples[i]); if (hashTable.containsKey(key)) sampleIDs = hashTable.get(key); else sampleIDs = new ArrayList<IntWritable>(); sampleIDs.add(new IntWritable(i % numSamples)); hashTable.put(key, sampleIDs); } /* * Convert the Hastable to a MapWritable which we will * write to HDFS and distribute to all Mappers using * DistributedCache */ MapWritable map = new MapWritable(); for (LongWritable key : hashTable.keySet()) { ArrayList<IntWritable> sampleIDs = hashTable.get(key); IntArrayWritable sampleIDsIAW = new IntArrayWritable(); sampleIDsIAW.set(sampleIDs.toArray(new IntWritable[sampleIDs.size()])); map.put(key, sampleIDsIAW); } fs = FileSystem.get(URI.create("samplesMap.ser"), conf); samplesMapPath = new Path("samplesMap.ser"); FSDataOutputStream out = fs.create(samplesMapPath, true); map.write(out); out.sync(); out.close(); DistributedCache.addCacheFile(new URI(fs.getWorkingDirectory() + "/samplesMap.ser#samplesMap.ser"), conf); // stop the sampling timer long sampling_end_time = System.nanoTime(); long sampling_runtime = (sampling_end_time - sampling_start_time) / 1000000; System.out.println("sampling runtime (milliseconds): " + sampling_runtime); break; // end switch case case 5: System.out.println("running random integer partition mapper..."); conf.setInputFormat(WholeSplitInputFormat.class); Path inputFilePath = new Path(args[8]); WholeSplitInputFormat.addInputPath(conf, inputFilePath); conf.setMapperClass(RandIntPartSamplerMapper.class); // Compute number of map tasks. fs = inputFilePath.getFileSystem(conf); FileStatus inputFileStatus = fs.getFileStatus(inputFilePath); long len = inputFileStatus.getLen(); long blockSize = inputFileStatus.getBlockSize(); conf.setLong("mapred.min.split.size", blockSize); conf.setLong("mapred.max.split.size", blockSize); int mapTasksNum = ((int) (len / blockSize)) + 1; conf.setNumMapTasks(mapTasksNum); //System.out.println("len: " + len + " blockSize: " // + blockSize + " mapTasksNum: " + mapTasksNum); // Extract random integer partition of total sample // size into up to mapTasksNum partitions. // XXX I'm not sure this is a correct way to do // it. rand = new Random(); IntWritable[][] toSampleArr = new IntWritable[mapTasksNum][numSamples]; for (int j = 0; j < numSamples; j++) { IntWritable[] tempToSampleArr = new IntWritable[mapTasksNum]; int sum = 0; int i; for (i = 0; i < mapTasksNum - 1; i++) { int size = rand.nextInt(sampleSize - sum); tempToSampleArr[i] = new IntWritable(size); sum += size; if (sum > numSamples * sampleSize) { System.out.println("Something went wrong generating the sample Sizes"); System.exit(1); } if (sum == sampleSize) { break; } } if (i == mapTasksNum - 1) { tempToSampleArr[i] = new IntWritable(sampleSize - sum); } else { for (; i < mapTasksNum; i++) { tempToSampleArr[i] = new IntWritable(0); } } Collections.shuffle(Arrays.asList(tempToSampleArr)); for (i = 0; i < mapTasksNum; i++) { toSampleArr[i][j] = tempToSampleArr[i]; } } for (int i = 0; i < mapTasksNum; i++) { DefaultStringifier.storeArray(conf, toSampleArr[i], "PARMM.toSampleArr_" + i); } break; default: System.err.println("Wrong Mapper ID. Can only be in [1,5]"); System.exit(1); break; } /* * We don't use the default hash partitioner because we want to * maximize the parallelism. That's why we also fix the number * of reducers. */ conf.setPartitionerClass(FIMPartitioner.class); conf.setReducerClass(FIMReducer.class); /************************ Job 2 (aggregation) Configuration ************************/ JobConf confAggr = new JobConf(getConf()); confAggr.setInt("PARMM.reducersNum", numSamples); confAggr.setInt("PARMM.reqApproxNum", reqApproxNum); confAggr.setInt("PARMM.sampleSize", sampleSize); confAggr.setFloat("PARMM.epsilon", epsilon); // XXX: Why do we disable speculative execution? MR confAggr.setBoolean("mapred.reduce.tasks.speculative.execution", false); confAggr.setInt("mapred.task.timeout", MR_TIMEOUT_MILLI); confAggr.setJarByClass(MRDriver.class); confAggr.setMapOutputKeyClass(Text.class); confAggr.setMapOutputValueClass(DoubleWritable.class); confAggr.setOutputKeyClass(Text.class); confAggr.setOutputValueClass(Text.class); confAggr.setMapperClass(AggregateMapper.class); confAggr.setReducerClass(AggregateReducer.class); confAggr.setInputFormat(CombineSequenceFileInputFormat.class); SequenceFileInputFormat.addInputPath(confAggr, new Path(args[9])); FileOutputFormat.setOutputPath(confAggr, new Path(args[10])); long FIMjob_start_time = System.currentTimeMillis(); RunningJob FIMjob = JobClient.runJob(conf); long FIMjob_end_time = System.currentTimeMillis(); RunningJob aggregateJob = JobClient.runJob(confAggr); long aggrJob_end_time = System.currentTimeMillis(); long FIMjob_runtime = FIMjob_end_time - FIMjob_start_time; long aggrJob_runtime = aggrJob_end_time - FIMjob_end_time; if (args[7].equals("4")) { // Remove samplesMap file fs.delete(samplesMapPath, false); } Counters counters = FIMjob.getCounters(); Counters.Group FIMMapperStartTimesCounters = counters.getGroup("FIMMapperStart"); long[] FIMMapperStartTimes = new long[FIMMapperStartTimesCounters.size()]; int i = 0; for (Counters.Counter counter : FIMMapperStartTimesCounters) { FIMMapperStartTimes[i++] = counter.getCounter(); } Counters.Group FIMMapperEndTimesCounters = counters.getGroup("FIMMapperEnd"); long[] FIMMapperEndTimes = new long[FIMMapperEndTimesCounters.size()]; i = 0; for (Counters.Counter counter : FIMMapperEndTimesCounters) { FIMMapperEndTimes[i++] = counter.getCounter(); } Counters.Group FIMReducerStartTimesCounters = counters.getGroup("FIMReducerStart"); long[] FIMReducerStartTimes = new long[FIMReducerStartTimesCounters.size()]; i = 0; for (Counters.Counter counter : FIMReducerStartTimesCounters) { FIMReducerStartTimes[i++] = counter.getCounter(); } Counters.Group FIMReducerEndTimesCounters = counters.getGroup("FIMReducerEnd"); long[] FIMReducerEndTimes = new long[FIMReducerEndTimesCounters.size()]; i = 0; for (Counters.Counter counter : FIMReducerEndTimesCounters) { FIMReducerEndTimes[i++] = counter.getCounter(); } Counters countersAggr = aggregateJob.getCounters(); Counters.Group AggregateMapperStartTimesCounters = countersAggr.getGroup("AggregateMapperStart"); long[] AggregateMapperStartTimes = new long[AggregateMapperStartTimesCounters.size()]; i = 0; for (Counters.Counter counter : AggregateMapperStartTimesCounters) { AggregateMapperStartTimes[i++] = counter.getCounter(); } Counters.Group AggregateMapperEndTimesCounters = countersAggr.getGroup("AggregateMapperEnd"); long[] AggregateMapperEndTimes = new long[AggregateMapperEndTimesCounters.size()]; i = 0; for (Counters.Counter counter : AggregateMapperEndTimesCounters) { AggregateMapperEndTimes[i++] = counter.getCounter(); } Counters.Group AggregateReducerStartTimesCounters = countersAggr.getGroup("AggregateReducerStart"); long[] AggregateReducerStartTimes = new long[AggregateReducerStartTimesCounters.size()]; i = 0; for (Counters.Counter counter : AggregateReducerStartTimesCounters) { AggregateReducerStartTimes[i++] = counter.getCounter(); } Counters.Group AggregateReducerEndTimesCounters = countersAggr.getGroup("AggregateReducerEnd"); long[] AggregateReducerEndTimes = new long[AggregateReducerEndTimesCounters.size()]; i = 0; for (Counters.Counter counter : AggregateReducerEndTimesCounters) { AggregateReducerEndTimes[i++] = counter.getCounter(); } long FIMMapperStartMin = FIMMapperStartTimes[0]; for (long l : FIMMapperStartTimes) { if (l < FIMMapperStartMin) { FIMMapperStartMin = l; } } long FIMMapperEndMax = FIMMapperEndTimes[0]; for (long l : FIMMapperEndTimes) { if (l > FIMMapperEndMax) { FIMMapperEndMax = l; } } System.out.println("FIM job setup time (milliseconds): " + (FIMMapperStartMin - FIMjob_start_time)); System.out.println("FIMMapper total runtime (milliseconds): " + (FIMMapperEndMax - FIMMapperStartMin)); long[] FIMMapperRunTimes = new long[FIMMapperStartTimes.length]; long FIMMapperRunTimesSum = 0; for (int l = 0; l < FIMMapperStartTimes.length; l++) { FIMMapperRunTimes[l] = FIMMapperEndTimes[l] - FIMMapperStartTimes[l]; FIMMapperRunTimesSum += FIMMapperRunTimes[l]; } System.out.println("FIMMapper average task runtime (milliseconds): " + FIMMapperRunTimesSum / FIMMapperStartTimes.length); long FIMMapperRunTimesMin = FIMMapperRunTimes[0]; long FIMMapperRunTimesMax = FIMMapperRunTimes[0]; for (long l : FIMMapperRunTimes) { if (l < FIMMapperRunTimesMin) { FIMMapperRunTimesMin = l; } if (l > FIMMapperRunTimesMax) { FIMMapperRunTimesMax = l; } } System.out.println("FIMMapper minimum task runtime (milliseconds): " + FIMMapperRunTimesMin); System.out.println("FIMMapper maximum task runtime (milliseconds): " + FIMMapperRunTimesMax); long FIMReducerStartMin = FIMReducerStartTimes[0]; for (long l : FIMReducerStartTimes) { if (l < FIMReducerStartMin) { FIMReducerStartMin = l; } } long FIMReducerEndMax = FIMReducerEndTimes[0]; for (long l : FIMReducerEndTimes) { if (l > FIMReducerEndMax) { FIMReducerEndMax = l; } } System.out .println("FIM job shuffle phase runtime (milliseconds): " + (FIMReducerStartMin - FIMMapperEndMax)); System.out.println("FIMReducer total runtime (milliseconds): " + (FIMReducerEndMax - FIMReducerStartMin)); long[] FIMReducerRunTimes = new long[FIMReducerStartTimes.length]; long FIMReducerRunTimesSum = 0; for (int l = 0; l < FIMReducerStartTimes.length; l++) { FIMReducerRunTimes[l] = FIMReducerEndTimes[l] - FIMReducerStartTimes[l]; FIMReducerRunTimesSum += FIMReducerRunTimes[l]; } System.out.println("FIMReducer average task runtime (milliseconds): " + FIMReducerRunTimesSum / FIMReducerStartTimes.length); long FIMReducerRunTimesMin = FIMReducerRunTimes[0]; long FIMReducerRunTimesMax = FIMReducerRunTimes[0]; for (long l : FIMReducerRunTimes) { if (l < FIMReducerRunTimesMin) { FIMReducerRunTimesMin = l; } if (l > FIMReducerRunTimesMax) { FIMReducerRunTimesMax = l; } } System.out.println("FIMReducer minimum task runtime (milliseconds): " + FIMReducerRunTimesMin); System.out.println("FIMReducer maximum task runtime (milliseconds): " + FIMReducerRunTimesMax); System.out.println("FIM job cooldown time (milliseconds): " + (FIMjob_end_time - FIMReducerEndMax)); long AggregateMapperStartMin = AggregateMapperStartTimes[0]; for (long l : AggregateMapperStartTimes) { if (l < AggregateMapperStartMin) { AggregateMapperStartMin = l; } } long AggregateMapperEndMax = AggregateMapperEndTimes[0]; for (long l : AggregateMapperEndTimes) { if (l > AggregateMapperEndMax) { AggregateMapperEndMax = l; } } System.out.println( "Aggregation job setup time (milliseconds): " + (AggregateMapperStartMin - FIMjob_end_time)); System.out.println("AggregateMapper total runtime (milliseconds): " + (AggregateMapperEndMax - AggregateMapperStartMin)); long[] AggregateMapperRunTimes = new long[AggregateMapperStartTimes.length]; long AggregateMapperRunTimesSum = 0; for (int l = 0; l < AggregateMapperStartTimes.length; l++) { AggregateMapperRunTimes[l] = AggregateMapperEndTimes[l] - AggregateMapperStartTimes[l]; AggregateMapperRunTimesSum += AggregateMapperRunTimes[l]; } System.out.println("AggregateMapper average task runtime (milliseconds): " + AggregateMapperRunTimesSum / AggregateMapperStartTimes.length); long AggregateMapperRunTimesMin = AggregateMapperRunTimes[0]; long AggregateMapperRunTimesMax = AggregateMapperRunTimes[0]; for (long l : AggregateMapperRunTimes) { if (l < AggregateMapperRunTimesMin) { AggregateMapperRunTimesMin = l; } if (l > AggregateMapperRunTimesMax) { AggregateMapperRunTimesMax = l; } } System.out.println("AggregateMapper minimum task runtime (milliseconds): " + AggregateMapperRunTimesMin); System.out.println("AggregateMapper maximum task runtime (milliseconds): " + AggregateMapperRunTimesMax); long AggregateReducerStartMin = AggregateReducerStartTimes[0]; for (long l : AggregateReducerStartTimes) { if (l < AggregateReducerStartMin) { AggregateReducerStartMin = l; } } long AggregateReducerEndMax = AggregateReducerEndTimes[0]; for (long l : AggregateReducerEndTimes) { if (l > AggregateReducerEndMax) { AggregateReducerEndMax = l; } } System.out.println("Aggregate job round shuffle phase runtime (milliseconds): " + (AggregateReducerStartMin - AggregateMapperEndMax)); System.out.println("AggregateReducer total runtime (milliseconds): " + (AggregateReducerEndMax - AggregateReducerStartMin)); long[] AggregateReducerRunTimes = new long[AggregateReducerStartTimes.length]; long AggregateReducerRunTimesSum = 0; for (int l = 0; l < AggregateReducerStartTimes.length; l++) { AggregateReducerRunTimes[l] = AggregateReducerEndTimes[l] - AggregateReducerStartTimes[l]; AggregateReducerRunTimesSum += AggregateReducerRunTimes[l]; } System.out.println("AggregateReducer average task runtime (milliseconds): " + AggregateReducerRunTimesSum / AggregateReducerStartTimes.length); long AggregateReducerRunTimesMin = AggregateReducerRunTimes[0]; long AggregateReducerRunTimesMax = AggregateReducerRunTimes[0]; for (long l : AggregateReducerRunTimes) { if (l < AggregateReducerRunTimesMin) { AggregateReducerRunTimesMin = l; } if (l > AggregateReducerRunTimesMax) { AggregateReducerRunTimesMax = l; } } System.out.println("AggregateReducer minimum task runtime (milliseconds): " + AggregateReducerRunTimesMin); System.out.println("AggregateReducer maximum task runtime (milliseconds): " + AggregateReducerRunTimesMax); System.out.println( "Aggregation job cooldown time (milliseconds): " + (aggrJob_end_time - AggregateReducerEndMax)); System.out .println("total runtime (all inclusive) (milliseconds): " + (aggrJob_end_time - FIMjob_start_time)); System.out.println("total runtime (no FIM job setup, no aggregation job cooldown) (milliseconds): " + (AggregateReducerEndMax - FIMMapperStartMin)); System.out.println("total runtime (no setups, no cooldowns) (milliseconds): " + (FIMReducerEndMax - FIMMapperStartMin + AggregateReducerEndMax - AggregateMapperStartMin)); System.out.println("FIM job runtime (including setup and cooldown) (milliseconds): " + FIMjob_runtime); System.out.println("FIM job runtime (no setup, no cooldown) (milliseconds): " + (FIMReducerEndMax - FIMMapperStartMin)); System.out.println( "Aggregation job runtime (including setup and cooldown) (milliseconds): " + aggrJob_runtime); System.out.println("Aggregation job runtime (no setup, no cooldown) (milliseconds): " + (AggregateReducerEndMax - AggregateMapperStartMin)); return 0; }
From source file:WikipediaDocnoMappingBuilder.java
License:Apache License
@SuppressWarnings("static-access") @Override/*from w ww .jav a 2 s .c o m*/ public int run(String[] args) throws Exception { Options options = new Options(); options.addOption( OptionBuilder.withArgName("path").hasArg().withDescription("XML dump file").create(INPUT_OPTION)); options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output file") .create(OUTPUT_FILE_OPTION)); options.addOption(OptionBuilder.withArgName("en|sv|de|cs|es|zh|ar|tr").hasArg() .withDescription("two-letter language code").create(LANGUAGE_OPTION)); options.addOption(KEEP_ALL_OPTION, false, "keep all pages"); CommandLine cmdline; CommandLineParser parser = new GnuParser(); try { cmdline = parser.parse(options, args); } catch (ParseException exp) { System.err.println("Error parsing command line: " + exp.getMessage()); return -1; } if (!cmdline.hasOption(INPUT_OPTION) || !cmdline.hasOption(OUTPUT_FILE_OPTION)) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp(this.getClass().getName(), options); ToolRunner.printGenericCommandUsage(System.out); return -1; } String language = null; if (cmdline.hasOption(LANGUAGE_OPTION)) { language = cmdline.getOptionValue(LANGUAGE_OPTION); if (language.length() != 2) { System.err.println("Error: \"" + language + "\" unknown language!"); return -1; } } String inputPath = cmdline.getOptionValue(INPUT_OPTION); String outputFile = cmdline.getOptionValue(OUTPUT_FILE_OPTION); boolean keepAll = cmdline.hasOption(KEEP_ALL_OPTION); String tmpPath = "tmp-" + WikipediaDocnoMappingBuilder.class.getSimpleName() + "-" + RANDOM.nextInt(10000); LOG.info("Tool name: " + this.getClass().getName()); LOG.info(" - input: " + inputPath); LOG.info(" - output file: " + outputFile); LOG.info(" - keep all pages: " + keepAll); LOG.info(" - language: " + language); // Job job = Job.getInstance(getConf()); JobConf conf = new JobConf(WikipediaDocnoMappingBuilder.class); conf.setJarByClass(WikipediaDocnoMappingBuilder.class); conf.setJobName(String.format("BuildWikipediaDocnoMapping[%s: %s, %s: %s, %s: %s]", INPUT_OPTION, inputPath, OUTPUT_FILE_OPTION, outputFile, LANGUAGE_OPTION, language)); conf.setBoolean(KEEP_ALL_OPTION, keepAll); // .getConfiguration().setBoolean(KEEP_ALL_OPTION, keepAll); if (language != null) { conf.set("wiki.language", language); } conf.setNumReduceTasks(1); FileInputFormat.addInputPath(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(tmpPath)); FileOutputFormat.setCompressOutput(conf, false); conf.setOutputKeyClass(IntWritable.class); conf.setOutputValueClass(IntWritable.class); conf.setInputFormat(WikipediaPageInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); conf.setMapperClass(MyMapper.class); conf.setReducerClass(MyReducer.class); // Delete the output directory if it exists already. FileSystem.get(getConf()).delete(new Path(tmpPath), true); // job.waitForCompletion(true); RunningJob job = JobClient.runJob(conf); job.waitForCompletion(); // JobClient jobClient = new JobClient(conf); long cnt = keepAll ? job.getCounters().findCounter(PageTypes.TOTAL).getValue() : job.getCounters().findCounter(PageTypes.ARTICLE).getValue(); WikipediaDocnoMapping.writeDocnoMappingData(FileSystem.get(getConf()), tmpPath + "/part-00000", (int) cnt, outputFile); FileSystem.get(getConf()).delete(new Path(tmpPath), true); return 0; }
From source file:HoopRemoteTask.java
License:Open Source License
/** * *///from w ww. ja v a 2 s .com public static void main(String args[]) throws Exception { // run the HoopLink constructor; We need this to have a global settings registry @SuppressWarnings("unused") HoopLink link = new HoopLink(); dbg("main ()"); showTimeStamp(); /** * I've taken out the statistics portion since it relies on code that isn't distributed * The next version will have this solved. I might try the solution in: * http://stackoverflow.com/questions/7443074/initialize-public-static-variable-in-hadoop-through-arguments * Although chances are I will switch to using Hoop to collect much better performance and distribution * statistics. See Hoop.java for more information */ HoopPerformanceMeasure metrics = new HoopPerformanceMeasure(); metrics.setMarker("main"); HoopLink.metrics.getDataSet().add(metrics); if (parseArgs(args) == false) { usage(); return; } if (HoopLink.postonly == true) { postOnly(); return; } if (HoopLink.task.equals("none") == true) { dbg("No task defined, please use the commandline option -task <task>"); return; } dbg("Starting system ..."); HoopRemoteTask driver = new HoopRemoteTask(); if (HoopLink.useHadoop == false) { dbg("Starting built-in mapper ..."); driver.indexDocuments(); } else { dbg("Starting hadoop job ..."); Configuration conf = new Configuration(); // TRANSFER SETTHoopGS FROM HoopLink to Configuration!!! transferConf(conf); // Now we're feeling much better HoopRemoteTask.hdfs = FileSystem.get(conf); if (HoopLink.dbglocal == true) { dbg("Enabling local debugging ..."); conf.set("mapred.job.tracker", "local"); } else dbg("Disabling local debugging"); JobConf job = new JobConf(conf, HoopRemoteTask.class); job.setJobName(driver.getClassName()); driver.setJob(job); @SuppressWarnings("unused") String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); job.setJarByClass(HoopRemoteTask.class); if (HoopLink.task.equals("invert") == true) { dbg("Configuring job for invert task ..."); job.setReducerClass(HoopInvertedListReducer.class); job.setMapperClass(HoopInvertedListMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); } if (HoopLink.task.equals("wordcount") == true) { dbg("Configuring job for wordcount task ..."); job.setReducerClass(HoopWordCountReducer.class); job.setMapperClass(HoopWordCountMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); } dbg("Using input path: " + HoopLink.datapath); dbg("Using output path: " + HoopLink.outputpath); FileInputFormat.addInputPath(job, new Path(HoopLink.datapath)); FileOutputFormat.setOutputPath(job, new Path(HoopLink.outputpath)); job.setInputFormat(HoopWholeFileInputFormat.class); if ((HoopLink.shardcreate.equals("mos") == true) && (HoopLink.nrshards > 1)) { dbg("Setting output to sharded output streams class ..."); job.setOutputFormat(HoopShardedOutputFormat.class); } else job.setOutputFormat(TextOutputFormat.class); /** * Temporarily commented out for testing purposes */ //job.setPartitionerClass (HoopPartitioner.class); driver.register("Main"); JobClient.runJob(job); postProcess(conf); } showTimeStamp(); metrics.closeMarker(); long timeTaken = metrics.getYValue(); //long timeTaken=metrics.getMarkerRaw (); metrics.printMetrics(timeTaken); driver.unregister(); /** * I've taken out the statistics portion since it relies on code that isn't distributed * The next version will have this solved. I might try the solution in: * http://stackoverflow.com/questions/7443074/initialize-public-static-variable-in-hadoop-through-arguments * Although chances are I will switch to using Hoop to collect much better performance and distribution * statistics. See Hoop.java for more information */ //stats.calcStatistics(); //dbg (stats.printStatistics()); }
From source file:RepackWikipedia.java
License:Apache License
@SuppressWarnings("static-access") @Override//from w w w . jav a2 s .co m public int run(String[] args) throws Exception { Options options = new Options(); options.addOption( OptionBuilder.withArgName("path").hasArg().withDescription("XML dump file").create(INPUT_OPTION)); options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output location") .create(OUTPUT_OPTION)); options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("mapping file") .create(MAPPING_FILE_OPTION)); options.addOption(OptionBuilder.withArgName("block|record|none").hasArg() .withDescription("compression type").create(COMPRESSION_TYPE_OPTION)); options.addOption(OptionBuilder.withArgName("en|sv|de").hasArg().withDescription("two-letter language code") .create(LANGUAGE_OPTION)); CommandLine cmdline; CommandLineParser parser = new GnuParser(); try { cmdline = parser.parse(options, args); } catch (ParseException exp) { System.err.println("Error parsing command line: " + exp.getMessage()); return -1; } if (!cmdline.hasOption(INPUT_OPTION) || !cmdline.hasOption(OUTPUT_OPTION) || !cmdline.hasOption(MAPPING_FILE_OPTION) || !cmdline.hasOption(COMPRESSION_TYPE_OPTION)) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp(this.getClass().getName(), options); ToolRunner.printGenericCommandUsage(System.out); return -1; } String inputPath = cmdline.getOptionValue(INPUT_OPTION); String outputPath = cmdline.getOptionValue(OUTPUT_OPTION); String mappingFile = cmdline.getOptionValue(MAPPING_FILE_OPTION); String compressionType = cmdline.getOptionValue(COMPRESSION_TYPE_OPTION); if (!"block".equals(compressionType) && !"record".equals(compressionType) && !"none".equals(compressionType)) { System.err.println("Error: \"" + compressionType + "\" unknown compression type!"); return -1; } String language = null; if (cmdline.hasOption(LANGUAGE_OPTION)) { language = cmdline.getOptionValue(LANGUAGE_OPTION); if (language.length() != 2) { System.err.println("Error: \"" + language + "\" unknown language!"); return -1; } } // this is the default block size int blocksize = 1000000; //Job job = Job.getInstance(getConf()); JobConf conf = new JobConf(RepackWikipedia.class); conf.setJarByClass(RepackWikipedia.class); conf.setJobName(String.format("RepackWikipedia[%s: %s, %s: %s, %s: %s, %s: %s]", INPUT_OPTION, inputPath, OUTPUT_OPTION, outputPath, COMPRESSION_TYPE_OPTION, compressionType, LANGUAGE_OPTION, language)); conf.set(DOCNO_MAPPING_FIELD, mappingFile); LOG.info("Tool name: " + this.getClass().getName()); LOG.info(" - XML dump file: " + inputPath); LOG.info(" - output path: " + outputPath); LOG.info(" - docno mapping data file: " + mappingFile); LOG.info(" - compression type: " + compressionType); LOG.info(" - language: " + language); if ("block".equals(compressionType)) { LOG.info(" - block size: " + blocksize); } conf.setNumReduceTasks(0); FileInputFormat.addInputPath(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); if ("none".equals(compressionType)) { FileOutputFormat.setCompressOutput(conf, false); } else { FileOutputFormat.setCompressOutput(conf, true); if ("record".equals(compressionType)) { SequenceFileOutputFormat.setOutputCompressionType(conf, SequenceFile.CompressionType.RECORD); } else { SequenceFileOutputFormat.setOutputCompressionType(conf, SequenceFile.CompressionType.BLOCK); conf.setInt("io.seqfile.compress.blocksize", blocksize); } } if (language != null) { conf.set("wiki.language", language); } conf.setInputFormat(WikipediaPageInputFormat.class); conf.setOutputFormat(SequenceFileOutputFormat.class); conf.setOutputKeyClass(IntWritable.class); conf.setOutputValueClass(WikipediaPage.class); conf.setMapperClass(MyMapper.class); // Delete the output directory if it exists already. FileSystem.get(getConf()).delete(new Path(outputPath), true); //job.waitForCompletion(true); JobClient.runJob(conf); return 0; }
From source file:azkaban.jobtype.examples.java.WordCount.java
License:Apache License
public void run() throws Exception { logger.info(String.format("Starting %s", getClass().getSimpleName())); // hadoop conf should be on the classpath JobConf jobconf = getJobConf(); jobconf.setJarByClass(WordCount.class); jobconf.setOutputKeyClass(Text.class); jobconf.setOutputValueClass(IntWritable.class); jobconf.setMapperClass(Map.class); jobconf.setReducerClass(Reduce.class); jobconf.setInputFormat(TextInputFormat.class); jobconf.setOutputFormat(TextOutputFormat.class); FileInputFormat.addInputPath(jobconf, new Path(inputPath)); FileOutputFormat.setOutputPath(jobconf, new Path(outputPath)); if (forceOutputOverrite) { FileSystem fs = FileOutputFormat.getOutputPath(jobconf).getFileSystem(jobconf); fs.delete(FileOutputFormat.getOutputPath(jobconf), true); }/*from w ww.j a va 2 s . c om*/ super.run(); }
From source file:br.eti.kinoshita.hadoop.WordCount.java
License:Open Source License
public static void main(String[] args) throws Exception { JobConf conf = new JobConf(WordCount.class); conf.setJarByClass(WordCount.class); conf.setJobName("wordcount"); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(IntWritable.class); conf.setMapperClass(Map.class); conf.setCombinerClass(Reduce.class); conf.setReducerClass(Reduce.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); //FileInputFormat.setInputPaths(conf, new Path("hdfs://chuva:9000/test/leiseca.")); FileInputFormat.setInputPaths(conf, new Path(args[0])); FileOutputFormat.setOutputPath(conf, new Path(args[1])); JobClient.runJob(conf);/*from ww w .j a v a 2s . com*/ }
From source file:cn.edu.hfut.dmic.webcollectorcluster.fetcher.Fetcher.java
@Override public int run(String[] args) throws Exception { JobConf jc = new JobConf(getConf()); jc.setJarByClass(Fetcher.class); jc.setInputFormat(SequenceFileInputFormat.class); Path input = new Path(args[0], "current"); Path output = new Path(args[1]); Configuration conf = CrawlerConfiguration.create(); FileSystem fs = output.getFileSystem(conf); if (fs.exists(output)) { fs.delete(output);//from w ww . j a va2 s. c o m } FileInputFormat.addInputPath(jc, input); FileOutputFormat.setOutputPath(jc, output); jc.setMapOutputKeyClass(Text.class); jc.setMapOutputValueClass(WebWritable.class); jc.setMapRunnerClass(Fetcher.class); jc.setOutputFormat(FetcherOutputFormat.class); JobClient.runJob(jc); return 0; }
From source file:co.nubetech.hiho.job.DBQueryInputJob.java
License:Apache License
public void runJobs(Configuration conf, int jobCounter) throws IOException { try {//from w ww . jav a 2 s . c o m checkMandatoryConfs(conf); } catch (HIHOException e1) { e1.printStackTrace(); throw new IOException(e1); } Job job = new Job(conf); for (Entry<String, String> entry : conf) { logger.warn("key, value " + entry.getKey() + "=" + entry.getValue()); } // logger.debug("Number of maps " + // conf.getInt("mapred.map.tasks", 1)); // conf.setInt(JobContext.NUM_MAPS, // conf.getInt("mapreduce.job.maps", 1)); // job.getConfiguration().setInt("mapred.map.tasks", 4); job.getConfiguration().setInt(MRJobConfig.NUM_MAPS, conf.getInt(HIHOConf.NUMBER_MAPPERS, 1)); logger.warn("Number of maps " + conf.getInt(MRJobConfig.NUM_MAPS, 1)); job.setJobName("Import job"); job.setJarByClass(DBQueryInputJob.class); String strategy = conf.get(HIHOConf.INPUT_OUTPUT_STRATEGY); OutputStrategyEnum os = OutputStrategyEnum.value(strategy); if (os == null) { throw new IllegalArgumentException("Wrong value of output strategy. Please correct"); } if (os != OutputStrategyEnum.AVRO) { switch (os) { case DUMP: { // job.setMapperClass(DBImportMapper.class); break; } /* * case AVRO: { job.setMapperClass(DBInputAvroMapper.class); // * need avro in cp // job.setJarByClass(Schema.class); // need * jackson which is needed by avro - ugly! // * job.setJarByClass(ObjectMapper.class); * job.setMapOutputKeyClass(NullWritable.class); * job.setMapOutputValueClass(AvroValue.class); * job.setOutputKeyClass(NullWritable.class); * job.setOutputValueClass(AvroValue.class); * job.setOutputFormatClass(AvroOutputFormat.class); * * AvroOutputFormat.setOutputPath(job, new * Path(getConf().get(HIHOConf.INPUT_OUTPUT_PATH))); break; } */ case DELIMITED: { job.setMapperClass(DBInputDelimMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setOutputFormatClass(NoKeyOnlyValueOutputFormat.class); NoKeyOnlyValueOutputFormat.setOutputPath(job, new Path(getConf().get(HIHOConf.INPUT_OUTPUT_PATH))); } case JSON: { // job.setMapperClass(DBImportJsonMapper.class); // job.setJarByClass(ObjectMapper.class); break; } default: { job.setMapperClass(DBInputDelimMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setOutputFormatClass(NoKeyOnlyValueOutputFormat.class); NoKeyOnlyValueOutputFormat.setOutputPath(job, new Path(getConf().get(HIHOConf.INPUT_OUTPUT_PATH))); break; } } String inputQuery = conf.get(DBConfiguration.INPUT_QUERY); String inputBoundingQuery = conf.get(DBConfiguration.INPUT_BOUNDING_QUERY); logger.debug("About to set the params"); DBQueryInputFormat.setInput(job, inputQuery, inputBoundingQuery, params); logger.debug("Set the params"); job.setNumReduceTasks(0); try { // job.setJarByClass(Class.forName(conf.get( // org.apache.hadoop.mapred.lib.db.DBConfiguration.DRIVER_CLASS_PROPERTY))); logger.debug("OUTPUT format class is " + job.getOutputFormatClass()); /* * org.apache.hadoop.mapreduce.OutputFormat<?, ?> output = * ReflectionUtils.newInstance(job.getOutputFormatClass(), * job.getConfiguration()); output.checkOutputSpecs(job); */ logger.debug("Class is " + ReflectionUtils .newInstance(job.getOutputFormatClass(), job.getConfiguration()).getClass().getName()); job.waitForCompletion(false); if (conf.get(HIHOConf.INPUT_OUTPUT_LOADTO) != null) { generateHiveScript(conf, job, jobCounter); generatePigScript(conf, job); } } /* * catch (HIHOException h) { h.printStackTrace(); } */ catch (Exception e) { e.printStackTrace(); } catch (HIHOException e) { e.printStackTrace(); } } // avro to be handled differently, thanks to all the incompatibilities // in the apis. else { String inputQuery = conf.get(DBConfiguration.INPUT_QUERY); String inputBoundingQuery = conf.get(DBConfiguration.INPUT_BOUNDING_QUERY); logger.debug("About to set the params"); // co.nubetech.apache.hadoop.mapred.DBQueryInputFormat.setInput(job, // inputQuery, inputBoundingQuery, params); logger.debug("Set the params"); JobConf jobConf = new JobConf(conf); try { GenericDBWritable queryWritable = getDBWritable(jobConf); Schema pair = DBMapper.getPairSchema(queryWritable.getColumns()); AvroJob.setMapOutputSchema(jobConf, pair); GenericRecordAvroOutputFormat.setOutputPath(jobConf, new Path(getConf().get(HIHOConf.INPUT_OUTPUT_PATH))); co.nubetech.apache.hadoop.mapred.DBQueryInputFormat.setInput(jobConf, inputQuery, inputBoundingQuery, params); jobConf.setInputFormat(co.nubetech.apache.hadoop.mapred.DBQueryInputFormat.class); jobConf.setMapperClass(DBInputAvroMapper.class); jobConf.setMapOutputKeyClass(NullWritable.class); jobConf.setMapOutputValueClass(AvroValue.class); jobConf.setOutputKeyClass(NullWritable.class); jobConf.setOutputValueClass(Text.class); jobConf.setOutputFormat(GenericRecordAvroOutputFormat.class); jobConf.setJarByClass(DBQueryInputJob.class); jobConf.setStrings("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization,org.apache.hadoop.io.serializer.WritableSerialization,org.apache.avro.mapred.AvroSerialization"); jobConf.setNumReduceTasks(0); /* * jobConf.setOutputFormat(org.apache.hadoop.mapred. * SequenceFileOutputFormat.class); * org.apache.hadoop.mapred.SequenceFileOutputFormat * .setOutputPath(jobConf, new * Path(getConf().get(HIHOConf.INPUT_OUTPUT_PATH))); */ JobClient.runJob(jobConf); } catch (Throwable e) { e.printStackTrace(); } } }
From source file:com.acme.extensions.mr.WordCount.java
License:Apache License
public static void main(String[] args) throws Exception { JobConf job = new JobConf(); String[] otherArgs = new GenericOptionsParser(job, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: wordcount <in> <out>"); System.exit(2);//from w w w .j a va 2s.c o m } 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])); JobClient.runJob(job); }