List of usage examples for org.apache.hadoop.fs Path getFileSystem
public FileSystem getFileSystem(Configuration conf) throws IOException
From source file:PageInputFormat.java
License:Apache License
public InputSplit[] getSplits(JobConf job, int num) throws IOException { long minSize = 1; long maxSize = getMaxSplitSize(job); // generate splits List<InputSplit> splits = new ArrayList<InputSplit>(); FileStatus[] files = listStatus(job); for (FileStatus file : files) { Path path = file.getPath(); long length = file.getLen(); if (length != 0) { BlockLocation[] blkLocations; FileSystem fs = path.getFileSystem(job); blkLocations = fs.getFileBlockLocations(file, 0, length); if (isSplitable(path.getFileSystem(job), path)) { long blockSize = file.getBlockSize(); long splitSize = computeSplitSize(blockSize, minSize, maxSize); long bytesRemaining = length; while (((double) bytesRemaining) / splitSize > SPLIT_SLOP) { int blkIndex = getBlockIndex(blkLocations, length - bytesRemaining); splits.add(makeSplit(path, length - bytesRemaining, splitSize, blkLocations[blkIndex].getHosts())); bytesRemaining -= splitSize; }//from www . ja v a 2 s.c o m if (bytesRemaining != 0) { int blkIndex = getBlockIndex(blkLocations, length - bytesRemaining); splits.add(makeSplit(path, length - bytesRemaining, bytesRemaining, blkLocations[blkIndex].getHosts())); } } else splits.add(makeSplit(path, 0, length, blkLocations[0].getHosts())); } else splits.add(makeSplit(path, 0, length, new String[0])); } // Save the number of input files for metrics/loadgen job.setLong(NUM_INPUT_FILES, files.length); return splits.toArray(new InputSplit[0]); }
From source file:Text2FormatStorageMR.java
License:Open Source License
@SuppressWarnings("deprecation") public static void main(String[] args) throws Exception { if (args.length != 2) { System.out.println("FormatFileMR <input> <output>"); System.exit(-1);/*from w w w.ja v a 2s . co m*/ } JobConf conf = new JobConf(FormatStorageMR.class); conf.setJobName("Text2FormatMR"); conf.setNumMapTasks(1); conf.setNumReduceTasks(4); conf.setOutputKeyClass(LongWritable.class); conf.setOutputValueClass(Unit.Record.class); conf.setMapperClass(TextFileTestMapper.class); conf.setReducerClass(FormatFileTestReducer.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(FormatStorageOutputFormat.class); conf.set("mapred.output.compress", "flase"); Head head = new Head(); initHead(head); head.toJobConf(conf); FileInputFormat.setInputPaths(conf, args[0]); Path outputPath = new Path(args[1]); FileOutputFormat.setOutputPath(conf, outputPath); FileSystem fs = outputPath.getFileSystem(conf); fs.delete(outputPath, true); JobClient jc = new JobClient(conf); RunningJob rj = null; rj = jc.submitJob(conf); String lastReport = ""; SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss,SSS"); long reportTime = System.currentTimeMillis(); long maxReportInterval = 3 * 1000; while (!rj.isComplete()) { try { Thread.sleep(1000); } catch (InterruptedException e) { } int mapProgress = Math.round(rj.mapProgress() * 100); int reduceProgress = Math.round(rj.reduceProgress() * 100); String report = " map = " + mapProgress + "%, reduce = " + reduceProgress + "%"; if (!report.equals(lastReport) || System.currentTimeMillis() >= reportTime + maxReportInterval) { String output = dateFormat.format(Calendar.getInstance().getTime()) + report; System.out.println(output); lastReport = report; reportTime = System.currentTimeMillis(); } } System.exit(0); }
From source file:HiveKeyIgnoringBAMOutputFormat.java
License:Open Source License
private void setSAMHeaderFrom(JobConf job) throws IOException { if (wrappedOutputFormat.getSAMHeader() != null) return;/*from w ww .j av a2s .c om*/ // XXX: We're not told where to take the SAM header from so we just merge // them all. There should probably be a better way of doing this. final List<SAMFileHeader> headers = new ArrayList<SAMFileHeader>(); // The "best" sort order among the headers: unsorted if they're sorted // differently, otherwise their common sort order. SAMFileHeader.SortOrder sortOrder = null; // XXX: it seems that FileInputFormat.getInputPaths(job) will point to // the directories of the input tables in the query. I'm not sure if this // is always the case. for (final Path table : FileInputFormat.getInputPaths(job)) { final FileSystem fs = table.getFileSystem(job); for (final FileStatus stat : fs.listStatus(table)) { if (!stat.isFile()) throw new IOException("Unexpected directory '" + stat.getPath() + "', expected only files"); final SAMFileReader r = new SAMFileReader(fs.open(stat.getPath())); final SAMFileHeader h = r.getFileHeader(); r.close(); headers.add(h); if (sortOrder == null) { sortOrder = h.getSortOrder(); continue; } if (sortOrder == SAMFileHeader.SortOrder.unsorted) continue; if (sortOrder != h.getSortOrder()) sortOrder = SAMFileHeader.SortOrder.unsorted; } } wrappedOutputFormat.setSAMHeader(new SamFileHeaderMerger(sortOrder, headers, true).getMergedHeader()); }
From source file:ComRoughSetApproInputSampler.java
License:Apache License
/** * Write a partition file for the given job, using the Sampler provided. * Queries the sampler for a sample keyset, sorts by the output key * comparator, selects the keys for each rank, and writes to the destination * returned from {@link TotalOrderPartitioner#getPartitionFile}. *//*from w w w .j a v a 2 s . c o m*/ @SuppressWarnings("unchecked") // getInputFormat, getOutputKeyComparator public static <K, V> void writePartitionFile(Job job, Sampler<K, V> sampler) throws IOException, ClassNotFoundException, InterruptedException { Configuration conf = job.getConfiguration(); final InputFormat inf = ReflectionUtils.newInstance(job.getInputFormatClass(), conf); int numPartitions = job.getNumReduceTasks(); K[] samples = (K[]) sampler.getSample(inf, job); LOG.info("Using " + samples.length + " samples"); RawComparator<K> comparator = (RawComparator<K>) job.getSortComparator(); Arrays.sort(samples, comparator); Path dst = new Path(TotalOrderPartitioner.getPartitionFile(conf)); FileSystem fs = dst.getFileSystem(conf); if (fs.exists(dst)) { fs.delete(dst, false); } SequenceFile.Writer writer = SequenceFile.createWriter(fs, conf, dst, job.getMapOutputKeyClass(), NullWritable.class); NullWritable nullValue = NullWritable.get(); float stepSize = samples.length / (float) numPartitions; int last = -1; for (int i = 1; i < numPartitions; ++i) { int k = Math.round(stepSize * i); while (last >= k && comparator.compare(samples[last], samples[k]) == 0) { ++k; } writer.append(samples[k], nullValue); last = k; } writer.close(); }
From source file:DeprecatedBAMRecordReader.java
License:Open Source License
public DeprecatedBAMRecordReader(InputSplit split, final JobConf job, Reporter reporter) throws IOException { if (split instanceof DeprecatedFileVirtualSplit) { rr.initialize(((DeprecatedFileVirtualSplit) split).vs, new FakeTaskAttemptContext(job)); splitLength = split.getLength(); return;/*from w w w .j a va2 s . com*/ } if (split instanceof FileSplit) { // XXX XXX // XXX XXX // XXX // XXX XXX // XXX XXX // // Hive gives us its own custom FileSplits for some reason, so we have // to do our own split alignment. (Sometimes, anyway; for "select // count(*) from table" we get FileSplits here, but for "select * from // table" our input format is used directly. Perhaps it's only because // the latter doesn't spawn a MapReduce job, so getting a FileSplit // here is the common case.) // // Since we get only one split at a time here, this is very poor: we // have to open the file for every split, even if it's the same file // every time. // // This should always work, but might be /very/ slow. I can't think of // a better way. final FileSplit fspl = (FileSplit) split; final Path path = fspl.getPath(); final long beg = fspl.getStart(); final long end = beg + fspl.getLength(); final SeekableStream sin = WrapSeekable.openPath(path.getFileSystem(job), path); final BAMSplitGuesser guesser = new BAMSplitGuesser(sin); final long alignedBeg = guesser.guessNextBAMRecordStart(beg, end); sin.close(); if (alignedBeg == end) throw new IOException("Guesser found nothing after pos " + beg); final long alignedEnd = end << 16 | 0xffff; splitLength = (alignedEnd - alignedBeg) >> 16; rr.initialize(new FileVirtualSplit(path, alignedBeg, alignedEnd, fspl.getLocations()), new FakeTaskAttemptContext(job)); return; } throw new ClassCastException("Can only handle DeprecatedFileVirtualSplit and FileSplit"); }
From source file:DupleInputFormat.java
License:Apache License
/** * Generate the list of files and make them into FileSplits. * @param job the job context//from w w w .jav a 2s .c o m * @throws IOException */ public List<InputSplit> getSplits(JobContext job) throws IOException { long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job)); long maxSize = getMaxSplitSize(job); // generate splits List<InputSplit> splits = new ArrayList<InputSplit>(); List<FileStatus> files = listStatus(job); // times that each file exists in the files List ArrayList<Integer> times = new ArrayList<Integer>(); ArrayList<Path> paths = new ArrayList<Path>(); for (FileStatus file : files) { Path path = file.getPath(); long length = file.getLen(); if (length != 0) { FileSystem fs = path.getFileSystem(job.getConfiguration()); BlockLocation[] blkLocations = fs.getFileBlockLocations(file, 0, length); int index; if ((index = paths.indexOf(path)) != -1) times.set(index, times.get(index) + 1); else { times.add(0); paths.add(path); index = times.size() - 1; } // not splitable splits.add(makeSplit(path, 0, length, blkLocations[0].getHosts(), times.get(index))); } else { //Create empty hosts array for zero length files splits.add(makeSplit(path, 0, length, new String[0])); } } // Save the number of input files for metrics/loadgen job.getConfiguration().setLong(NUM_INPUT_FILES, files.size()); //LOG.debug("Total # of splits: " + splits.size()); return splits; }
From source file:MRDriver.java
License:Apache License
public int run(String args[]) throws Exception { FileSystem fs = null;//from w w w.j a v a 2 s . com 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:Text2ColumntStorageMR.java
License:Open Source License
@SuppressWarnings("deprecation") public static void main(String[] args) throws Exception { if (args.length != 3) { System.out.println("Text2ColumnStorageMR <input> <output> <columnStorageMode>"); System.exit(-1);//from www. java2s. c o m } JobConf conf = new JobConf(Text2ColumntStorageMR.class); conf.setJobName("Text2ColumnStorageMR"); conf.setNumMapTasks(1); conf.setNumReduceTasks(4); conf.setOutputKeyClass(LongWritable.class); conf.setOutputValueClass(Unit.Record.class); conf.setMapperClass(TextFileMapper.class); conf.setReducerClass(ColumnStorageReducer.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat((Class<? extends OutputFormat>) ColumnStorageHiveOutputFormat.class); conf.set("mapred.output.compress", "flase"); Head head = new Head(); initHead(head); head.toJobConf(conf); int bt = Integer.valueOf(args[2]); FileInputFormat.setInputPaths(conf, args[0]); Path outputPath = new Path(args[1]); FileOutputFormat.setOutputPath(conf, outputPath); FileSystem fs = outputPath.getFileSystem(conf); fs.delete(outputPath, true); JobClient jc = new JobClient(conf); RunningJob rj = null; rj = jc.submitJob(conf); String lastReport = ""; SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss,SSS"); long reportTime = System.currentTimeMillis(); long maxReportInterval = 3 * 1000; while (!rj.isComplete()) { try { Thread.sleep(1000); } catch (InterruptedException e) { } int mapProgress = Math.round(rj.mapProgress() * 100); int reduceProgress = Math.round(rj.reduceProgress() * 100); String report = " map = " + mapProgress + "%, reduce = " + reduceProgress + "%"; if (!report.equals(lastReport) || System.currentTimeMillis() >= reportTime + maxReportInterval) { String output = dateFormat.format(Calendar.getInstance().getTime()) + report; System.out.println(output); lastReport = report; reportTime = System.currentTimeMillis(); } } System.exit(0); }
From source file:ApplicationMaster.java
License:Apache License
private void renameScriptFile(final Path renamedScriptPath) throws IOException, InterruptedException { appSubmitterUgi.doAs(new PrivilegedExceptionAction<Void>() { @Override/* w ww .j a va 2s . c o m*/ public Void run() throws IOException { FileSystem fs = renamedScriptPath.getFileSystem(conf); fs.rename(new Path(scriptPath), renamedScriptPath); return null; } }); LOG.info("User " + appSubmitterUgi.getUserName() + " added suffix(.sh/.bat) to script file as " + renamedScriptPath); }
From source file:JavaCustomReceiver.java
License:Apache License
/** Create a socket connection and receive data until receiver is stopped */ private void receive() { Socket socket = null;/*w w w .j a v a 2 s. c o m*/ String userInput = null; try { // connect to the server socket = new Socket(host, port); // BufferedReader reader = new BufferedReader(new InputStreamReader(socket.getInputStream())); // Path pt=new Path("hdfs://192.168.0.1:9000/equinox-sanjose.20120119-netflow.txt"); // FileSystem fs = FileSystem.get(new Configuration()); // BufferedReader in=new BufferedReader(new InputStreamReader(fs.open(pt))); Path pt = new Path("hdfs://192.168.0.1:9000/user/hduser/equinox-sanjose.20120119-netflow.txt"); Configuration conf = new Configuration(); conf.addResource(new Path("/usr/local/hadoop/conf/core-site.xml")); conf.addResource(new Path("/usr/local/hadoop/conf/hdfs-site.xml")); // FileSystem fs = FileSystem.get(conf); FileSystem fs = pt.getFileSystem(conf); System.out.println(fs.getHomeDirectory()); BufferedReader in = new BufferedReader(new InputStreamReader(fs.open(pt))); // BufferedReader in = new BufferedReader( // new FileReader( // "/home/hduser/spark_scratchPad/equinox-sanjose.20120119-netflow.txt")); // // Until stopped or connection broken continue reading while (!isStopped() && (userInput = in.readLine()) != null) { System.out.println("Received data '" + userInput + "'"); store(userInput); } in.close(); socket.close(); // Restart in an attempt to connect again when server is active again restart("Trying to connect again"); } catch (ConnectException ce) { // restart if could not connect to server restart("Could not connect", ce); } catch (Throwable t) { restart("Error receiving data", t); } }