List of usage examples for org.apache.hadoop.fs Path toUri
public URI toUri()
From source file:com.elex.dmp.lda.CVB0Driver.java
License:Apache License
private static int getCurrentIterationNumber(Configuration config, Path modelTempDir, int maxIterations) throws IOException { FileSystem fs = FileSystem.get(modelTempDir.toUri(), config); int iterationNumber = 1; Path iterationPath = modelPath(modelTempDir, iterationNumber); while (fs.exists(iterationPath) && iterationNumber <= maxIterations) { log.info("Found previous state: " + iterationPath); iterationNumber++;/* w w w . j av a 2 s . co m*/ iterationPath = modelPath(modelTempDir, iterationNumber); } return iterationNumber - 1; }
From source file:com.elex.dmp.lda.CVB0Driver.java
License:Apache License
private static void setModelPaths(Job job, Path modelPath) throws IOException { Configuration conf = job.getConfiguration(); if (modelPath == null || !FileSystem.get(modelPath.toUri(), conf).exists(modelPath)) { return;//w ww .ja v a 2 s.co m } FileStatus[] statuses = FileSystem.get(modelPath.toUri(), conf).listStatus(modelPath, PathFilters.partFilter()); Preconditions.checkState(statuses.length > 0, "No part files found in model path '%s'", modelPath.toString()); String[] modelPaths = new String[statuses.length]; for (int i = 0; i < statuses.length; i++) { modelPaths[i] = statuses[i].getPath().toUri().toString(); } conf.setStrings(MODEL_PATHS, modelPaths); }
From source file:com.elex.dmp.vectorizer.DictionaryVectorizer.java
License:Apache License
/** * Read the feature frequency List which is built at the end of the Word Count Job and assign ids to them. * This will use constant memory and will run at the speed of your disk read *///from ww w. ja v a2 s . c o m private static List<Path> createDictionaryChunks(Path wordCountPath, Path dictionaryPathBase, Configuration baseConf, int chunkSizeInMegabytes, int[] maxTermDimension) throws IOException { List<Path> chunkPaths = Lists.newArrayList(); Configuration conf = new Configuration(baseConf); FileSystem fs = FileSystem.get(wordCountPath.toUri(), conf); long chunkSizeLimit = chunkSizeInMegabytes * 1024L * 1024L; int chunkIndex = 0; Path chunkPath = new Path(dictionaryPathBase, DICTIONARY_FILE + chunkIndex); chunkPaths.add(chunkPath); SequenceFile.Writer dictWriter = new SequenceFile.Writer(fs, conf, chunkPath, Text.class, IntWritable.class); try { long currentChunkSize = 0; Path filesPattern = new Path(wordCountPath, OUTPUT_FILES_PATTERN); int i = 0; for (Pair<Writable, Writable> record : new SequenceFileDirIterable<Writable, Writable>(filesPattern, PathType.GLOB, null, null, true, conf)) { if (currentChunkSize > chunkSizeLimit) { Closeables.closeQuietly(dictWriter); chunkIndex++; chunkPath = new Path(dictionaryPathBase, DICTIONARY_FILE + chunkIndex); chunkPaths.add(chunkPath); dictWriter = new SequenceFile.Writer(fs, conf, chunkPath, Text.class, IntWritable.class); currentChunkSize = 0; } Writable key = record.getFirst(); int fieldSize = DICTIONARY_BYTE_OVERHEAD + key.toString().length() * 2 + Integer.SIZE / 8; currentChunkSize += fieldSize; dictWriter.append(key, new IntWritable(i++)); } maxTermDimension[0] = i; } finally { Closeables.closeQuietly(dictWriter); } return chunkPaths; }
From source file:com.elex.dmp.vectorizer.DictionaryVectorizer.java
License:Apache License
/** * Create a partial vector using a chunk of features from the input documents. The input documents has to be * in the {@link SequenceFile} format/* w w w. j a va 2 s . com*/ * * @param input * input directory of the documents in {@link SequenceFile} format * @param baseConf * job configuration * @param maxNGramSize * maximum size of ngrams to generate * @param dictionaryFilePath * location of the chunk of features and the id's * @param output * output directory were the partial vectors have to be created * @param dimension * @param sequentialAccess * output vectors should be optimized for sequential access * @param namedVectors * output vectors should be named, retaining key (doc id) as a label * @param numReducers * the desired number of reducer tasks */ private static void makePartialVectors(Path input, Configuration baseConf, int maxNGramSize, Path dictionaryFilePath, Path output, int dimension, boolean sequentialAccess, boolean namedVectors, int numReducers) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(baseConf); // this conf parameter needs to be set enable serialisation of conf values conf.set("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization," + "org.apache.hadoop.io.serializer.WritableSerialization"); conf.setInt(PartialVectorMerger.DIMENSION, dimension); conf.setBoolean(PartialVectorMerger.SEQUENTIAL_ACCESS, sequentialAccess); conf.setBoolean(PartialVectorMerger.NAMED_VECTOR, namedVectors); conf.setInt(MAX_NGRAMS, maxNGramSize); DistributedCache.setCacheFiles(new URI[] { dictionaryFilePath.toUri() }, conf); Job job = new Job(conf); job.setJobName("DictionaryVectorizer::MakePartialVectors: input-folder: " + input + ", dictionary-file: " + dictionaryFilePath); job.setJarByClass(DictionaryVectorizer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(StringTuple.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(VectorWritable.class); FileInputFormat.setInputPaths(job, input); FileOutputFormat.setOutputPath(job, output); job.setMapperClass(Mapper.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setReducerClass(TFPartialVectorReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setNumReduceTasks(numReducers); HadoopUtil.delete(conf, output); boolean succeeded = job.waitForCompletion(true); if (!succeeded) throw new IllegalStateException("Job failed!"); }
From source file:com.elex.dmp.vectorizer.FixDictionaryVectorizer.java
License:Apache License
/** * Read the feature frequency List which is built at the end of the Word Count Job and assign ids to them. * This will use constant memory and will run at the speed of your disk read */// w ww . java 2 s .c o m private static List<Path> createDictionaryChunks(Path dictPath, Path dictionaryPathBase, Configuration baseConf, int chunkSizeInMegabytes, int[] maxTermDimension) throws IOException { List<Path> chunkPaths = Lists.newArrayList(); Configuration conf = new Configuration(baseConf); FileSystem fs = FileSystem.get(dictPath.toUri(), conf); FileStatus[] dictFiles = fs.listStatus(dictPath, new PathFilter() { @Override public boolean accept(Path path) { String name = path.getName(); return name.startsWith("dictionary.") && !name.endsWith(".crc"); } }); for (int i = 0; i < dictFiles.length; i++) { chunkPaths.add(dictFiles[i].getPath()); } return chunkPaths; }
From source file:com.elex.dmp.vectorizer.FixDictionaryVectorizer.java
License:Apache License
/** * Create a partial vector using a chunk of features from the input documents. The input documents has to be * in the {@link SequenceFile} format/*from w w w . j a va2s. co m*/ * * @param input * input directory of the documents in {@link SequenceFile} format * @param baseConf * job configuration * @param maxNGramSize * maximum size of ngrams to generate * @param dictionaryFilePath * location of the chunk of features and the id's * @param output * output directory were the partial vectors have to be created * @param dimension * @param sequentialAccess * output vectors should be optimized for sequential access * @param namedVectors * output vectors should be named, retaining key (doc id) as a label * @param numReducers * the desired number of reducer tasks */ private static void makePartialVectors(Path input, Configuration baseConf, int maxNGramSize, Path dictionaryFilePath, Path output, int dimension, boolean sequentialAccess, boolean namedVectors, int numReducers) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(baseConf); // this conf parameter needs to be set enable serialisation of conf values conf.set("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization," + "org.apache.hadoop.io.serializer.WritableSerialization"); conf.setInt(PartialVectorMerger.DIMENSION, dimension); conf.setBoolean(PartialVectorMerger.SEQUENTIAL_ACCESS, sequentialAccess); conf.setBoolean(PartialVectorMerger.NAMED_VECTOR, namedVectors); conf.setInt(MAX_NGRAMS, maxNGramSize); DistributedCache.setCacheFiles(new URI[] { dictionaryFilePath.toUri() }, conf); Job job = new Job(conf); job.setJobName("DictionaryVectorizer::MakePartialVectors: input-folder: " + input + ", dictionary-file: " + dictionaryFilePath); job.setJarByClass(FixDictionaryVectorizer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(StringTuple.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(VectorWritable.class); FileInputFormat.setInputPaths(job, input); FileOutputFormat.setOutputPath(job, output); job.setMapperClass(Mapper.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setReducerClass(TFPartialVectorReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setNumReduceTasks(numReducers); HadoopUtil.delete(conf, output); boolean succeeded = job.waitForCompletion(true); if (!succeeded) throw new IllegalStateException("Job failed!"); }
From source file:com.epam.hadoop.nv.yarn.Client.java
License:Apache License
/** * Main run function for the client/* w w w. j av a2 s. c o m*/ * * @return true if application completed successfully * @throws IOException * @throws YarnException */ public boolean run() throws IOException, YarnException { LOG.info("Running Client"); yarnClient.start(); YarnClusterMetrics clusterMetrics = yarnClient.getYarnClusterMetrics(); LOG.info("Got Cluster metric info from ASM" + ", numNodeManagers=" + clusterMetrics.getNumNodeManagers()); List<NodeReport> clusterNodeReports = yarnClient.getNodeReports(NodeState.RUNNING); LOG.info("Got Cluster node info from ASM"); for (NodeReport node : clusterNodeReports) { LOG.info("Got node report from ASM for" + ", nodeId=" + node.getNodeId() + ", nodeAddress" + node.getHttpAddress() + ", nodeRackName" + node.getRackName() + ", nodeNumContainers" + node.getNumContainers()); } QueueInfo queueInfo = yarnClient.getQueueInfo(this.amQueue); LOG.info("Queue info" + ", queueName=" + queueInfo.getQueueName() + ", queueCurrentCapacity=" + queueInfo.getCurrentCapacity() + ", queueMaxCapacity=" + queueInfo.getMaximumCapacity() + ", queueApplicationCount=" + queueInfo.getApplications().size() + ", queueChildQueueCount=" + queueInfo.getChildQueues().size()); List<QueueUserACLInfo> listAclInfo = yarnClient.getQueueAclsInfo(); for (QueueUserACLInfo aclInfo : listAclInfo) { for (QueueACL userAcl : aclInfo.getUserAcls()) { LOG.info("User ACL Info for Queue" + ", queueName=" + aclInfo.getQueueName() + ", userAcl=" + userAcl.name()); } } // Get a new application id YarnClientApplication app = yarnClient.createApplication(); GetNewApplicationResponse appResponse = app.getNewApplicationResponse(); // TODO get min/max resource capabilities from RM and change memory ask // if needed // If we do not have min/max, we may not be able to correctly request // the required resources from the RM for the app master // Memory ask has to be a multiple of min and less than max. // Dump out information about cluster capability as seen by the resource // manager int maxMem = appResponse.getMaximumResourceCapability().getMemory(); LOG.info("Max mem capabililty of resources in this cluster " + maxMem); // A resource ask cannot exceed the max. if (amMemory > maxMem) { LOG.info("AM memory specified above max threshold of cluster. Using max value." + ", specified=" + amMemory + ", max=" + maxMem); amMemory = maxMem; } int maxVCores = appResponse.getMaximumResourceCapability().getVirtualCores(); LOG.info("Max virtual cores capabililty of resources in this cluster " + maxVCores); if (amVCores > maxVCores) { LOG.info("AM virtual cores specified above max threshold of cluster. " + "Using max value." + ", specified=" + amVCores + ", max=" + maxVCores); amVCores = maxVCores; } // set the application name ApplicationSubmissionContext appContext = app.getApplicationSubmissionContext(); ApplicationId appId = appContext.getApplicationId(); appContext.setKeepContainersAcrossApplicationAttempts(keepContainers); appContext.setApplicationName(appName); // set local resources for the application master // local files or archives as needed // In this scenario, the jar file for the application master is part of // the local resources Map<String, LocalResource> localResources = new HashMap<String, LocalResource>(); LOG.info("Copy App Master jar from local filesystem and add to local environment"); // Copy the application master jar to the filesystem // Create a local resource to point to the destination jar path FileSystem fs = FileSystem.get(conf); addToLocalResources(fs, appMasterJar, appMasterJarPath, appId.toString(), localResources, null); // Set the log4j properties if needed if (!log4jPropFile.isEmpty()) { addToLocalResources(fs, log4jPropFile, log4jPath, appId.toString(), localResources, null); } // The shell script has to be made available on the final container(s) // where it will be executed. // To do this, we need to first copy into the filesystem that is visible // to the yarn framework. // We do not need to set this as a local resource for the application // master as the application master does not need it. String hdfsShellScriptLocation = ""; long hdfsShellScriptLen = 0; long hdfsShellScriptTimestamp = 0; if (!shellScriptPath.isEmpty()) { Path shellSrc = new Path(shellScriptPath); String shellPathSuffix = appName + "/" + appId.toString() + "/" + SCRIPT_PATH; Path shellDst = new Path(fs.getHomeDirectory(), shellPathSuffix); fs.copyFromLocalFile(false, true, shellSrc, shellDst); hdfsShellScriptLocation = shellDst.toUri().toString(); FileStatus shellFileStatus = fs.getFileStatus(shellDst); hdfsShellScriptLen = shellFileStatus.getLen(); hdfsShellScriptTimestamp = shellFileStatus.getModificationTime(); } if (!shellCommand.isEmpty()) { addToLocalResources(fs, null, shellCommandPath, appId.toString(), localResources, shellCommand); } if (shellArgs.length > 0) { addToLocalResources(fs, null, shellArgsPath, appId.toString(), localResources, StringUtils.join(shellArgs, " ")); } // Set the necessary security tokens as needed // amContainer.setContainerTokens(containerToken); // Set the env variables to be setup in the env where the application // master will be run LOG.info("Set the environment for the application master"); Map<String, String> env = new HashMap<String, String>(); // put location of shell script into env // using the env info, the application master will create the correct // local resource for the // eventual containers that will be launched to execute the shell // scripts env.put(DSConstants.DISTRIBUTEDSHELLSCRIPTLOCATION, hdfsShellScriptLocation); env.put(DSConstants.DISTRIBUTEDSHELLSCRIPTTIMESTAMP, Long.toString(hdfsShellScriptTimestamp)); env.put(DSConstants.DISTRIBUTEDSHELLSCRIPTLEN, Long.toString(hdfsShellScriptLen)); // Add AppMaster.jar location to classpath // At some point we should not be required to add // the hadoop specific classpaths to the env. // It should be provided out of the box. // For now setting all required classpaths including // the classpath to "." for the application jar StringBuilder classPathEnv = new StringBuilder(Environment.CLASSPATH.$$()) .append(ApplicationConstants.CLASS_PATH_SEPARATOR).append("./*"); for (String c : conf.getStrings(YarnConfiguration.YARN_APPLICATION_CLASSPATH, YarnConfiguration.DEFAULT_YARN_CROSS_PLATFORM_APPLICATION_CLASSPATH)) { classPathEnv.append(ApplicationConstants.CLASS_PATH_SEPARATOR); classPathEnv.append(c.trim()); } classPathEnv.append(ApplicationConstants.CLASS_PATH_SEPARATOR).append("./log4j.properties"); // add the runtime classpath needed for tests to work if (conf.getBoolean(YarnConfiguration.IS_MINI_YARN_CLUSTER, false)) { classPathEnv.append(':'); classPathEnv.append(System.getProperty("java.class.path")); } env.put("CLASSPATH", classPathEnv.toString()); // Set the necessary command to execute the application master Vector<CharSequence> vargs = new Vector<CharSequence>(30); // Set java executable command LOG.info("Setting up app master command"); vargs.add(Environment.JAVA_HOME.$$() + "/bin/java"); // Set Xmx based on am memory size vargs.add("-Xmx" + amMemory + "m"); // Set class name vargs.add(appMasterMainClass); // Set params for Application Master vargs.add("--container_memory " + String.valueOf(containerMemory)); vargs.add("--container_vcores " + String.valueOf(containerVirtualCores)); vargs.add("--num_containers " + String.valueOf(numContainers)); vargs.add("--priority " + String.valueOf(shellCmdPriority)); for (Map.Entry<String, String> entry : shellEnv.entrySet()) { vargs.add("--shell_env " + entry.getKey() + "=" + entry.getValue()); } if (debugFlag) { vargs.add("--debug"); } vargs.add("1>" + ApplicationConstants.LOG_DIR_EXPANSION_VAR + "/AppMaster.stdout"); vargs.add("2>" + ApplicationConstants.LOG_DIR_EXPANSION_VAR + "/AppMaster.stderr"); // Get final commmand StringBuilder command = new StringBuilder(); for (CharSequence str : vargs) { command.append(str).append(" "); } LOG.info("Completed setting up app master command " + command.toString()); List<String> commands = new ArrayList<String>(); commands.add(command.toString()); // Set up the container launch context for the application master ContainerLaunchContext amContainer = ContainerLaunchContext.newInstance(localResources, env, commands, null, null, null); // Set up resource type requirements // For now, both memory and vcores are supported, so we set memory and // vcores requirements Resource capability = Resource.newInstance(amMemory, amVCores); appContext.setResource(capability); // Service data is a binary blob that can be passed to the application // Not needed in this scenario // amContainer.setServiceData(serviceData); // Setup security tokens if (UserGroupInformation.isSecurityEnabled()) { // Note: Credentials class is marked as LimitedPrivate for HDFS and // MapReduce Credentials credentials = new Credentials(); String tokenRenewer = conf.get(YarnConfiguration.RM_PRINCIPAL); if (tokenRenewer == null || tokenRenewer.length() == 0) { throw new IOException("Can't get Master Kerberos principal for the RM to use as renewer"); } // For now, only getting tokens for the default file-system. final Token<?> tokens[] = fs.addDelegationTokens(tokenRenewer, credentials); if (tokens != null) { for (Token<?> token : tokens) { LOG.info("Got dt for " + fs.getUri() + "; " + token); } } DataOutputBuffer dob = new DataOutputBuffer(); credentials.writeTokenStorageToStream(dob); ByteBuffer fsTokens = ByteBuffer.wrap(dob.getData(), 0, dob.getLength()); amContainer.setTokens(fsTokens); } appContext.setAMContainerSpec(amContainer); // Set the priority for the application master // TODO - what is the range for priority? how to decide? Priority pri = Priority.newInstance(amPriority); appContext.setPriority(pri); // Set the queue to which this application is to be submitted in the RM appContext.setQueue(amQueue); // Submit the application to the applications manager // SubmitApplicationResponse submitResp = // applicationsManager.submitApplication(appRequest); // Ignore the response as either a valid response object is returned on // success // or an exception thrown to denote some form of a failure LOG.info("Submitting application to ASM"); yarnClient.submitApplication(appContext); // TODO // Try submitting the same request again // app submission failure? // Monitor the application return monitorApplication(appId); }
From source file:com.epam.hadoop.nv.yarn.Client.java
License:Apache License
private void addToLocalResources(FileSystem fs, String fileSrcPath, String fileDstPath, String appId, Map<String, LocalResource> localResources, String resources) throws IOException { String suffix = appName + "/" + appId + "/" + fileDstPath; Path dst = new Path(fs.getHomeDirectory(), suffix); if (fileSrcPath == null) { FSDataOutputStream ostream = null; try {//from www.j av a 2 s . co m ostream = FileSystem.create(fs, dst, new FsPermission((short) 0710)); ostream.writeUTF(resources); } finally { IOUtils.closeQuietly(ostream); } } else { fs.copyFromLocalFile(new Path(fileSrcPath), dst); } FileStatus scFileStatus = fs.getFileStatus(dst); LocalResource scRsrc = LocalResource.newInstance(ConverterUtils.getYarnUrlFromURI(dst.toUri()), LocalResourceType.FILE, LocalResourceVisibility.APPLICATION, scFileStatus.getLen(), scFileStatus.getModificationTime()); localResources.put(fileDstPath, scRsrc); }
From source file:com.facebook.hiveio.common.FileSystems.java
License:Apache License
/** * Get path to file from source directory in a target directory. * Computes relative path of file in source and adds that to destination. * * @param file path to file//w ww. jav a 2 s . c o m * @param srcDir path to source directory * @param destDir path to target directory * @return path of file in destination */ public static Path pathInDestination(Path file, Path srcDir, Path destDir) { URI fileUri = file.toUri(); URI relativeUri = srcDir.toUri().relativize(fileUri); if (relativeUri == fileUri) { throw new IllegalArgumentException("Could not get file " + file + " relative path in " + srcDir); } String relativePath = relativeUri.getPath(); if (relativePath.isEmpty()) { return destDir; } else { return new Path(destDir, relativePath); } }
From source file:com.facebook.presto.hive.HdfsEnvironment.java
License:Apache License
public Configuration getConfiguration(Path path) { URI uri = path.toUri(); if ("file".equals(uri.getScheme())) { return new Configuration(); }//from w w w .j a v a 2s . c o m String host = uri.getHost(); checkArgument(host != null, "path host is null: %s", path); return hdfsConfiguration.getConfiguration(host); }