List of usage examples for org.apache.hadoop.mapreduce Job addCacheFile
public void addCacheFile(URI uri)
From source file:GetUserInfoGivenMovieId.java
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); conf.set("movieId", args[2]); Job job = new Job(conf, "GetUserInfoGivenMovieId"); job.setInputFormatClass(TextInputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setJarByClass(GetUserInfoGivenMovieId.class); job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[3])); boolean flag1 = job.waitForCompletion(true); if (flag1) {//from ww w.j a v a 2 s . c om Configuration conf2 = new Configuration(); //FileSystem fs = FileSystem.get(conf2); //Path Intermediate = new Path(args[1]); //DistributedCache.addCacheFile(Intermediate.toUri(), conf2); //DistributedCache.addCacheFile(new URI(args[1]),conf2); Job job2 = new Job(conf2, "UserInfo"); /*Job job2 = new Job(new Configuration()); Configuration conf2 = job.getConfiguration(); job2.setJobName("Join with Cache"); DistributedCache.addCacheFile(new URI(args[1]), conf2);*/ job2.addCacheFile(new URI(args[1])); job2.setOutputKeyClass(Text.class); job2.setOutputValueClass(Text.class); job2.setJarByClass(GetUserInfoGivenMovieId.class); job2.setMapperClass(MapWithJoin.class); //job2.setCombinerClass(Reduce.class); job2.setReducerClass(ReduceFinal.class); job2.setInputFormatClass(TextInputFormat.class); job2.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.addInputPath(job2, new Path(args[3])); FileOutputFormat.setOutputPath(job2, new Path(args[4])); job2.waitForCompletion(true); } }
From source file:cienciaCelularMR.Main.java
@Override public int run(String[] args) throws Exception { for (int i = 0; i < args.length; i++) { System.out.println("Hadoop - arg[" + i + "] es: " + args[i]); }/* w w w . j a va2 s. c o m*/ //Configuracin de memoria de YARN Configuration conf = new Configuration(); conf.set("mapreduce.map.memory.mb", "1400"); conf.set("mapreduce.reduce.memory.mb", "2800"); conf.set("mapreduce.map.java.opts", "-Xmx1120m"); conf.set("mapreduce.reduce.java.opts", "-Xmx2240m"); conf.set("yarn.app.mapreduce.am.resource.mb", "2800"); conf.set("yarn.app.mapreduce.am.command-opts", "-Xmx2240m"); conf.set("yarn.nodemanager.resource.memory-mb", "5040"); conf.set("yarn.scheduler.minimum-allocation-mb", "1400"); conf.set("yarn.scheduler.maximum-allocation-mb", "5040"); conf.set("mapreduce.task.timeout", "18000000");//5 horas //Creacin del Job Job job = Job.getInstance(conf); job.setInputFormatClass(WholeFileInputFormat.class); FileInputFormat.setInputPaths(job, new Path(args[5])); FileOutputFormat.setOutputPath(job, new Path(args[6])); //Salidas alternativas de Mapper para brindar informacin MultipleOutputs.addNamedOutput(job, "controloutput", TextOutputFormat.class, KeyMcell.class, Text.class); MultipleOutputs.addNamedOutput(job, "errormcell", TextOutputFormat.class, KeyMcell.class, Text.class); //Archivos copiados a cache de los nodos job.addCacheFile(new Path("wasb:///mcell.exe").toUri()); job.addCacheFile(new Path("wasb:///fernet.exe").toUri()); job.addCacheFile(new Path("wasb:///fernet.cfg").toUri()); job.addCacheFile(new Path("wasb:///libconfig_d.dll").toUri()); job.addCacheFile(new Path("wasb:///libtiff3.dll").toUri()); job.addCacheFile(new Path("wasb:///jpeg62.dll").toUri()); job.addCacheFile(new Path("wasb:///zlib1.dll").toUri()); job.addCacheFile(new Path("wasb:///msvcr100d.dll").toUri()); job.setJarByClass(Main.class); Configuration mapAConf = new Configuration(false); ChainMapper.addMapper(job, McellMapper.class, KeyMcell.class, BytesWritable.class, KeyMcell.class, Text.class, mapAConf); Configuration mapBConf = new Configuration(false); ChainMapper.addMapper(job, FernetMapper.class, KeyMcell.class, Text.class, KeyMcell.class, FernetOutput.class, mapBConf); job.setReducerClass(ResultReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(BytesWritable.class); job.submit(); return 0; }
From source file:clustering.mst.Driver.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length < 3) { System.err.printf("usage: %s similarity_result_dir document_count_file output_dir " + "[cluster_threshold] [reduce_number] [compression]\n", getClass().getSimpleName()); System.exit(1);//from ww w. ja va 2s . com } Path step1_OutputDir = new Path(args[2] + "/step1"); Path resultDir = new Path(args[2] + "/result"); URI docCntFile = new URI(args[1] + "/part-r-00000#docCnt"); Configuration conf = getConf(); conf = MapReduceUtils.initConf(conf); if (args.length > 3) { conf.setDouble("final.threshold", Double.valueOf(args[3])); } else { conf.setDouble("final.threshold", 0.2d); } if (args.length > 4) { conf.setInt("reduce.task.num", Integer.valueOf(args[4])); } else { conf.setInt("reduce.task.num", 5); } JobControl jobControl = new JobControl("mst jobs"); /* step 1, split and calculate the child msts */ Job childJob = Job.getInstance(conf, "mst child job"); childJob.setJarByClass(Driver.class); childJob.addCacheFile(docCntFile); if (args.length > 5 && args[5].equals("0")) { FileInputFormat.addInputPath(childJob, new Path(args[0])); childJob.setInputFormatClass(KeyValueTextInputFormat.class); } else { SequenceFileInputFormat.addInputPath(childJob, new Path(args[0])); childJob.setInputFormatClass(SequenceFileAsTextInputFormat.class); } FileOutputFormat.setOutputPath(childJob, step1_OutputDir); childJob.setMapperClass(ChildMapper.class); childJob.setMapOutputKeyClass(DoubleWritable.class); childJob.setMapOutputValueClass(Text.class); childJob.setPartitionerClass(ChildPartitioner.class); childJob.setReducerClass(ChildReducer.class); childJob.setNumReduceTasks(conf.getInt("reduce.task.num", 1)); childJob.setOutputKeyClass(DoubleWritable.class); childJob.setOutputValueClass(Text.class); ControlledJob controlledChildJob = new ControlledJob(conf); controlledChildJob.setJob(childJob); jobControl.addJob(controlledChildJob); /* step 2, merge step 1's output and calculate final mst */ Job finalJob = Job.getInstance(conf, "mst final job"); finalJob.setJarByClass(FinalReducer.class); finalJob.addCacheFile(docCntFile); FileInputFormat.addInputPath(finalJob, step1_OutputDir); finalJob.setInputFormatClass(KeyValueTextInputFormat.class); finalJob.setMapperClass(FinalMapper.class); finalJob.setMapOutputKeyClass(DoubleWritable.class); finalJob.setMapOutputValueClass(Text.class); finalJob.setReducerClass(FinalReducer.class); finalJob.setOutputKeyClass(IntWritable.class); finalJob.setOutputValueClass(IntWritable.class); FileOutputFormat.setOutputPath(finalJob, resultDir); ControlledJob finalControlledJob = new ControlledJob(conf); finalControlledJob.setJob(finalJob); finalControlledJob.addDependingJob(controlledChildJob); jobControl.addJob(finalControlledJob); // run jobs MapReduceUtils.runJobs(jobControl); return finalJob.waitForCompletion(true) ? 0 : 1; }
From source file:co.cask.cdap.internal.app.runtime.batch.MapReduceRuntimeService.java
License:Apache License
@Override protected void startUp() throws Exception { // Creates a temporary directory locally for storing all generated files. File tempDir = createTempDirectory(); cleanupTask = createCleanupTask(tempDir); try {//w w w. j a v a2 s. c o m Job job = createJob(new File(tempDir, "mapreduce")); Configuration mapredConf = job.getConfiguration(); classLoader = new MapReduceClassLoader(injector, cConf, mapredConf, context.getProgram().getClassLoader(), context.getPlugins(), context.getPluginInstantiator()); cleanupTask = createCleanupTask(cleanupTask, classLoader); mapredConf.setClassLoader(new WeakReferenceDelegatorClassLoader(classLoader)); ClassLoaders.setContextClassLoader(mapredConf.getClassLoader()); context.setJob(job); beforeSubmit(job); // Localize additional resources that users have requested via BasicMapReduceContext.localize methods Map<String, String> localizedUserResources = localizeUserResources(job, tempDir); // Override user-defined job name, since we set it and depend on the name. // https://issues.cask.co/browse/CDAP-2441 String jobName = job.getJobName(); if (!jobName.isEmpty()) { LOG.warn("Job name {} is being overridden.", jobName); } job.setJobName(getJobName(context)); // Create a temporary location for storing all generated files through the LocationFactory. Location tempLocation = createTempLocationDirectory(); cleanupTask = createCleanupTask(cleanupTask, tempLocation); // For local mode, everything is in the configuration classloader already, hence no need to create new jar if (!MapReduceTaskContextProvider.isLocal(mapredConf)) { // After calling beforeSubmit, we know what plugins are needed for the program, hence construct the proper // ClassLoader from here and use it for setting up the job Location pluginArchive = createPluginArchive(tempLocation); if (pluginArchive != null) { job.addCacheArchive(pluginArchive.toURI()); mapredConf.set(Constants.Plugin.ARCHIVE, pluginArchive.getName()); } } // set resources for the job TaskType.MAP.setResources(mapredConf, context.getMapperResources()); TaskType.REDUCE.setResources(mapredConf, context.getReducerResources()); // replace user's Mapper & Reducer's with our wrappers in job config MapperWrapper.wrap(job); ReducerWrapper.wrap(job); // packaging job jar which includes cdap classes with dependencies File jobJar = buildJobJar(job, tempDir); job.setJar(jobJar.toURI().toString()); Location programJar = programJarLocation; if (!MapReduceTaskContextProvider.isLocal(mapredConf)) { // Copy and localize the program jar in distributed mode programJar = copyProgramJar(tempLocation); job.addCacheFile(programJar.toURI()); List<String> classpath = new ArrayList<>(); // Localize logback.xml Location logbackLocation = createLogbackJar(tempLocation); if (logbackLocation != null) { job.addCacheFile(logbackLocation.toURI()); classpath.add(logbackLocation.getName()); } // Generate and localize the launcher jar to control the classloader of MapReduce containers processes classpath.add("job.jar/lib/*"); classpath.add("job.jar/classes"); Location launcherJar = createLauncherJar( Joiner.on(",").join(MapReduceContainerHelper.getMapReduceClassPath(mapredConf, classpath)), tempLocation); job.addCacheFile(launcherJar.toURI()); // The only thing in the container classpath is the launcher.jar // The MapReduceContainerLauncher inside the launcher.jar will creates a MapReduceClassLoader and launch // the actual MapReduce AM/Task from that // We explicitly localize the mr-framwork, but not use it with the classpath URI frameworkURI = MapReduceContainerHelper.getFrameworkURI(mapredConf); if (frameworkURI != null) { job.addCacheArchive(frameworkURI); } mapredConf.unset(MRJobConfig.MAPREDUCE_APPLICATION_FRAMEWORK_PATH); mapredConf.set(MRJobConfig.MAPREDUCE_APPLICATION_CLASSPATH, launcherJar.getName()); mapredConf.set(YarnConfiguration.YARN_APPLICATION_CLASSPATH, launcherJar.getName()); } MapReduceContextConfig contextConfig = new MapReduceContextConfig(mapredConf); // We start long-running tx to be used by mapreduce job tasks. Transaction tx = txClient.startLong(); try { // We remember tx, so that we can re-use it in mapreduce tasks CConfiguration cConfCopy = cConf; contextConfig.set(context, cConfCopy, tx, programJar.toURI(), localizedUserResources); LOG.info("Submitting MapReduce Job: {}", context); // submits job and returns immediately. Shouldn't need to set context ClassLoader. job.submit(); this.job = job; this.transaction = tx; } catch (Throwable t) { Transactions.invalidateQuietly(txClient, tx); throw t; } } catch (Throwable t) { LOG.error("Exception when submitting MapReduce Job: {}", context, t); cleanupTask.run(); throw t; } }
From source file:co.cask.cdap.internal.app.runtime.batch.MapReduceRuntimeService.java
License:Apache License
/** * Localizes resources requested by users in the MapReduce Program's beforeSubmit phase. * In Local mode, also copies resources to a temporary directory. * * @param job the {@link Job} for this MapReduce program * @param targetDir in local mode, a temporary directory to copy the resources to * @return a {@link Map} of resource name to the resource path. The resource path will be absolute in local mode, * while it will just contain the file name in distributed mode. *//* w w w . j a va2 s . co m*/ private Map<String, String> localizeUserResources(Job job, File targetDir) throws IOException { Map<String, String> localizedResources = new HashMap<>(); Map<String, LocalizeResource> resourcesToLocalize = context.getResourcesToLocalize(); for (Map.Entry<String, LocalizeResource> entry : resourcesToLocalize.entrySet()) { String localizedFilePath; String name = entry.getKey(); Configuration mapredConf = job.getConfiguration(); if (MapReduceTaskContextProvider.isLocal(mapredConf)) { // in local mode, also add localize resources in a temporary directory localizedFilePath = LocalizationUtils.localizeResource(entry.getKey(), entry.getValue(), targetDir) .getAbsolutePath(); } else { URI uri = entry.getValue().getURI(); // in distributed mode, use the MapReduce Job object to localize resources URI actualURI; try { actualURI = new URI(uri.getScheme(), uri.getAuthority(), uri.getPath(), uri.getQuery(), name); } catch (URISyntaxException e) { // Most of the URI is constructed from the passed URI. So ideally, this should not happen. // If it does though, there is nothing that clients can do to recover, so not propagating a checked exception. throw Throwables.propagate(e); } if (entry.getValue().isArchive()) { job.addCacheArchive(actualURI); } else { job.addCacheFile(actualURI); } localizedFilePath = name; } localizedResources.put(name, localizedFilePath); } return localizedResources; }
From source file:com.airline.analytics.AirlineUniqueRoutesAnalytics.java
@Override public int run(String[] strings) throws Exception { Job job = Job.getInstance(getConf(), "Hadoop Airline Orign Destination Analytics"); job.setJarByClass(getClass());//from w w w . j a v a2 s . com // Distributed Cache job.addCacheFile(new URI("/airline/codes.csv")); job.setMapperClass(AirlineMapper.class); // job.setCombinerClass(AirlineReducer.class); job.setReducerClass(AirlineReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(strings[0])); FileOutputFormat.setOutputPath(job, new Path(strings[1])); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.aliyun.emr.example.WordCount.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); GenericOptionsParser optionParser = new GenericOptionsParser(conf, args); String[] remainingArgs = optionParser.getRemainingArgs(); if (!(remainingArgs.length == 2 || remainingArgs.length == 4)) { System.err.println("Usage: wordcount <in> <out> [-skip skipPatternFile]"); System.exit(2);// ww w . j a v a 2 s . c o m } Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); List<String> otherArgs = new ArrayList<String>(); for (int i = 0; i < remainingArgs.length; ++i) { if ("-skip".equals(remainingArgs[i])) { job.addCacheFile(new Path(EMapReduceOSSUtil.buildOSSCompleteUri(remainingArgs[++i], conf)).toUri()); job.getConfiguration().setBoolean("wordcount.skip.patterns", true); } else { otherArgs.add(remainingArgs[i]); } } FileInputFormat.addInputPath(job, new Path(EMapReduceOSSUtil.buildOSSCompleteUri(otherArgs.get(0), conf))); FileOutputFormat.setOutputPath(job, new Path(EMapReduceOSSUtil.buildOSSCompleteUri(otherArgs.get(1), conf))); System.exit(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 www . j a va2 s . com*/ 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.ema.hadoop.wordcount.WordCount_cache.java
public static void main(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: WordCount <input path> <output path>"); System.exit(-1);//ww w . j a v a 2s .c o m } // First we write the stop word list // it could also be a file manually loaded into HDFS String[] stopwords = { "the", "a" }; Configuration configuration = new Configuration(); FileSystem hdfs = FileSystem.get(new URI("hdfs://localhost:9000"), configuration); Path file = new Path("hdfs://localhost:9000/user/student/stop_words.txt"); if (hdfs.exists(file)) { hdfs.delete(file, true); } OutputStream os = hdfs.create(file, new Progressable() { @Override public void progress() { out.println("...bytes written"); } }); BufferedWriter br = new BufferedWriter(new OutputStreamWriter(os, "UTF-8")); for (String w : stopwords) { br.write(w + "\n"); } br.close(); hdfs.close(); Job job = Job.getInstance(); job.addCacheFile(new Path("hdfs://localhost:9000/user/student/stop_words.txt").toUri()); job.setJarByClass(WordCount_cache.class); job.setJobName("Word count job"); FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(WCMapper_cache.class); job.setReducerClass(WCReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.lakhani.anchorgraph.anchorgraph.java
public int run(String[] args) throws Exception { Configuration conf = new Configuration(); //DistributedCache.addCacheFile(new URI("hdfs://zphdc1n1:8020/user/clakhani/anchorgraph/centroids.txt"), conf); conf.set("numberCentroids", args[3]); conf.set("numberFeatures", args[4]); Job job = new Job(conf, "anchorgraph"); job.addCacheFile(new URI(args[2])); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(Map.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[2])); job.setJarByClass(anchorgraph.class); job.submit();// www.j a va 2 s . c o m int rc = (job.waitForCompletion(true)) ? 1 : 0; return rc; }