List of usage examples for org.apache.hadoop.fs FileSystem getUri
public abstract URI getUri();
From source file:io.hops.tensorflow.Client.java
License:Apache License
private ContainerLaunchContext createContainerLaunchContext(GetNewApplicationResponse appResponse) throws IOException { FileSystem fs = FileSystem.get(conf); ApplicationId appId = appResponse.getApplicationId(); DistributedCacheList dcl = populateDistributedCache(fs, appId); Map<String, LocalResource> localResources = prepareLocalResources(fs, appId, dcl); Map<String, String> launchEnv = setupLaunchEnv(); // Set the executable command for the application master Vector<CharSequence> vargs = new Vector<>(30); LOG.info("Setting up app master command"); vargs.add(Environment.JAVA_HOME.$$() + "/bin/java"); vargs.add("-Xmx" + amMemory + "m"); vargs.add(appMasterMainClass);/* ww w . j a v a2 s . c om*/ if (python != null) { vargs.add(newArg(PYTHON, python)); } vargs.add(newArg(MEMORY, String.valueOf(memory))); vargs.add(newArg(VCORES, String.valueOf(vcores))); vargs.add(newArg(GPUS, String.valueOf(gpus))); if (protocol != null) { vargs.add(newArg(PROTOCOL, protocol)); } // vargs.add(newArg(PRIORITY, String.valueOf(priority))); vargs.add(newArg(ALLOCATION_TIMEOUT, String.valueOf(allocationTimeout / 1000))); vargs.add(newArg(ApplicationMasterArguments.MAIN_RELATIVE, mainRelativePath)); if (arguments != null) { vargs.add(newArg(ARGS, StringUtils.join(arguments, " "))); } vargs.add(newArg(WORKERS, Integer.toString(numWorkers))); vargs.add(newArg(PSES, Integer.toString(numPses))); for (Map.Entry<String, String> entry : environment.entrySet()) { vargs.add(newArg(ENV, entry.getKey() + "=" + entry.getValue())); } if (tensorboard) { vargs.add("--" + TENSORBOARD); } if (debugFlag) { vargs.add("--" + DEBUG); } // Add log redirect params vargs.add("1>" + ApplicationConstants.LOG_DIR_EXPANSION_VAR + "/AppMaster.stdout"); vargs.add("2>" + ApplicationConstants.LOG_DIR_EXPANSION_VAR + "/AppMaster.stderr"); // Get final command 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<>(); commands.add(command.toString()); // Set up the container launch context for the application master ContainerLaunchContext amContainer = ContainerLaunchContext.newInstance(localResources, launchEnv, commands, null, null, null); // Setup security tokens if (UserGroupInformation.isSecurityEnabled()) { 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); } return amContainer; }
From source file:it.crs4.seal.read_sort.MergeAlignments.java
License:Open Source License
private void loadAnnotations() throws IOException { FileSystem fs = annotationPath.getFileSystem(getConf()); log.info("Reading reference annotations from " + annotationPath); try {//from w w w.ja v a 2s . c o m FSDataInputStream in = fs.open(annotationPath); refAnnotation = new BwaRefAnnotation(new InputStreamReader(in)); } catch (IOException e) { log.fatal("Can't read annotation file " + annotationPath + " on filesystem " + fs.getUri()); throw e; } }
From source file:me.haosdent.noya.Client.java
License:Apache License
/** * Main run function for the client/*from w ww .j a v a2s . co m*/ * * @return true if application completed successfully * * @throws java.io.IOException * @throws org.apache.hadoop.yarn.exceptions.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 up the container launch context for the application master ContainerLaunchContext amContainer = Records.newRecord(ContainerLaunchContext.class); // 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 local resource info into app master container launch context amContainer.setLocalResources(localResources); // 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(ApplicationConstants.Environment.CLASSPATH.$$()) .append(ApplicationConstants.CLASS_PATH_SEPARATOR).append("./*"); for (String c : conf.getStrings(YarnConfiguration.YARN_APPLICATION_CLASSPATH, ApplicationConstants.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()); amContainer.setEnvironment(env); // 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(ApplicationConstants.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()); commands.add("echo 'hello' >/tmp/yarn_test"); amContainer.setCommands(commands); // Set up resource type requirements // For now, both memory and vcores are supported, so we set memory and // vcores requirements Resource capability = Records.newRecord(Resource.class); capability.setMemory(amMemory); capability.setVirtualCores(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()) { 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 Priority pri = Records.newRecord(Priority.class); // TODO - what is the range for priority? how to decide? pri.setPriority(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:ml.shifu.guagua.yarn.GuaguaYarnClient.java
License:Apache License
/** * Set delegation tokens for AM container * //from ww w . j a va2 s.c o m * @param amContainer * AM container */ private void setToken(ContainerLaunchContext amContainer) throws IOException { // Setup security tokens if (UserGroupInformation.isSecurityEnabled()) { Credentials credentials = new Credentials(); String tokenRenewer = getConf().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"); } FileSystem fs = FileSystem.get(getConf()); // 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); } }
From source file:nl.basjes.hadoop.io.compress.TestSplittableCodecSeams.java
License:Apache License
/** * Write the specified number of records to file in test dir using codec. * Records are simply lines random ASCII *///from w w w. ja v a2 s.com private static Path writeSplitTestFile(final Configuration conf, final Class<? extends SplittableCompressionCodec> codecClass, final long records, final int recordLength, final int trailingSizeJitter, final int randomizeEveryNChars) throws IOException { RAND.setSeed(1); // Make the tests better reproducable final FileSystem fs = FileSystem.getLocal(conf); final SplittableCompressionCodec codec = ReflectionUtils.newInstance(codecClass, conf); final Path wd = new Path(new Path(System.getProperty("test.build.data", "/tmp")).makeQualified(fs.getUri(), fs.getWorkingDirectory()), codec.getClass().getSimpleName()); final Path file = new Path(wd, "test-" + records + "-" + recordLength + "-" + trailingSizeJitter + codec.getDefaultExtension()); DataOutputStream out = null; final Compressor cmp = CodecPool.getCompressor(codec); try { out = new DataOutputStream(codec.createOutputStream(fs.create(file, true), cmp)); for (long seq = 1; seq <= records; ++seq) { final String line = randomGibberish( recordLength + (trailingSizeJitter > 0 ? RAND.nextInt(trailingSizeJitter) : 0), randomizeEveryNChars) + "\n"; // There must be a simpler way to output ACSII instead of 2 byte UNICODE out.writeBytes(new String(line.getBytes("UTF-8"), "US-ASCII")); } } finally { IOUtils.cleanup(LOG, out); CodecPool.returnCompressor(cmp); } return file; }
From source file:org.apache.accumulo.core.file.rfile.PrintInfo.java
License:Apache License
@Override public void execute(final String[] args) throws Exception { Opts opts = new Opts(); opts.parseArgs(PrintInfo.class.getName(), args); if (opts.files.isEmpty()) { System.err.println("No files were given"); System.exit(-1);//from w w w . ja v a 2s. c o m } Configuration conf = new Configuration(); for (String confFile : opts.configFiles) { log.debug("Adding Hadoop configuration file " + confFile); conf.addResource(new Path(confFile)); } FileSystem hadoopFs = FileSystem.get(conf); FileSystem localFs = FileSystem.getLocal(conf); LogHistogram kvHistogram = new LogHistogram(); KeyStats dataKeyStats = new KeyStats(); KeyStats indexKeyStats = new KeyStats(); for (String arg : opts.files) { Path path = new Path(arg); FileSystem fs; if (arg.contains(":")) fs = path.getFileSystem(conf); else { log.warn("Attempting to find file across filesystems. Consider providing URI instead of path"); fs = hadoopFs.exists(path) ? hadoopFs : localFs; // fall back to local } System.out.println( "Reading file: " + path.makeQualified(fs.getUri(), fs.getWorkingDirectory()).toString()); CachableBlockFile.Reader _rdr = new CachableBlockFile.Reader(fs, path, conf, null, null, SiteConfiguration.getInstance(DefaultConfiguration.getInstance())); Reader iter = new RFile.Reader(_rdr); MetricsGatherer<Map<String, ArrayList<VisibilityMetric>>> vmg = new VisMetricsGatherer(); if (opts.vis || opts.hash) iter.registerMetrics(vmg); iter.printInfo(); System.out.println(); org.apache.accumulo.core.file.rfile.bcfile.PrintInfo.main(new String[] { arg }); Map<String, ArrayList<ByteSequence>> localityGroupCF = null; if (opts.histogram || opts.dump || opts.vis || opts.hash || opts.keyStats) { localityGroupCF = iter.getLocalityGroupCF(); FileSKVIterator dataIter; if (opts.useSample) { dataIter = iter.getSample(); if (dataIter == null) { System.out.println("ERROR : This rfile has no sample data"); return; } } else { dataIter = iter; } if (opts.keyStats) { FileSKVIterator indexIter = iter.getIndex(); while (indexIter.hasTop()) { indexKeyStats.add(indexIter.getTopKey()); indexIter.next(); } } for (Entry<String, ArrayList<ByteSequence>> cf : localityGroupCF.entrySet()) { dataIter.seek(new Range((Key) null, (Key) null), cf.getValue(), true); while (dataIter.hasTop()) { Key key = dataIter.getTopKey(); Value value = dataIter.getTopValue(); if (opts.dump) { System.out.println(key + " -> " + value); if (System.out.checkError()) return; } if (opts.histogram) { kvHistogram.add(key.getSize() + value.getSize()); } if (opts.keyStats) { dataKeyStats.add(key); } dataIter.next(); } } } iter.close(); if (opts.vis || opts.hash) { System.out.println(); vmg.printMetrics(opts.hash, "Visibility", System.out); } if (opts.histogram) { System.out.println(); kvHistogram.print(""); } if (opts.keyStats) { System.out.println(); System.out.println("Statistics for keys in data :"); dataKeyStats.print("\t"); System.out.println(); System.out.println("Statistics for keys in index :"); indexKeyStats.print("\t"); } // If the output stream has closed, there is no reason to keep going. if (System.out.checkError()) return; } }
From source file:org.apache.accumulo.core.volume.VolumeImpl.java
License:Apache License
/** * Test whether the provided {@link FileSystem} object reference the same actual filesystem as the member <code>fs</code>. * * @param other/*from ww w .ja va2s . c om*/ * The filesystem to compare */ boolean equivalentFileSystems(FileSystem other) { return fs.getUri().equals(other.getUri()); }
From source file:org.apache.accumulo.core.volume.VolumeImplTest.java
License:Apache License
@Test public void testFileSystemInequivalence() { FileSystem fs = createMock(FileSystem.class), other = createMock(FileSystem.class); String basePath = "/accumulo"; VolumeImpl volume = new VolumeImpl(fs, basePath); expect(fs.getUri()).andReturn(URI.create("hdfs://localhost:8020")).anyTimes(); expect(other.getUri()).andReturn(URI.create("hdfs://otherhost:8020")).anyTimes(); replay(fs, other);//from w w w.j a v a 2 s . c om assertFalse(volume.equivalentFileSystems(other)); verify(fs, other); }
From source file:org.apache.accumulo.core.volume.VolumeImplTest.java
License:Apache License
@Test public void testFileSystemEquivalence() { FileSystem fs = createMock(FileSystem.class), other = createMock(FileSystem.class); String basePath = "/accumulo"; VolumeImpl volume = new VolumeImpl(fs, basePath); expect(fs.getUri()).andReturn(URI.create("hdfs://myhost:8020")).anyTimes(); expect(other.getUri()).andReturn(URI.create("hdfs://myhost:8020")).anyTimes(); replay(fs, other);//w w w . j a va 2 s.c om assertTrue(volume.equivalentFileSystems(other)); verify(fs, other); }
From source file:org.apache.accumulo.server.fs.VolumeManagerImpl.java
License:Apache License
@Override public Volume getVolumeByPath(Path path) { if (path.toString().contains(":")) { try {// w w w . j av a 2s .c om FileSystem desiredFs = path.getFileSystem(CachedConfiguration.getInstance()); URI desiredFsUri = desiredFs.getUri(); Collection<Volume> candidateVolumes = volumesByFileSystemUri.get(desiredFsUri); if (null != candidateVolumes) { for (Volume candidateVolume : candidateVolumes) { if (candidateVolume.isValidPath(path)) { return candidateVolume; } } } else { log.debug("Could not determine volume for Path: " + path); } return new NonConfiguredVolume(desiredFs); } catch (IOException ex) { throw new RuntimeException(ex); } } return defaultVolume; }