List of usage examples for org.apache.hadoop.fs FileSystem getUri
public abstract URI getUri();
From source file:com.asakusafw.windgate.hadoopfs.ssh.WindGateHadoopDelete.java
License:Apache License
void doDelete(List<Path> paths, FileList.Writer drain) throws IOException { assert paths != null; assert drain != null; FileSystem fs = FileSystem.get(conf); for (Path path : paths) { WGLOG.info("I22003", fs.getUri(), path); FileStatus[] results = fs.globStatus(path); if (results == null) { continue; }//from ww w .j a va 2 s . c o m for (FileStatus status : results) { doDelete(fs, status, drain); } } }
From source file:com.asakusafw.windgate.hadoopfs.ssh.WindGateHadoopDelete.java
License:Apache License
private void doDelete(FileSystem fs, FileStatus status, FileList.Writer drain) throws IOException { assert fs != null; assert status != null; assert drain != null; WGLOG.info("I22004", fs.getUri(), status.getPath()); try (OutputStream output = drain.openNext(status.getPath())) { String failReason = null; try {/*from ww w.j a v a2 s. c o m*/ boolean deleted; if (RuntimeContext.get().isSimulation()) { deleted = true; } else { deleted = fs.delete(status.getPath(), true); } if (deleted == false) { if (fs.exists(status.getPath())) { WGLOG.warn("W22001", fs.getUri(), status.getPath()); failReason = "Unknown"; } } } catch (IOException e) { WGLOG.warn(e, "W22001", fs.getUri(), status.getPath()); failReason = e.toString(); } if (failReason != null) { output.write(failReason.getBytes(UTF8)); } } }
From source file:com.asakusafw.windgate.hadoopfs.ssh.WindGateHadoopGet.java
License:Apache License
void fetch(FileSystem fs, List<Path> paths, BlockingQueue<Pair> queue) throws IOException, InterruptedException { assert fs != null; assert paths != null; assert queue != null; for (Path path : paths) { boolean found = false; WGLOG.info("I20003", fs.getUri(), path); FileStatus[] results = fs.globStatus(path); if (results != null) { for (FileStatus status : results) { if (FileSystemCompatibility.isDirectory(status)) { continue; }/*ww w. j a va2s . c o m*/ found = true; InputStream in = getInput(fs, status); boolean succeed = false; try { queue.put(new Pair(in, status)); succeed = true; } finally { if (succeed == false) { in.close(); } } } } if (found == false && RuntimeContext.get().isSimulation() == false) { throw new FileNotFoundException(paths.toString()); } } }
From source file:com.asakusafw.windgate.hadoopfs.ssh.WindGateHadoopGet.java
License:Apache License
private void transfer(FileSystem fs, FileStatus status, InputStream input, Writer drain) throws IOException { assert fs != null; assert status != null; assert input != null; assert drain != null; WGLOG.info("I20004", fs.getUri(), status.getPath()); long transferred = 0; try {/*from w w w . j a v a2s. c o m*/ if (RuntimeContext.get().isSimulation() == false) { try (OutputStream output = drain.openNext(status.getPath())) { byte[] buf = new byte[1024]; while (true) { int read = input.read(buf); if (read < 0) { break; } output.write(buf, 0, read); transferred += read; } } } } finally { input.close(); } WGLOG.info("I20005", fs.getUri(), status.getPath(), transferred); }
From source file:com.asakusafw.windgate.hadoopfs.ssh.WindGateHadoopPut.java
License:Apache License
private void doPut(FileSystem fs, Path path, InputStream input) throws IOException { assert fs != null; assert path != null; assert input != null; WGLOG.info("I21003", fs.getUri(), path); long transferred = 0; try (OutputStream output = getOutput(fs, path)) { byte[] buf = new byte[256]; while (true) { int read = input.read(buf); if (read < 0) { break; }//from w w w . ja va 2 s .com output.write(buf, 0, read); transferred += read; } } WGLOG.info("I21004", fs.getUri(), path, transferred); }
From source file:com.asakusafw.windgate.hadoopfs.temporary.FileSystemModelInputProvider.java
License:Apache License
/** * Creates a new instance.//from ww w .j a v a 2s . co m * @param configuration the configuration * @param fileSystem target file system * @param paths source paths * @param dataModelClass target data model class * @throws IOException if failed to resolve paths * @throws IllegalArgumentException if some parameters were {@code null} */ public FileSystemModelInputProvider(final Configuration configuration, final FileSystem fileSystem, final Iterable<Path> paths, final Class<T> dataModelClass) throws IOException { if (configuration == null) { throw new IllegalArgumentException("configuration must not be null"); //$NON-NLS-1$ } if (fileSystem == null) { throw new IllegalArgumentException("fileSystem must not be null"); //$NON-NLS-1$ } if (paths == null) { throw new IllegalArgumentException("paths must not be null"); //$NON-NLS-1$ } if (dataModelClass == null) { throw new IllegalArgumentException("dataModelClass must not be null"); //$NON-NLS-1$ } this.fileSystem = fileSystem; this.queue = new SynchronousQueue<>(); this.executor = Executors.newFixedThreadPool(1, new ThreadFactory() { @Override public Thread newThread(Runnable r) { Thread t = new Thread(r, "HadoopFileCollector"); t.setDaemon(true); return t; } }); this.fetcher = this.executor.submit(new Callable<Void>() { @Override public Void call() throws Exception { for (Path path : paths) { WGLOG.info("I09001", fileSystem.getUri(), paths); FileStatus[] statusList = fileSystem.globStatus(path); if (statusList == null || statusList.length == 0) { throw new FileNotFoundException(MessageFormat.format("File is not found in {1} (fs={0})", fileSystem.getUri(), paths)); } for (FileStatus status : statusList) { WGLOG.info("I09002", fileSystem.getUri(), status.getPath(), status.getLen()); ModelInput<T> input = TemporaryStorage.openInput(configuration, dataModelClass, status.getPath()); boolean succeed = false; try { queue.put(new Entry<>(status, input)); succeed = true; } finally { if (succeed == false) { input.close(); } } } } queue.put(Entry.<T>eof()); return null; } }); }
From source file:com.bigjob.Client.java
License:Apache License
/** * Main run function for the client// w ww . j a va 2s. co 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 (RM)" + ", 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.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 // if (dfsUrl!=null && dfsUrl.equals("")==false){ // conf.set("fs.defaultFS", dfsUrl); // } FileSystem fs = FileSystem.get(conf); addToLocalResources(fs, appMasterJar, appMasterJarPath, appId.getId(), localResources, null); // Set the log4j properties if needed if (!log4jPropFile.isEmpty()) { addToLocalResources(fs, log4jPropFile, log4jPath, appId.getId(), 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.getId() + "/" + (Shell.WINDOWS ? windowBatPath : linuxShellPath); 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.getId(), localResources, shellCommand); } if (shellArgs.length > 0) { addToLocalResources(fs, null, shellArgsPath, appId.getId(), 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(Environment.CLASSPATH.$()).append(File.pathSeparatorChar) .append("./*"); for (String c : conf.getStrings(YarnConfiguration.YARN_APPLICATION_CLASSPATH, YarnConfiguration.DEFAULT_YARN_APPLICATION_CLASSPATH)) { classPathEnv.append(File.pathSeparatorChar); classPathEnv.append(c.trim()); } classPathEnv.append(File.pathSeparatorChar).append("./log4j.properties"); // add the runtime classpath needed for tests to work if (conf.getBoolean(YarnConfiguration.IS_MINI_YARN_CLUSTER, false)) { classPathEnv.append(':'); classPathEnv.append(System.getProperty("java.class.path")); } env.put("CLASSPATH", classPathEnv.toString()); amContainer.setEnvironment(env); // Set the necessary command to execute the application master Vector<CharSequence> vargs = new Vector<CharSequence>(30); // Set java executable command LOG.info("Setting up app master command"); vargs.add(Environment.JAVA_HOME.$() + "/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()); 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); System.out.println("ApplicationId:" + appId); return true; }
From source file:com.cloudera.circus.test.TestXTest.java
License:Open Source License
@Test @TestHadoop/*from ww w . j a v a 2 s .c om*/ public void testHadoopMinicluster() throws Exception { JobConf conf = getHadoopConf(); Assert.assertNotNull(conf); FileSystem fs = FileSystem.get(conf); Assert.assertNotNull(fs); Assert.assertEquals(fs.getUri().getScheme(), "hdfs"); Assert.assertTrue(fs.exists(getHadoopTestDir())); fs.close(); JobClient jobClient = new JobClient(conf); Assert.assertNotNull(jobClient); jobClient.close(); }
From source file:com.cloudera.hoop.client.fs.TestHoopFileSystem.java
License:Open Source License
private void testGet() throws Exception { Configuration conf = new Configuration(); conf.set("fs.http.impl", HoopFileSystem.class.getName()); FileSystem fs = FileSystem.get(getJettyURL().toURI(), conf); Assert.assertNotNull(fs);/*from w w w .ja v a 2 s. c o m*/ Assert.assertEquals(fs.getUri(), getJettyURL().toURI()); fs.close(); }
From source file:com.cloudera.impala.service.JniFrontend.java
License:Apache License
/** * Derive the namenode http address from the current file system, * either default or as set by "-fs" in the generic options. * * @return Returns http address or null if failure. *///from w w w . j av a2 s .c om private String getCurrentNameNodeAddress() throws Exception { // get the filesystem object to verify it is an HDFS system FileSystem fs; fs = FileSystem.get(CONF); if (!(fs instanceof DistributedFileSystem)) { LOG.error("FileSystem is " + fs.getUri()); return null; } return DFSUtil.getInfoServer(HAUtil.getAddressOfActive(fs), CONF, false); }