List of usage examples for org.apache.hadoop.mapred JobConf setOutputFormat
public void setOutputFormat(Class<? extends OutputFormat> theClass)
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);/* w w w . j a v a 2 s .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.Sort.java
License:Apache License
/** * The main driver for sort program./*from www.j a va 2 s. c o m*/ * Invoke this method to submit the map/reduce job. * @throws IOException When there is communication problems with the * job tracker. */ public int run(String[] args) throws Exception { JobConf jobConf = new JobConf(getConf(), Sort.class); jobConf.setJobName("sorter"); jobConf.setMapperClass(IdentityMapper.class); jobConf.setReducerClass(IdentityReducer.class); JobClient client = new JobClient(jobConf); ClusterStatus cluster = client.getClusterStatus(); int num_reduces = (int) (cluster.getMaxReduceTasks() * 0.9); String sort_reduces = jobConf.get("test.sort.reduces_per_host"); if (sort_reduces != null) { num_reduces = cluster.getTaskTrackers() * Integer.parseInt(sort_reduces); } Class<? extends InputFormat> inputFormatClass = SequenceFileInputFormat.class; Class<? extends OutputFormat> outputFormatClass = SequenceFileOutputFormat.class; Class<? extends WritableComparable> outputKeyClass = BytesWritable.class; Class<? extends Writable> outputValueClass = BytesWritable.class; List<String> otherArgs = new ArrayList<String>(); InputSampler.Sampler<K, V> sampler = null; for (int i = 0; i < args.length; ++i) { try { if ("-m".equals(args[i])) { jobConf.setNumMapTasks(Integer.parseInt(args[++i])); } else if ("-r".equals(args[i])) { num_reduces = Integer.parseInt(args[++i]); } else if ("-inFormat".equals(args[i])) { inputFormatClass = Class.forName(args[++i]).asSubclass(InputFormat.class); } else if ("-outFormat".equals(args[i])) { outputFormatClass = Class.forName(args[++i]).asSubclass(OutputFormat.class); } else if ("-outKey".equals(args[i])) { outputKeyClass = Class.forName(args[++i]).asSubclass(WritableComparable.class); } else if ("-outValue".equals(args[i])) { outputValueClass = Class.forName(args[++i]).asSubclass(Writable.class); } else if ("-totalOrder".equals(args[i])) { double pcnt = Double.parseDouble(args[++i]); int numSamples = Integer.parseInt(args[++i]); int maxSplits = Integer.parseInt(args[++i]); if (0 >= maxSplits) maxSplits = Integer.MAX_VALUE; sampler = new InputSampler.RandomSampler<K, V>(pcnt, numSamples, maxSplits); } else { otherArgs.add(args[i]); } } catch (NumberFormatException except) { System.out.println("ERROR: Integer expected instead of " + args[i]); return printUsage(); } catch (ArrayIndexOutOfBoundsException except) { System.out.println("ERROR: Required parameter missing from " + args[i - 1]); return printUsage(); // exits } } // Set user-supplied (possibly default) job configs jobConf.setNumReduceTasks(num_reduces); jobConf.setInputFormat(inputFormatClass); jobConf.setOutputFormat(outputFormatClass); jobConf.setOutputKeyClass(outputKeyClass); jobConf.setOutputValueClass(outputValueClass); // Make sure there are exactly 2 parameters left. if (otherArgs.size() != 2) { System.out.println("ERROR: Wrong number of parameters: " + otherArgs.size() + " instead of 2."); return printUsage(); } FileInputFormat.setInputPaths(jobConf, otherArgs.get(0)); FileOutputFormat.setOutputPath(jobConf, new Path(otherArgs.get(1))); if (sampler != null) { System.out.println("Sampling input to effect total-order sort..."); jobConf.setPartitionerClass(TotalOrderPartitioner.class); Path inputDir = FileInputFormat.getInputPaths(jobConf)[0]; inputDir = inputDir.makeQualified(inputDir.getFileSystem(jobConf)); Path partitionFile = new Path(inputDir, "_sortPartitioning"); TotalOrderPartitioner.setPartitionFile(jobConf, partitionFile); InputSampler.<K, V>writePartitionFile(jobConf, sampler); URI partitionUri = new URI(partitionFile.toString() + "#" + "_sortPartitioning"); DistributedCache.addCacheFile(partitionUri, jobConf); DistributedCache.createSymlink(jobConf); } System.out.println("Running on " + cluster.getTaskTrackers() + " nodes to sort from " + FileInputFormat.getInputPaths(jobConf)[0] + " into " + FileOutputFormat.getOutputPath(jobConf) + " with " + num_reduces + " reduces."); Date startTime = new Date(); System.out.println("Job started: " + startTime); jobResult = JobClient.runJob(jobConf); Date end_time = new Date(); System.out.println("Job ended: " + end_time); System.out.println("The job took " + (end_time.getTime() - startTime.getTime()) / 1000 + " seconds."); return 0; }
From source file:com.benchmark.mapred.terasort.TeraGen.java
License:Apache License
/** * @param args the cli arguments/* w w w .j a v a 2 s . c o m*/ */ public int run(String[] args) throws IOException { JobConf job = (JobConf) getConf(); setNumberOfRows(job, Long.parseLong(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setJobName("TeraGen"); job.setJarByClass(TeraGen.class); job.setMapperClass(SortGenMapper.class); job.setNumReduceTasks(0); job.setNumMapTasks(50); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setInputFormat(RangeInputFormat.class); job.setOutputFormat(TeraOutputFormat.class); JobClient.runJob(job); return 0; }
From source file:com.benchmark.mapred.terasort.TeraSort.java
License:Apache License
public int run(String[] args) throws Exception { LOG.info("starting"); JobConf job = (JobConf) getConf(); Path inputDir = new Path(args[0]); if (args.length != 3) { System.out.println("ERROR: Wrong number of parameters: " + args.length + " instead of 3."); }//from www . ja va 2 s .c o m inputDir = inputDir.makeQualified(inputDir.getFileSystem(job)); Path partitionFile = new Path(inputDir, TeraInputFormat.PARTITION_FILENAME); URI partitionUri = new URI(partitionFile.toString() + "#" + TeraInputFormat.PARTITION_FILENAME); TeraInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setJobName("TeraSort"); job.setJarByClass(TeraSort.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setInputFormat(TeraInputFormat.class); job.setOutputFormat(TeraOutputFormat.class); job.setPartitionerClass(TotalOrderPartitioner.class); job.setNumReduceTasks(Integer.parseInt(args[2])); TeraInputFormat.writePartitionFile(job, partitionFile); DistributedCache.addCacheFile(partitionUri, job); DistributedCache.createSymlink(job); job.setInt("dfs.replication", 1); TeraOutputFormat.setFinalSync(job, true); Date startIteration = new Date(); JobClient.runJob(job); Date endIteration = new Date(); System.out.println( "The iteration took " + (endIteration.getTime() - startIteration.getTime()) / 1000 + " seconds."); LOG.info("done"); return 0; }
From source file:com.bixolabs.cascading.avro.AvroScheme.java
License:Apache License
@SuppressWarnings({ "deprecation" })
@Override/*from www . j a v a2 s .co m*/
public void sinkInit(Tap tap, JobConf conf) {
conf.set(AvroJob.OUTPUT_SCHEMA, getSchema().toString());
conf.setOutputFormat(AvroOutputFormat.class);
// Since we're outputting to Avro, we need to set up output values.
// TODO KKr - why don't we need to set the OutputValueClass?
// TODO KKr - why do we need to set the OutputKeyComparatorClass?
conf.setOutputKeyClass(NullWritable.class);
conf.setOutputValueClass(AvroWrapper.class);
conf.setOutputKeyComparatorClass(AvroKeyComparator.class);
// conf.setMapOutputKeyClass(AvroKey.class);
// conf.setMapOutputValueClass(AvroValue.class);
// add AvroSerialization to io.serializations
// Collection<String> serializations = conf.getStringCollection("io.serializations");
// if (!serializations.contains(AvroSerialization.class.getName())) {
// serializations.add(AvroSerialization.class.getName());
// conf.setStrings("io.serializations", serializations.toArray(new String[0]));
// }
// Class<? extends Mapper> mapClass = conf.getMapperClass();
// Class<? extends Reducer> reduceClass = conf.getReducerClass();
// AvroJob.setOutputSchema(conf, getSchema());
// conf.setMapperClass(mapClass);
// conf.setReducerClass(reduceClass);
LOGGER.info(String.format("Initializing Avro scheme for sink tap - scheme fields: %s", _schemeFields));
}
From source file:com.chriscx.mapred.Driver.java
public int run(String[] args) throws Exception { JobConf conf = new JobConf(getConf(), Driver.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); List<String> other_args = new ArrayList<String>(); for (int i = 0; i < args.length; ++i) { if ("-skip".equals(args[i])) { DistributedCache.addCacheFile(new Path(args[++i]).toUri(), conf); conf.setBoolean("wordcount.skip.patterns", true); } else {//from w w w . jav a 2 s.c o m other_args.add(args[i]); } } FileInputFormat.setInputPaths(conf, new Path(other_args.get(0))); FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1))); JobClient.runJob(conf); return 0; }
From source file:com.chriscx.matching.Driver.java
public int run(String[] args) throws Exception { JobConf conf = new JobConf(getConf(), com.chriscx.mapred.Driver.class); conf.setJobName("Matching"); 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); List<String> other_args = new ArrayList<String>(); for (int i = 0; i < args.length; ++i) { if ("-skip".equals(args[i])) { DistributedCache.addCacheFile(new Path(args[++i]).toUri(), conf); conf.setBoolean("wordcount.skip.patterns", true); } else {//from w w w .j a v a2 s.c o m other_args.add(args[i]); } } FileInputFormat.setInputPaths(conf, new Path(other_args.get(0))); FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1))); JobClient.runJob(conf); return 0; }
From source file:com.cloudera.hbase.OldWordCount.java
License:Open Source License
public static void main(String[] args) throws Exception { JobConf conf = new JobConf(WordCount.class); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: wordcount <in> <out>"); System.exit(2);//from ww w .j a v a 2s. co m } conf.setJobName("word count"); 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(otherArgs[0])); FileOutputFormat.setOutputPath(conf, new Path(otherArgs[1])); JobClient.runJob(conf); return; }
From source file:com.cloudera.recordservice.examples.mapreduce.WordCount.java
License:Apache License
public void run(String[] args) throws Exception { boolean useRecordService = true; if (args.length == 3) { useRecordService = Boolean.parseBoolean(args[2]); } else if (args.length != 2) { System.err.println("Usage: WordCount <input path> <output path>"); System.exit(-1);// w ww . j a va 2s . c om } String input = args[0].trim(); String output = args[1]; JobConf conf = new JobConf(WordCount.class); conf.setJobName("wordcount-" + (useRecordService ? "with" : "without") + "-RecordService"); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(IntWritable.class); conf.setMapperClass(Map.class); conf.setCombinerClass(Reduce.class); conf.setReducerClass(Reduce.class); if (useRecordService) { conf.setInputFormat(com.cloudera.recordservice.mapred.TextInputFormat.class); RecordServiceConfig.setInput(conf, input); } else { conf.setInputFormat(TextInputFormat.class); FileInputFormat.setInputPaths(conf, new Path(input)); } FileSystem fs = FileSystem.get(conf); Path outputPath = new Path(output); if (fs.exists(outputPath)) fs.delete(outputPath, true); conf.setOutputFormat(TextOutputFormat.class); FileOutputFormat.setOutputPath(conf, outputPath); JobClient.runJob(conf); System.out.println("Done"); }
From source file:com.cloudera.recordservice.mapreduce.testapps.RecordCount.java
License:Apache License
public static long countRecords(String path) throws IOException { String output = TestUtil.getTempDirectory(); Path inputPath = new Path(path); Path outputPath = new Path(output); JobConf conf = new JobConf(RecordCount.class); conf.setJobName("recordcount"); conf.setOutputKeyClass(NullWritable.class); conf.setOutputValueClass(LongWritable.class); conf.setInt("mapreduce.job.reduces", 1); conf.setMapperClass(Map.class); conf.setCombinerClass(Reduce.class); conf.setReducerClass(Reduce.class); conf.setInputFormat(com.cloudera.recordservice.mapred.TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); FileInputFormat.setInputPaths(conf, inputPath); FileOutputFormat.setOutputPath(conf, outputPath); JobClient.runJob(conf);//ww w . ja v a2 s .co m // Read the result and return it. Since we set the number of reducers to 1, // there is always just one file containing the value. FileSystem fs = outputPath.getFileSystem(conf); FSDataInputStream resultStream = fs.open(new Path(output + "/part-00000")); byte[] bytes = new byte[16]; int length = resultStream.read(bytes); String result = new String(bytes, 0, length).trim(); return Long.parseLong(result); }