List of usage examples for org.apache.hadoop.mapred JobConf setLong
public void setLong(String name, long value)
name property to a long. From source file:Brush.PairMark.java
License:Apache License
public RunningJob run(String inputPath, String outputPath, long randseed) throws Exception { sLogger.info("Tool name: PairMark"); sLogger.info(" - input: " + inputPath); sLogger.info(" - output: " + outputPath); sLogger.info(" - randseed: " + randseed); JobConf conf = new JobConf(PairMark.class); conf.setJobName("PairMark " + inputPath); BrushConfig.initializeConfiguration(conf); conf.setLong("randseed", randseed); FileInputFormat.addInputPath(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); conf.setMapOutputKeyClass(Text.class); conf.setMapOutputValueClass(Text.class); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); conf.setMapperClass(PairMarkMapper.class); conf.setReducerClass(PairMarkReducer.class); //delete the output directory if it exists already FileSystem.get(conf).delete(new Path(outputPath), true); return JobClient.runJob(conf); }
From source file:com.benchmark.mapred.RandomTextWriter.java
License:Apache License
/** * This is the main routine for launching a distributed random write job. * It runs 10 maps/node and each node writes 1 gig of data to a DFS file. * The reduce doesn't do anything./* w w w . ja va 2 s . c om*/ * * @throws IOException */ public int run(String[] args) throws Exception { if (args.length == 0) { return printUsage(); } JobConf job = new JobConf(getConf()); job.setJarByClass(RandomTextWriter.class); job.setJobName("random-text-writer"); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setInputFormat(RandomWriter.RandomInputFormat.class); job.setMapperClass(Map.class); JobClient client = new JobClient(job); ClusterStatus cluster = client.getClusterStatus(); int numMapsPerHost = job.getInt("test.randomtextwrite.maps_per_host", 10); long numBytesToWritePerMap = job.getLong("test.randomtextwrite.bytes_per_map", 1 * 1024 * 1024 * 1024); if (numBytesToWritePerMap == 0) { System.err.println("Cannot have test.randomtextwrite.bytes_per_map set to 0"); return -2; } long totalBytesToWrite = job.getLong("test.randomtextwrite.total_bytes", numMapsPerHost * numBytesToWritePerMap * cluster.getTaskTrackers()); int numMaps = (int) (totalBytesToWrite / numBytesToWritePerMap); if (numMaps == 0 && totalBytesToWrite > 0) { numMaps = 1; job.setLong("test.randomtextwrite.bytes_per_map", totalBytesToWrite); } Class<? extends OutputFormat> outputFormatClass = SequenceFileOutputFormat.class; List<String> otherArgs = new ArrayList<String>(); for (int i = 0; i < args.length; ++i) { try { if ("-outFormat".equals(args[i])) { outputFormatClass = Class.forName(args[++i]).asSubclass(OutputFormat.class); } else { otherArgs.add(args[i]); } } catch (ArrayIndexOutOfBoundsException except) { System.out.println("ERROR: Required parameter missing from " + args[i - 1]); return printUsage(); // exits } } job.setOutputFormat(outputFormatClass); FileOutputFormat.setOutputPath(job, new Path(otherArgs.get(0))); job.setNumMapTasks(numMaps); System.out.println("Running " + numMaps + " maps."); // reducer NONE job.setNumReduceTasks(0); Date startTime = new Date(); System.out.println("Job started: " + startTime); JobClient.runJob(job); Date endTime = new Date(); System.out.println("Job ended: " + endTime); System.out.println("The job took " + (endTime.getTime() - startTime.getTime()) / 1000 + " seconds."); return 0; }
From source file:com.benchmark.mapred.RandomWriter.java
License:Apache License
/** * This is the main routine for launching a distributed random write job. * It runs 10 maps/node and each node writes 1 gig of data to a DFS file. * The reduce doesn't do anything.//from w w w. j ava 2s . c o m * * @throws IOException */ public int run(String[] args) throws Exception { if (args.length == 0) { System.out.println("Usage: writer <out-dir>"); ToolRunner.printGenericCommandUsage(System.out); return -1; } Path outDir = new Path(args[0]); JobConf job = new JobConf(getConf()); job.setJarByClass(RandomWriter.class); job.setJobName("random-writer"); FileOutputFormat.setOutputPath(job, outDir); job.setOutputKeyClass(BytesWritable.class); job.setOutputValueClass(BytesWritable.class); job.setInputFormat(RandomInputFormat.class); job.setMapperClass(Map.class); job.setReducerClass(IdentityReducer.class); job.setOutputFormat(SequenceFileOutputFormat.class); JobClient client = new JobClient(job); ClusterStatus cluster = client.getClusterStatus(); int numMapsPerHost = job.getInt("test.randomwriter.maps_per_host", 10); long numBytesToWritePerMap = job.getLong("test.randomwrite.bytes_per_map", 1 * 1024 * 1024 * 1024); if (numBytesToWritePerMap == 0) { System.err.println("Cannot have test.randomwrite.bytes_per_map set to 0"); return -2; } long totalBytesToWrite = job.getLong("test.randomwrite.total_bytes", numMapsPerHost * numBytesToWritePerMap * cluster.getTaskTrackers()); int numMaps = (int) (totalBytesToWrite / numBytesToWritePerMap); if (numMaps == 0 && totalBytesToWrite > 0) { numMaps = 1; job.setLong("test.randomwrite.bytes_per_map", totalBytesToWrite); } job.setNumMapTasks(numMaps); System.out.println("Running " + numMaps + " maps."); // reducer NONE job.setNumReduceTasks(0); Date startTime = new Date(); System.out.println("Job started: " + startTime); JobClient.runJob(job); Date endTime = new Date(); System.out.println("Job ended: " + endTime); System.out.println("The job took " + (endTime.getTime() - startTime.getTime()) / 1000 + " seconds."); return 0; }
From source file:com.benchmark.mapred.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);/*from ww w.ja va2s .c o 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); job.setJobName("Sleep job"); 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:com.benchmark.mapred.terasort.TeraGen.java
License:Apache License
static void setNumberOfRows(JobConf job, long numRows) { job.setLong("terasort.num-rows", numRows); }
From source file:com.benchmark.mapred.terasort.TeraValidate.java
License:Apache License
public int run(String[] args) throws Exception { JobConf job = (JobConf) getConf(); TeraInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setJobName("TeraValidate"); job.setJarByClass(TeraValidate.class); job.setMapperClass(ValidateMapper.class); job.setReducerClass(ValidateReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); // force a single reducer job.setNumReduceTasks(1);/*from w w w . j av a 2 s .co m*/ // force a single split job.setLong("mapred.min.split.size", Long.MAX_VALUE); job.setInputFormat(TeraInputFormat.class); JobClient.runJob(job); return 0; }
From source file:com.bianfeng.bfas.hive.io.RealtimeInputFormat2.java
License:Apache License
/** Splits files returned by {@link #listStatus(JobConf)} when * they're too big.*//*www.j a v a2 s . c o m*/ @SuppressWarnings("deprecation") public InputSplit[] getSplits(JobConf job, int numSplits) throws IOException { LOG.warn("test go go go"); FileStatus[] files = listStatus(job); // Save the number of input files in the job-conf job.setLong(NUM_INPUT_FILES, files.length); long totalSize = 0; // compute total size for (FileStatus file : files) { // check we have valid files if (file.isDir()) { throw new IOException("Not a file: " + file.getPath()); } totalSize += file.getLen(); } long goalSize = totalSize / (numSplits == 0 ? 1 : numSplits); long minSize = Math.max(job.getLong("mapred.min.split.size", 1), minSplitSize); // generate splits ArrayList<FileSplit> splits = new ArrayList<FileSplit>(numSplits); NetworkTopology clusterMap = new NetworkTopology(); for (FileStatus file : files) { Path path = file.getPath(); FileSystem fs = path.getFileSystem(job); long length = file.getLen(); BlockLocation[] blkLocations = fs.getFileBlockLocations(file, 0, length); if ((length != 0) && isSplitable(fs, path)) { long blockSize = file.getBlockSize(); long splitSize = computeSplitSize(goalSize, minSize, blockSize); long bytesRemaining = length; while (((double) bytesRemaining) / splitSize > SPLIT_SLOP) { String[] splitHosts = getSplitHosts(blkLocations, length - bytesRemaining, splitSize, clusterMap); splits.add(new FileSplit(path, length - bytesRemaining, splitSize, splitHosts)); bytesRemaining -= splitSize; } if (bytesRemaining != 0) { splits.add(new FileSplit(path, length - bytesRemaining, bytesRemaining, blkLocations[blkLocations.length - 1].getHosts())); } } else if (length != 0) { String[] splitHosts = getSplitHosts(blkLocations, 0, length, clusterMap); splits.add(new FileSplit(path, 0, length, splitHosts)); } else { //Create empty hosts array for zero length files splits.add(new FileSplit(path, 0, length, new String[0])); } } LOG.debug("Total # of splits: " + splits.size()); return splits.toArray(new FileSplit[splits.size()]); }
From source file:com.blackberry.logdriver.mapred.avro.AvroBlockInputFormat.java
License:Apache License
@SuppressWarnings("deprecation") @Override/* w w w . ja v a 2 s . c o m*/ public RecordReader<AvroFileHeader, BytesWritable> getRecordReader(InputSplit split, JobConf job, Reporter reporter) throws IOException { // Ensure we have sensible defaults for how we build blocks. if (job.get("mapreduce.job.max.split.locations") == null) { job.setLong("mapreduce.job.max.split.locations", MAX_SPLIT_LOCATIONS); } if (job.get("mapred.max.split.size") == null) { // Try to set the split size to the default block size. In case of // failure, we'll use this 128MB default. long blockSize = 128 * 1024 * 1024; // 128MB try { blockSize = FileSystem.get(job).getDefaultBlockSize(); } catch (IOException e) { LOG.error("Error getting filesystem to get get default block size (this does not bode well)."); } job.setLong("mapred.max.split.size", blockSize); } return new AvroBlockRecordReader(split, job); }
From source file:com.blackberry.logdriver.mapred.boom.BoomInputFormat.java
License:Apache License
@SuppressWarnings("deprecation") @Override/*from w ww . j a v a 2s.co m*/ public InputSplit[] getSplits(JobConf job, int numSplits) throws IOException { // Ensure we have sensible defaults for how we build blocks. if (job.get("mapreduce.job.max.split.locations") == null) { job.setLong("mapreduce.job.max.split.locations", MAX_SPLIT_LOCATIONS); } if (job.get("mapred.max.split.size") == null) { // Try to set the split size to the default block size. In case of // failure, we'll use this 128MB default. long blockSize = 128 * 1024 * 1024; // 128MB try { blockSize = FileSystem.get(job).getDefaultBlockSize(); } catch (IOException e) { LOG.error("Error getting filesystem to get get default block size (this does not bode well)."); } job.setLong("mapred.max.split.size", blockSize); } return super.getSplits(job, numSplits); }
From source file:com.conductor.s3.S3OptimizedFileInputFormatMRV1.java
License:Apache License
/** * {@inheritDoc}//from w w w . j av a2 s . co m */ @Override public InputSplit[] getSplits(final JobConf job, final int numSplits) throws IOException { long minSize = getMinSplitSize(job); long maxSize = getMaxSplitSize(job); final List<FileStatus> fileStatuses = Lists.newArrayList(listStatus(job)); final List<InputSplit> splits = S3InputFormatUtils.convertToInputSplitsMRV1(fileStatuses, minSize, maxSize); // Save the number of input files in the job-conf job.setLong("mapreduce.input.num.files", fileStatuses.size()); return splits.toArray(new InputSplit[splits.size()]); }