List of usage examples for org.apache.hadoop.mapreduce Job setJobName
public void setJobName(String name) throws IllegalStateException
From source file:com.cloudera.recordservice.examples.mapreduce.RecordCount.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: RecordCount <input_query> <output_path>"); System.exit(1);//w w w.j a va2s . c o m } String inputQuery = args[0]; String output = args[1]; Job job = Job.getInstance(getConf()); job.setJobName("recordcount"); job.setJarByClass(RecordCount.class); job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); job.setNumReduceTasks(1); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(LongWritable.class); RecordServiceConfig.setInputQuery(job.getConfiguration(), inputQuery); job.setInputFormatClass(RecordServiceInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileSystem fs = FileSystem.get(job.getConfiguration()); Path outputPath = new Path(output); if (fs.exists(outputPath)) fs.delete(outputPath, true); FileOutputFormat.setOutputPath(job, outputPath); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.recordservice.examples.terasort.TeraChecksum.java
License:Apache License
@Override public int run(String[] args) throws Exception { boolean useRecordService = false; Job job = Job.getInstance(getConf()); if (args.length != 2 && args.length != 3) { usage();//from ww w.j a v a 2 s . c o m return 2; } if (args.length == 3) { useRecordService = Boolean.parseBoolean(args[2]); } FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setJobName("TeraSum"); job.setJarByClass(TeraChecksum.class); job.setMapperClass(ChecksumMapper.class); job.setReducerClass(ChecksumReducer.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(Unsigned16.class); // force a single reducer job.setNumReduceTasks(1); if (useRecordService) { RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]); job.setInputFormatClass(RecordServiceTeraInputFormat.class); } else { TeraInputFormat.setInputPaths(job, new Path(args[0])); job.setInputFormatClass(TeraInputFormat.class); } return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.recordservice.examples.terasort.TeraGen.java
License:Apache License
/** * @param args the cli arguments/*from w w w.ja va2s .c om*/ */ @Override public int run(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Job job = Job.getInstance(getConf()); if (args.length != 2) { usage(); return 2; } setNumberOfRows(job, parseHumanLong(args[0])); Path outputDir = new Path(args[1]); if (outputDir.getFileSystem(getConf()).exists(outputDir)) { throw new IOException("Output directory " + outputDir + " already exists."); } FileOutputFormat.setOutputPath(job, outputDir); job.setJobName("TeraGen"); job.setJarByClass(TeraGen.class); job.setMapperClass(SortGenMapper.class); job.setNumReduceTasks(0); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setInputFormatClass(RangeInputFormat.class); job.setOutputFormatClass(TeraOutputFormat.class); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.recordservice.examples.terasort.TeraSort.java
License:Apache License
@Override public int run(String[] args) throws Exception { boolean useRecordService = false; if (args.length != 2 && args.length != 3) { usage();/*from ww w. j a va 2 s . c o m*/ return 1; } if (args.length == 3) { useRecordService = Boolean.parseBoolean(args[2]); } LOG.info("starting"); Job job = Job.getInstance(getConf()); boolean useSimplePartitioner = getUseSimplePartitioner(job); if (useRecordService) { RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]); job.setInputFormatClass(RecordServiceTeraInputFormat.class); useSimplePartitioner = true; } else { Path inputDir = new Path(args[0]); TeraInputFormat.setInputPaths(job, inputDir); job.setInputFormatClass(TeraInputFormat.class); } Path outputDir = new Path(args[1]); FileOutputFormat.setOutputPath(job, outputDir); job.setJobName("TeraSort"); job.setJarByClass(TeraSort.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setOutputFormatClass(TeraOutputFormat.class); if (useSimplePartitioner) { job.setPartitionerClass(SimplePartitioner.class); } else { long start = System.currentTimeMillis(); Path partitionFile = new Path(outputDir, TeraInputFormat.PARTITION_FILENAME); URI partitionUri = new URI(partitionFile.toString() + "#" + TeraInputFormat.PARTITION_FILENAME); try { TeraInputFormat.writePartitionFile(job, partitionFile); } catch (Throwable e) { LOG.error(e.getMessage()); return -1; } job.addCacheFile(partitionUri); long end = System.currentTimeMillis(); System.out.println("Spent " + (end - start) + "ms computing partitions."); job.setPartitionerClass(TotalOrderPartitioner.class); } job.getConfiguration().setInt("dfs.replication", getOutputReplication(job)); TeraOutputFormat.setFinalSync(job, true); int ret = job.waitForCompletion(true) ? 0 : 1; LOG.info("done"); return ret; }
From source file:com.cloudera.recordservice.examples.terasort.TeraValidate.java
License:Apache License
@Override public int run(String[] args) throws Exception { boolean useRecordService = false; if (args.length != 2 && args.length != 3) { usage();//from www . ja va2 s .c om return 1; } if (args.length == 3) { useRecordService = Boolean.parseBoolean(args[2]); } Job job = Job.getInstance(getConf()); 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); // force a single split FileInputFormat.setMinInputSplitSize(job, Long.MAX_VALUE); if (useRecordService) { RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]); job.setInputFormatClass(RecordServiceTeraInputFormat.class); } else { TeraInputFormat.setInputPaths(job, new Path(args[0])); job.setInputFormatClass(TeraInputFormat.class); } return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.conversantmedia.mapreduce.tool.annotation.handler.MaraAnnotationUtil.java
License:Apache License
/** * * @param job the job * @param jobField the field to retrieve annotations from * @param driver the driver bean * @param context the tool context * @throws ToolException if any issue is encountered through reflection or expression evaluation *///ww w.j av a2s .co m public void configureJobFromField(Job job, Field jobField, Object driver, AnnotatedToolContext context) throws ToolException { JobInfo jobInfo = jobField.getAnnotation(JobInfo.class); String name = StringUtils.isBlank(jobInfo.value()) ? jobInfo.name() : jobInfo.value(); if (StringUtils.isBlank(name)) { name = defaultDriverIdForClass(driver.getClass()); } name = (String) ExpressionEvaluator.instance().evaluate(driver, context, name); job.setJobName(name); if (!jobInfo.numReducers().equals("-1")) { if (NumberUtils.isNumber(jobInfo.numReducers())) { job.setNumReduceTasks(Integer.valueOf(jobInfo.numReducers())); } else { Object reducerValue = ExpressionEvaluator.instance().evaluate(driver, context, jobInfo.numReducers()); if (reducerValue != null) { job.setNumReduceTasks((Integer) reducerValue); } } } // We can override (the runjob script does) which jar to use instead of using running driver class if (StringUtils.isBlank(job.getConfiguration().get("mapred.jar"))) { job.setJarByClass(driver.getClass()); } handleJobFieldAnnotations(job, jobField, jobInfo); }
From source file:com.cotdp.hadoop.ZipFileTest.java
License:Apache License
/** * This test operates on a single file/*from ww w.j ava 2 s . c o m*/ * * Expected result: success * * @throws IOException * @throws InterruptedException * @throws ClassNotFoundException */ public void testSingle() throws IOException, ClassNotFoundException, InterruptedException { LOG.info("============================================================"); LOG.info("== Running testSingle() =="); LOG.info("============================================================"); // Standard stuff Job job = new Job(conf); job.setJobName(this.getClass().getSimpleName()); job.setJarByClass(this.getClass()); job.setMapperClass(MyMapper.class); job.setReducerClass(MyReducer.class); // job.setInputFormatClass(ZipFileInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); // The output files will contain "Word [TAB] Count" job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // ZipFileInputFormat.setInputPaths(job, new Path(inputPath, "zip-01.zip")); TextOutputFormat.setOutputPath(job, new Path(workingPath, "Output_Single")); // assertTrue(job.waitForCompletion(true)); }
From source file:com.cotdp.hadoop.ZipFileTest.java
License:Apache License
/** * This test operates on a Path containing files that will cause the Job to fail * /*from ww w . j a v a2 s . c om*/ * Expected result: failure * * @throws IOException * @throws InterruptedException * @throws ClassNotFoundException */ public void testMultiple() throws IOException, ClassNotFoundException, InterruptedException { LOG.info("============================================================"); LOG.info("== Running testMultiple() =="); LOG.info("============================================================"); // Standard stuff Job job = new Job(conf); job.setJobName(this.getClass().getSimpleName()); job.setJarByClass(this.getClass()); job.setMapperClass(MyMapper.class); job.setReducerClass(MyReducer.class); // job.setInputFormatClass(ZipFileInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); // The output files will contain "Word [TAB] Count" job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // ZipFileInputFormat.setInputPaths(job, inputPath); TextOutputFormat.setOutputPath(job, new Path(workingPath, "Output_Multiple")); // assertFalse(job.waitForCompletion(true)); }
From source file:com.cotdp.hadoop.ZipFileTest.java
License:Apache License
/** * This test is identical to testMultiple() however the ZipFileInputFormat is set to * be lenient, errors that cause testMultiple() to fail will be quietly ignored here. * /*ww w. j a v a 2 s . com*/ * Expected result: success * * @throws IOException * @throws InterruptedException * @throws ClassNotFoundException */ public void testMultipleLenient() throws IOException, ClassNotFoundException, InterruptedException { LOG.info("============================================================"); LOG.info("== Running testMultipleLenient() =="); LOG.info("============================================================"); // Standard stuff Job job = new Job(conf); job.setJobName(this.getClass().getSimpleName()); job.setJarByClass(this.getClass()); job.setMapperClass(MyMapper.class); job.setReducerClass(MyReducer.class); // job.setInputFormatClass(ZipFileInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); // The output files will contain "Word [TAB] Count" job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // ZipFileInputFormat.setLenient(true); ZipFileInputFormat.setInputPaths(job, inputPath); TextOutputFormat.setOutputPath(job, new Path(workingPath, "Output_MultipleLenient")); // assertTrue(job.waitForCompletion(true)); }
From source file:com.cotdp.hadoop.ZipFileTest.java
License:Apache License
/** * ZipInputStream doesn't support encrypted entries thus this will fail. * //from www. j a v a 2s . c o m * Expected result: failure * * @throws IOException * @throws InterruptedException * @throws ClassNotFoundException */ public void testEncryptedZip() throws IOException, ClassNotFoundException, InterruptedException { LOG.info("============================================================"); LOG.info("== Running testEncryptedZip() =="); LOG.info("============================================================"); // Standard stuff Job job = new Job(conf); job.setJobName(this.getClass().getSimpleName()); job.setJarByClass(this.getClass()); job.setMapperClass(MyMapper.class); job.setReducerClass(MyReducer.class); // job.setInputFormatClass(ZipFileInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); // The output files will contain "Word [TAB] Count" job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // ZipFileInputFormat.setInputPaths(job, new Path(inputPath, "encrypted.zip")); TextOutputFormat.setOutputPath(job, new Path(workingPath, "Output_Encrypted")); // assertFalse(job.waitForCompletion(true)); }