List of usage examples for org.apache.hadoop.mapred JobConf setInt
public void setInt(String name, int value)
name property to an int. 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 w w w .jav a2 s . co 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;/*w w w . j a va 2 s . 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:SleepJob.java
License:Apache License
public JobConf setupJobConf(int numMapper, int numReducer, long mapSleepTime, int mapSleepCount, long reduceSleepTime, int reduceSleepCount) { JobConf job = new JobConf(getConf(), SleepJob.class); job.setNumMapTasks(numMapper);//www .j a v a 2 s.co m job.setNumReduceTasks(numReducer); job.setMapperClass(SleepJob.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(NullWritable.class); job.setReducerClass(SleepJob.class); job.setOutputFormat(NullOutputFormat.class); job.setInputFormat(SleepInputFormat.class); job.setPartitionerClass(SleepJob.class); job.setSpeculativeExecution(false); FileInputFormat.addInputPath(job, new Path("ignored")); job.setLong("sleep.job.map.sleep.time", mapSleepTime); job.setLong("sleep.job.reduce.sleep.time", reduceSleepTime); job.setInt("sleep.job.map.sleep.count", mapSleepCount); job.setInt("sleep.job.reduce.sleep.count", reduceSleepCount); return job; }
From source file:NaivePageRank.java
License:Apache License
public static void main(String[] args) throws Exception { int iteration = -1; String inputPath = args[0];/*from w w w. j av a 2 s . co m*/ String outputPath = args[1]; int specIteration = 0; if (args.length > 2) { specIteration = Integer.parseInt(args[2]); } int numNodes = 100000; if (args.length > 3) { numNodes = Integer.parseInt(args[3]); } int numReducers = 32; if (args.length > 4) { numReducers = Integer.parseInt(args[4]); } System.out.println("specified iteration: " + specIteration); long start = System.currentTimeMillis(); /** * job to count out-going links for each url */ JobConf conf = new JobConf(NaivePageRank.class); conf.setJobName("PageRank-Count"); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); conf.setMapperClass(CountMapper.class); conf.setReducerClass(CountReducer.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); FileInputFormat.setInputPaths(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath + "/count")); conf.setNumReduceTasks(numReducers); JobClient.runJob(conf); /******************** Initial Rank Assignment Job ***********************/ conf = new JobConf(NaivePageRank.class); conf.setJobName("PageRank-Initialize"); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); conf.setMapperClass(InitialRankAssignmentMapper.class); conf.setReducerClass(InitialRankAssignmentReducer.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); FileInputFormat.setInputPaths(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath + "/i" + iteration)); conf.setNumReduceTasks(numReducers); // conf.setIterative(false); JobClient.runJob(conf); iteration++; do { /****************** Join Job ********************************/ conf = new JobConf(NaivePageRank.class); conf.setJobName("PageRank-Join"); conf.setOutputKeyClass(Text.class); // conf.setOutputValueClass(Text.class); conf.setMapperClass(ComputeRankMap.class); conf.setReducerClass(ComputeRankReduce.class); conf.setMapOutputKeyClass(TextPair.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); conf.setPartitionerClass(FirstPartitioner.class); conf.setOutputKeyComparatorClass(KeyComparator.class); conf.setOutputValueGroupingComparator(GroupComparator.class); // relation table FileInputFormat.setInputPaths(conf, new Path(inputPath)); // rank table FileInputFormat.addInputPath(conf, new Path(outputPath + "/i" + (iteration - 1))); // count table FileInputFormat.addInputPath(conf, new Path(outputPath + "/count")); FileOutputFormat.setOutputPath(conf, new Path(outputPath + "/i" + iteration)); conf.setNumReduceTasks(numReducers); JobClient.runJob(conf); iteration++; /******************** Rank Aggregate Job ***********************/ conf = new JobConf(NaivePageRank.class); conf.setJobName("PageRank-Aggregate"); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); conf.setMapOutputKeyClass(Text.class); conf.setMapperClass(RankAggregateMapper.class); conf.setReducerClass(RankAggregateReducer.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); FileInputFormat.setInputPaths(conf, new Path(outputPath + "/i" + (iteration - 1))); FileOutputFormat.setOutputPath(conf, new Path(outputPath + "/i" + iteration)); conf.setNumReduceTasks(numReducers); conf.setInt("haloop.num.nodes", numNodes); JobClient.runJob(conf); iteration++; } while (iteration < 2 * specIteration); long end = System.currentTimeMillis(); System.out.println("running time " + (end - start) / 1000 + "s"); }
From source file:RepackWikipedia.java
License:Apache License
@SuppressWarnings("static-access") @Override//from w w w . j av a2 s. com 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:SleepJobWithArray.java
License:Apache License
public JobConf setupJobConf(int numMapper, int numReducer, long mapSleepTime, int mapSleepCount, long reduceSleepTime, int reduceSleepCount) { JobConf job = new JobConf(getConf(), SleepJobWithArray.class); job.setNumMapTasks(numMapper);//from w w w .j av a2s .com job.setNumReduceTasks(numReducer); job.setMapperClass(SleepJobWithArray.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(NullWritable.class); job.setReducerClass(SleepJobWithArray.class); job.setOutputFormat(NullOutputFormat.class); job.setInputFormat(SleepInputFormat.class); job.setPartitionerClass(SleepJobWithArray.class); job.setSpeculativeExecution(false); FileInputFormat.addInputPath(job, new Path("ignored")); job.setLong("sleep.job.map.sleep.time", mapSleepTime); job.setLong("sleep.job.reduce.sleep.time", reduceSleepTime); job.setInt("sleep.job.map.sleep.count", mapSleepCount); job.setInt("sleep.job.reduce.sleep.count", reduceSleepCount); return job; }
From source file:at.illecker.hadoop.rootbeer.examples.matrixmultiplication.cpu.MatrixMultiplicationCpu.java
License:Apache License
public static Configuration createMatrixMultiplicationCpuConf(Configuration initialConf, Path aPath, Path bPath, Path outPath, int outCardinality, boolean isDebugging) { JobConf conf = new JobConf(initialConf, MatrixMultiplicationCpu.class); conf.setJobName("MatrixMultiplicationCPU: " + aPath + " x " + bPath + " = " + outPath); conf.setInt(CONF_OUT_CARD, outCardinality); conf.setBoolean(CONF_DEBUG, isDebugging); conf.setInputFormat(CompositeInputFormat.class); conf.set("mapred.join.expr", CompositeInputFormat.compose("inner", SequenceFileInputFormat.class, aPath, bPath)); conf.setOutputFormat(SequenceFileOutputFormat.class); FileOutputFormat.setOutputPath(conf, outPath); conf.setMapperClass(MatrixMultiplyCpuMapper.class); conf.setCombinerClass(MatrixMultiplicationCpuReducer.class); conf.setReducerClass(MatrixMultiplicationCpuReducer.class); conf.setMapOutputKeyClass(IntWritable.class); conf.setMapOutputValueClass(VectorWritable.class); conf.setOutputKeyClass(IntWritable.class); conf.setOutputValueClass(VectorWritable.class); // Increase client heap size conf.set("mapred.child.java.opts", "-Xms8G -Xmx8G"); return conf;/*from ww w . j a va 2 s.com*/ }
From source file:at.illecker.hadoop.rootbeer.examples.matrixmultiplication.gpu.MatrixMultiplicationGpu.java
License:Apache License
public static Configuration createMatrixMultiplicationGpuConf(Configuration initialConf, Path aPath, Path bPath, Path outPath, int outCardinality, int tileWidth, boolean isDebugging) { JobConf conf = new JobConf(initialConf, MatrixMultiplicationGpu.class); conf.setJobName("MatrixMultiplicationGPU: " + aPath + " x " + bPath + " = " + outPath); conf.setInt(CONF_OUT_CARD, outCardinality); conf.setInt(CONF_TILE_WIDTH, tileWidth); conf.setBoolean(CONF_DEBUG, isDebugging); conf.setInputFormat(CompositeInputFormat.class); conf.set("mapred.join.expr", CompositeInputFormat.compose("inner", SequenceFileInputFormat.class, aPath, bPath)); conf.setOutputFormat(SequenceFileOutputFormat.class); FileOutputFormat.setOutputPath(conf, outPath); conf.setMapperClass(MatrixMultiplyGpuMapper.class); conf.setMapOutputKeyClass(IntWritable.class); conf.setMapOutputValueClass(VectorWritable.class); conf.setOutputKeyClass(IntWritable.class); conf.setOutputValueClass(VectorWritable.class); // Increase client heap size for GPU Rootbeer execution conf.set("mapred.child.java.opts", "-Xms8G -Xmx8G"); // No Reduce step is needed // -> 0 reducer means reduce step will be skipped and // mapper output will be the final out // -> Identity reducer means then shuffling/sorting will still take place conf.setNumReduceTasks(0);/*from ww w .j a v a2 s . c o m*/ return conf; }
From source file:bixo.examples.webmining.DemoWebMiningWorkflow.java
License:Apache License
public static Flow createWebMiningWorkflow(Path crawlDbPath, Path curLoopDirPath, FetcherPolicy fetcherPolicy, UserAgent userAgent, DemoWebMiningOptions options) throws IOException, InterruptedException { // Fetch at most 200 pages, max size of 128K, complete mode, from the current dir. // HTML only. // We want to extract the cleaned up HTML, and pass that to the parser, which will // be specified via options.getAnalyzer. From this we'll get outlinks, page score, and // any results. JobConf conf = HadoopUtils.getDefaultJobConf(CrawlConfig.CRAWL_STACKSIZE_KB); boolean isLocal = HadoopUtils.isJobLocal(conf); int numReducers = HadoopUtils.getNumReducers(conf); conf.setNumReduceTasks(numReducers); conf.setInt("mapred.min.split.size", 64 * 1024 * 1024); Properties props = HadoopUtils.getDefaultProperties(DemoWebMiningWorkflow.class, false, conf); FileSystem fs = crawlDbPath.getFileSystem(conf); // Input : the crawldb if (!fs.exists(crawlDbPath)) { throw new RuntimeException("CrawlDb not found"); }//from w w w . j a v a2 s . c o m Tap inputSource = new Hfs(new TextDelimited(CrawlDbDatum.FIELDS, "\t", CrawlDbDatum.TYPES), crawlDbPath.toString()); Pipe importPipe = new Pipe("import pipe"); // Split into tuples that are to be fetched and that have already been fetched SplitterAssembly splitter = new SplitterAssembly(importPipe, new SplitFetchedUnfetchedSSCrawlDatums()); Pipe finishedDatumsFromDb = new Pipe("finished datums from db", splitter.getRHSPipe()); Pipe urlsToFetchPipe = splitter.getLHSPipe(); // Limit to MAX_DISTRIBUTED_FETCH if running in real cluster, // or MAX_LOCAL_FETCH if running locally. So first we sort the entries // from high to low by links score. // TODO add unit test urlsToFetchPipe = new GroupBy(urlsToFetchPipe, new Fields(CrawlDbDatum.LINKS_SCORE_FIELD), true); long maxToFetch = HadoopUtils.isJobLocal(conf) ? MAX_LOCAL_FETCH : MAX_DISTRIBUTED_FETCH; urlsToFetchPipe = new Each(urlsToFetchPipe, new CreateUrlDatumFromCrawlDbDatum(maxToFetch)); BaseScoreGenerator scorer = new LinkScoreGenerator(); // Create the sub-assembly that runs the fetch job int maxThreads = isLocal ? CrawlConfig.DEFAULT_NUM_THREADS_LOCAL : CrawlConfig.DEFAULT_NUM_THREADS_CLUSTER; SimpleHttpFetcher fetcher = new SimpleHttpFetcher(maxThreads, fetcherPolicy, userAgent); fetcher.setMaxRetryCount(CrawlConfig.MAX_RETRIES); fetcher.setSocketTimeout(CrawlConfig.SOCKET_TIMEOUT); fetcher.setConnectionTimeout(CrawlConfig.CONNECTION_TIMEOUT); FetchPipe fetchPipe = new FetchPipe(urlsToFetchPipe, scorer, fetcher, numReducers); Pipe statusPipe = new Pipe("status pipe", fetchPipe.getStatusTailPipe()); Pipe contentPipe = new Pipe("content pipe", fetchPipe.getContentTailPipe()); contentPipe = TupleLogger.makePipe(contentPipe, true); // Create a parser that returns back the raw HTML (cleaned up by Tika) as the parsed content. SimpleParser parser = new SimpleParser(new ParserPolicy(), true); ParsePipe parsePipe = new ParsePipe(fetchPipe.getContentTailPipe(), parser); Pipe analyzerPipe = new Pipe("analyzer pipe"); analyzerPipe = new Each(parsePipe.getTailPipe(), new AnalyzeHtml()); Pipe outlinksPipe = new Pipe("outlinks pipe", analyzerPipe); outlinksPipe = new Each(outlinksPipe, new CreateLinkDatumFromOutlinksFunction()); Pipe resultsPipe = new Pipe("results pipe", analyzerPipe); resultsPipe = new Each(resultsPipe, new CreateResultsFunction()); // Group the finished datums, the skipped datums, status, outlinks Pipe updatePipe = new CoGroup("update pipe", Pipe.pipes(finishedDatumsFromDb, statusPipe, analyzerPipe, outlinksPipe), Fields.fields(new Fields(CrawlDbDatum.URL_FIELD), new Fields(StatusDatum.URL_FN), new Fields(AnalyzedDatum.URL_FIELD), new Fields(LinkDatum.URL_FN)), null, new OuterJoin()); updatePipe = new Every(updatePipe, new UpdateCrawlDbBuffer(), Fields.RESULTS); // output : loop dir specific crawldb Path outCrawlDbPath = new Path(curLoopDirPath, CrawlConfig.CRAWLDB_SUBDIR_NAME); Tap crawlDbSink = new Hfs(new TextLine(), outCrawlDbPath.toString()); // Status, Path statusDirPath = new Path(curLoopDirPath, CrawlConfig.STATUS_SUBDIR_NAME); Tap statusSink = new Hfs(new TextLine(), statusDirPath.toString()); // Content Path contentDirPath = new Path(curLoopDirPath, CrawlConfig.CONTENT_SUBDIR_NAME); Tap contentSink = new Hfs(new SequenceFile(FetchedDatum.FIELDS), contentDirPath.toString()); // PageResults Path resultsDirPath = new Path(curLoopDirPath, CrawlConfig.RESULTS_SUBDIR_NAME); Tap resultsSink = new Hfs(new TextLine(), resultsDirPath.toString()); // Create the output map that connects each tail pipe to the appropriate sink. Map<String, Tap> sinkMap = new HashMap<String, Tap>(); sinkMap.put(updatePipe.getName(), crawlDbSink); sinkMap.put(statusPipe.getName(), statusSink); sinkMap.put(contentPipe.getName(), contentSink); sinkMap.put(resultsPipe.getName(), resultsSink); FlowConnector flowConnector = new FlowConnector(props); Flow flow = flowConnector.connect(inputSource, sinkMap, updatePipe, statusPipe, contentPipe, resultsPipe); return flow; }
From source file:bixo.examples.webmining.WebMiningWorkflow.java
License:Apache License
public static Flow createWebMiningWorkflow(Path crawlDbPath, Path curLoopDirPath, FetcherPolicy fetcherPolicy, UserAgent userAgent, WebMiningOptions options, boolean resetSolr) throws IOException, InterruptedException { // Fetch at most 200 pages, max size of 128K, complete mode, from the current dir. // HTML only. // We want to extract the cleaned up HTML, and pass that to the parser, which will // be specified via options.getAnalyzer. From this we'll get outlinks, page score, and // any results. JobConf conf = HadoopUtils.getDefaultJobConf(CrawlConfig.CRAWL_STACKSIZE_KB); boolean isLocal = HadoopUtils.isJobLocal(conf); int numReducers = 1; // we always want to use a single reducer, to avoid contention conf.setNumReduceTasks(numReducers); conf.setInt("mapred.min.split.size", 64 * 1024 * 1024); Properties props = HadoopUtils.getDefaultProperties(WebMiningWorkflow.class, false, conf); FileSystem fs = crawlDbPath.getFileSystem(conf); // Input : the crawldb if (!fs.exists(crawlDbPath)) { throw new RuntimeException("CrawlDb not found"); }/*from w w w . j a v a 2s.c om*/ Tap inputSource = new Hfs(new TextDelimited(CrawlDbDatum.FIELDS, "\t", CrawlDbDatum.TYPES), crawlDbPath.toString()); Pipe importPipe = new Pipe("import pipe"); // Split into tuples that are to be fetched and that have already been fetched SplitterAssembly splitter = new SplitterAssembly(importPipe, new SplitFetchedUnfetchedSSCrawlDatums()); Pipe finishedDatumsFromDb = new Pipe("finished datums from db", splitter.getRHSPipe()); Pipe urlsToFetchPipe = splitter.getLHSPipe(); // Limit to MAX_DISTRIBUTED_FETCH if running in real cluster, // or MAX_LOCAL_FETCH if running locally. So first we sort the entries // from high to low by links score. // TODO add unit test urlsToFetchPipe = new GroupBy(urlsToFetchPipe, new Fields(CrawlDbDatum.LINKS_SCORE_FIELD), true); long maxToFetch = HadoopUtils.isJobLocal(conf) ? MAX_LOCAL_FETCH : MAX_DISTRIBUTED_FETCH; urlsToFetchPipe = new Each(urlsToFetchPipe, new CreateUrlDatumFromCrawlDbDatum(maxToFetch)); BaseScoreGenerator scorer = new LinkScoreGenerator(); // Create the sub-assembly that runs the fetch job int maxThreads = isLocal ? CrawlConfig.DEFAULT_NUM_THREADS_LOCAL : CrawlConfig.DEFAULT_NUM_THREADS_CLUSTER; SimpleHttpFetcher fetcher = new SimpleHttpFetcher(maxThreads, fetcherPolicy, userAgent); fetcher.setMaxRetryCount(CrawlConfig.MAX_RETRIES); fetcher.setSocketTimeout(CrawlConfig.SOCKET_TIMEOUT); fetcher.setConnectionTimeout(CrawlConfig.CONNECTION_TIMEOUT); FetchPipe fetchPipe = new FetchPipe(urlsToFetchPipe, scorer, fetcher, numReducers); Pipe statusPipe = new Pipe("status pipe", fetchPipe.getStatusTailPipe()); Pipe contentPipe = new Pipe("content pipe", fetchPipe.getContentTailPipe()); contentPipe = TupleLogger.makePipe(contentPipe, true); // Create a parser that returns back the raw HTML (cleaned up by Tika) as the parsed content. SimpleParser parser = new SimpleParser(new ParserPolicy(), true); ParsePipe parsePipe = new ParsePipe(fetchPipe.getContentTailPipe(), parser); Pipe analyzerPipe = new Pipe("analyzer pipe"); analyzerPipe = new Each(parsePipe.getTailPipe(), new AnalyzeHtml()); Pipe outlinksPipe = new Pipe("outlinks pipe", analyzerPipe); outlinksPipe = new Each(outlinksPipe, new CreateLinkDatumFromOutlinksFunction()); Pipe resultsPipe = new Pipe("results pipe", analyzerPipe); resultsPipe = new Each(resultsPipe, new CreateResultsFunction()); // Group the finished datums, the skipped datums, status, outlinks Pipe updatePipe = new CoGroup("update pipe", Pipe.pipes(finishedDatumsFromDb, statusPipe, analyzerPipe, outlinksPipe), Fields.fields(new Fields(CrawlDbDatum.URL_FIELD), new Fields(StatusDatum.URL_FN), new Fields(AnalyzedDatum.URL_FIELD), new Fields(LinkDatum.URL_FN)), null, new OuterJoin()); updatePipe = new Every(updatePipe, new UpdateCrawlDbBuffer(), Fields.RESULTS); // output : loop dir specific crawldb Path outCrawlDbPath = new Path(curLoopDirPath, CrawlConfig.CRAWLDB_SUBDIR_NAME); Tap crawlDbSink = new Hfs(new TextLine(), outCrawlDbPath.toString()); // Status, Path statusDirPath = new Path(curLoopDirPath, CrawlConfig.STATUS_SUBDIR_NAME); Tap statusSink = new Hfs(new TextLine(), statusDirPath.toString()); // Content Path contentDirPath = new Path(curLoopDirPath, CrawlConfig.CONTENT_SUBDIR_NAME); Tap contentSink = new Hfs(new SequenceFile(FetchedDatum.FIELDS), contentDirPath.toString()); // PageResults Path resultsDirPath = new Path(curLoopDirPath, CrawlConfig.RESULTS_SUBDIR_NAME); Tap resultsSink = new Hfs(new TextLine(), resultsDirPath.toString()); // Create the output map that connects each tail pipe to the appropriate sink. Map<String, Tap> sinkMap = new HashMap<String, Tap>(); sinkMap.put(updatePipe.getName(), crawlDbSink); sinkMap.put(statusPipe.getName(), statusSink); sinkMap.put(contentPipe.getName(), contentSink); sinkMap.put(resultsPipe.getName(), resultsSink); FlowConnector flowConnector = new FlowConnector(props); Flow flow = flowConnector.connect(inputSource, sinkMap, updatePipe, statusPipe, contentPipe, resultsPipe); return flow; }