List of usage examples for org.apache.hadoop.fs FileSystem FS_DEFAULT_NAME_KEY
String FS_DEFAULT_NAME_KEY
To view the source code for org.apache.hadoop.fs FileSystem FS_DEFAULT_NAME_KEY.
Click Source Link
From source file:com.splicemachine.si.testsetup.HBaseSITestEnv.java
License:Apache License
private void startCluster(Configuration conf) throws Exception { int basePort = getNextBasePort(); // -> MapR work-around conf.set(FileSystem.FS_DEFAULT_NAME_KEY, "file:///"); conf.set("fs.default.name", "file:///"); conf.set("fs.hdfs.client", "org.apache.hadoop.hdfs.DistributedFileSystem"); System.setProperty("zookeeper.sasl.client", "false"); System.setProperty("zookeeper.sasl.serverconfig", "fake"); // <- MapR work-around conf.setInt("hbase.master.port", basePort); conf.setInt("hbase.master.info.port", basePort + 1); conf.setInt("hbase.regionserver.port", basePort + 2); conf.setInt("hbase.regionserver.info.port", basePort + 3); testUtility = new HBaseTestingUtility(conf); Configuration configuration = testUtility.getConfiguration(); // -> MapR work-around configuration.set(FileSystem.FS_DEFAULT_NAME_KEY, "file:///"); configuration.set("fs.default.name", "file:///"); configuration.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem"); configuration.set("fs.hdfs.client", "org.apache.hadoop.hdfs.DistributedFileSystem"); System.setProperty("zookeeper.sasl.client", "false"); System.setProperty("zookeeper.sasl.serverconfig", "fake"); // <- MapR work-around configuration.setInt("hbase.master.port", basePort); configuration.setInt("hbase.master.info.port", basePort + 1); configuration.setInt("hbase.regionserver.port", basePort + 2); configuration.setInt("hbase.regionserver.info.port", basePort + 3); if (FileSystem.class.getProtectionDomain().getCodeSource().getLocation().getPath().contains("mapr")) { testUtility.startMiniCluster(1); } else {/* w w w .ja v a 2 s .c o m*/ testUtility.startMiniZKCluster(); testUtility.startMiniHBaseCluster(1, 1, null, null, false); } ZkUtils.getZkManager().initialize(HConfiguration.getConfiguration()); ZkUtils.initializeZookeeper(); }
From source file:com.splicemachine.test.SpliceTestPlatformConfig.java
License:Apache License
public static Configuration create(String hbaseRootDirUri, Integer masterPort, Integer masterInfoPort, Integer regionServerPort, Integer regionServerInfoPort, Integer derbyPort, boolean failTasksRandomly) { Configuration config = HConfiguration.unwrapDelegate(); config.set(SQLConfiguration.STORAGE_FACTORY_HOME, hbaseRootDirUri); //// w ww. j a v a 2 s . c o m // Coprocessors // config.set("hbase.coprocessor.regionserver.classes", getRegionServerCoprocessorsAsString()); config.set("hbase.coprocessor.region.classes", getRegionCoprocessorsAsString()); config.set("hbase.coprocessor.master.classes", getMasterCoprocessorsAsString()); // // Networking // config.set("hbase.zookeeper.quorum", "127.0.0.1:2181"); config.setInt("hbase.master.port", masterPort); config.setInt("hbase.master.info.port", masterInfoPort); config.setInt("hbase.regionserver.port", regionServerPort); config.setInt("hbase.regionserver.info.port", regionServerInfoPort); config.setInt("hbase.master.jmx.port", HConfiguration.DEFAULT_JMX_BIND_PORT); // this is set because the HBase master and regionserver are running on the same machine and in the same JVM config.setInt(SQLConfiguration.NETWORK_BIND_PORT, derbyPort); config.setClass(DefaultStoreEngine.DEFAULT_COMPACTOR_CLASS_KEY, SpliceDefaultCompactor.class, Compactor.class); // config.setClass(ConsistencyControlUtils.MVCC_IMPL, SIMultiVersionConsistencyControl.class, ConsistencyControl.class); config.setClass(DefaultStoreEngine.DEFAULT_COMPACTION_POLICY_CLASS_KEY, SpliceDefaultCompactionPolicy.class, CompactionPolicy.class); // // Networking -- interfaces // // force use of loop back interface on MacOSX, else don't set it // if (System.getProperty("os.name").contains("Mac") ) { // String interfaceName = "lo0"; // config.set("hbase.zookeeper.dns.interface", interfaceName); // config.set("hbase.master.dns.interface", interfaceName); // config.set("hbase.regionserver.dns.interface", interfaceName); // } // // File System // config.set("fs.defaultFS", "file:///"); // MapR Hack, tells it local filesystem // fs.default.name is deprecated config.set(FileSystem.FS_DEFAULT_NAME_KEY, "file:///"); config.setDouble("yarn.nodemanager.resource.io-spindles", 2.0); config.set("fs.default.name", "file:///"); config.set("yarn.nodemanager.container-executor.class", "org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor"); // Must allow Cygwin instance to config its own rootURI if (!"CYGWIN".equals(hbaseRootDirUri)) { config.set("hbase.rootdir", hbaseRootDirUri); } // // Threads, timeouts // config.setLong("hbase.rpc.timeout", MINUTES.toMillis(2)); config.setLong("hbase.client.scanner.timeout.period", MINUTES.toMillis(2)); // hbase.regionserver.lease.period is deprecated config.setLong("hbase.client.operation.timeout", MINUTES.toMillis(2)); config.setLong("hbase.regionserver.handler.count", 200); config.setLong("hbase.regionserver.msginterval", 1000); config.setLong("hbase.master.event.waiting.time", 20); config.setLong("hbase.master.lease.thread.wakefrequency", SECONDS.toMillis(3)); // config.setBoolean("hbase.master.loadbalance.bytable",true); config.setInt("hbase.balancer.period", 5000); config.setLong("hbase.server.thread.wakefrequency", SECONDS.toMillis(1)); config.setLong("hbase.client.pause", 100); // // Compaction Controls // config.setLong("hbase.hstore.compaction.min", 5); // min number of eligible files before we compact config.setLong("hbase.hstore.compaction.max", 10); // max files to be selected for a single minor compaction config.setLong("hbase.hstore.compaction.min.size", 16 * MiB); // store files smaller than this will always be eligible for minor compaction. HFiles this size or larger are evaluated by hbase.hstore.compaction.ratio to determine if they are eligible config.setLong("hbase.hstore.compaction.max.size", 248 * MiB); // store files larger than this will be excluded from compaction config.setFloat("hbase.hstore.compaction.ratio", 1.25f); // default is 1.2f, at one point we had this set to 0.25f and 25f (which was likely a typo) // // Memstore, store files, splits // config.setLong(HConstants.HREGION_MAX_FILESIZE, 32 * MiB); // hbase.hregion.max.filesize config.setLong("hbase.hregion.memstore.flush.size", 128 * MiB); // was 512 MiB config.setLong("hbase.hregion.memstore.block.multiplier", 4); config.setFloat("hbase.regionserver.global.memstore.size", 0.25f); // set mem store to 25% of heap config.setLong("hbase.hstore.blockingStoreFiles", 20); // config.set("hbase.regionserver.region.split.policy", "org.apache.hadoop.hbase.regionserver.ConstantSizeRegionSplitPolicy"); // change default split policy. this makes more sense for a standalone/single regionserver // Support SI //config.setClass(HConstants.MVCC_IMPL, SIMultiVersionConsistencyControl.class, ConsistencyControl.class); // // HFile // config.setInt("hfile.index.block.max.size", 16 * 1024); // 16KiB config.setFloat("hfile.block.cache.size", 0.25f); // set block cache to 25% of heap config.setFloat("io.hfile.bloom.error.rate", (float) 0.005); config.setBoolean(CacheConfig.CACHE_BLOOM_BLOCKS_ON_WRITE_KEY, true); // hfile.block.bloom.cacheonwrite //config.set("hbase.master.hfilecleaner.plugins", getHFileCleanerAsString()); config.set("hbase.master.hfilecleaner.plugins", getHFileCleanerAsString()); // // Misc // config.set("hbase.cluster.distributed", "true"); // don't start zookeeper for us config.set("hbase.master.distributed.log.splitting", "false"); // TODO: explain why we are setting this // AWS Credentials for test... // config.set(ACCESS_KEY, "AKIAJ6HBMCK5ALHVBFPQ"); config.set(SECRET_KEY, "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"); // // Splice // config.setLong("splice.ddl.drainingWait.maximum", SECONDS.toMillis(15)); // wait 15 seconds before bailing on bad ddl statements config.setLong("splice.ddl.maxWaitSeconds", 120000); // // Snapshots // config.setBoolean("hbase.snapshot.enabled", true); HConfiguration.reloadConfiguration(config); return HConfiguration.unwrapDelegate(); }
From source file:com.splicemachine.test.SpliceTestYarnPlatform.java
License:Apache License
private void configForTesting() throws URISyntaxException { yarnSiteConfigURL = Thread.currentThread().getContextClassLoader().getResource("yarn-site.xml"); if (yarnSiteConfigURL == null) { throw new RuntimeException("Could not find 'yarn-site.xml' file in classpath"); } else {//from w w w. jav a2s . c o m LOG.info("Found 'yarn-site.xml' at " + yarnSiteConfigURL.toURI().toString()); } conf = new YarnConfiguration(); conf.set(FileSystem.FS_DEFAULT_NAME_KEY, "file:///"); conf.setDouble("yarn.nodemanager.resource.io-spindles", 2.0); conf.set("fs.default.name", "file:///"); conf.set("yarn.nodemanager.container-executor.class", "org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor"); System.setProperty("zookeeper.sasl.client", "false"); System.setProperty("zookeeper.sasl.serverconfig", "fake"); conf.setInt(YarnConfiguration.RM_NM_HEARTBEAT_INTERVAL_MS, DEFAULT_HEARTBEAT_INTERVAL); conf.setInt(YarnConfiguration.RM_SCHEDULER_MINIMUM_ALLOCATION_MB, 128); conf.setClass(YarnConfiguration.RM_SCHEDULER, FifoScheduler.class, ResourceScheduler.class); conf.set("yarn.application.classpath", new File(yarnSiteConfigURL.getPath()).getParent()); }
From source file:com.thinkbiganalytics.kylo.catalog.file.DefaultCatalogFileManager.java
License:Apache License
/** * Constructs a {@code CatalogFileManager} using the specified Kylo data directory. *//*from www .j a v a 2s. c o m*/ @Autowired public DefaultCatalogFileManager(@Nonnull final PathValidator pathValidator) { this.pathValidator = pathValidator; defaultConf = new Configuration(); defaultConf.size(); // causes defaults to be loaded defaultConf.set(FileSystem.FS_DEFAULT_NAME_KEY, "file:///"); // Spark uses file:/// as default FileSystem }
From source file:common.NameNode.java
License:Apache License
public static InetSocketAddress getAddress(Configuration conf) { URI filesystemURI = FileSystem.getDefaultUri(conf); String authority = filesystemURI.getAuthority(); if (authority == null) { throw new IllegalArgumentException( String.format("Invalid URI for NameNode address (check %s): %s has no authority.", FileSystem.FS_DEFAULT_NAME_KEY, filesystemURI.toString())); }/*from w ww. j a v a2 s.c o m*/ if (!FSConstants.HDFS_URI_SCHEME.equalsIgnoreCase(filesystemURI.getScheme())) { throw new IllegalArgumentException( String.format("Invalid URI for NameNode address (check %s): %s is not of scheme '%s'.", FileSystem.FS_DEFAULT_NAME_KEY, filesystemURI.toString(), FSConstants.HDFS_URI_SCHEME)); } return getAddress(authority); }
From source file:eu.edisonproject.classification.tfidf.mapreduce.CompetencesDistanceDriver.java
License:Apache License
@Override public int run(String[] args) { try {/*from w w w. j av a 2 s .co m*/ Configuration conf = HBaseConfiguration.create(); //additional output using TextOutputFormat. conf.set("file.names", args[3]); Job job = Job.getInstance(conf); //TableMapReduceUtil.addDependencyJars(job); job.setJarByClass(CompetencesDistanceDriver.class); //This row must be changed job.setJobName("Words Group By Title Driver"); Path inPath = new Path(args[0]); Path outPath = new Path(args[1]); Path competencesPath = new Path(args[2]); Path competencesPathHDFS = competencesPath; FileSystem fs = FileSystem.get(conf); if (!conf.get(FileSystem.FS_DEFAULT_NAME_KEY).startsWith("file")) { competencesPathHDFS = new Path(competencesPath.getName()); if (!fs.exists(competencesPathHDFS)) { fs.mkdirs(competencesPathHDFS); File[] stats = new File(competencesPath.toString()).listFiles(); for (File stat : stats) { Path filePath = new Path(stat.getAbsolutePath()); if (FilenameUtils.getExtension(filePath.getName()).endsWith("csv")) { Path dest = new Path(competencesPathHDFS.toUri() + "/" + filePath.getName()); fs.copyFromLocalFile(filePath, dest); } } } } job.addCacheFile(competencesPathHDFS.toUri()); FileInputFormat.setInputPaths(job, inPath); FileOutputFormat.setOutputPath(job, outPath); fs.delete(outPath, true); job.setMapperClass(CompetencesDistanceMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setReducerClass(CompetencesDistanceReducer.class); // job.setOutputFormatClass(TableOutputFormat.class); // job.getConfiguration().set(TableOutputFormat.OUTPUT_TABLE, "jobpostcompetence"); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); String[] fileNames = args[3].split(","); for (String n : fileNames) { MultipleOutputs.addNamedOutput(job, n, TextOutputFormat.class, Text.class, Text.class); } return (job.waitForCompletion(true) ? 0 : 1); } catch (IOException | IllegalStateException | IllegalArgumentException | InterruptedException | ClassNotFoundException ex) { Logger.getLogger(CompetencesDistanceDriver.class.getName()).log(Level.SEVERE, null, ex); } return 0; }
From source file:eu.edisonproject.classification.tfidf.mapreduce.TermWordFrequency.java
License:Apache License
@Override public int run(String[] args) throws Exception { Configuration jobconf = getConf(); Job job = Job.getInstance(jobconf);// w w w . j a v a2 s . c o m FileSystem fs = FileSystem.get(jobconf); fs.delete(new Path(args[1]), true); Path dictionary = new Path(args[0]); Path dictionaryHdfs = dictionary; Path localDocs = new Path(args[2]); Path hdfsDocs = localDocs; Path stopwordsLocal = new Path(args[3]); Path stopwordsHDFS = stopwordsLocal; if (!jobconf.get(FileSystem.FS_DEFAULT_NAME_KEY).startsWith("file")) { dictionaryHdfs = new Path(dictionary.getName()); if (!fs.exists(dictionaryHdfs)) { fs.copyFromLocalFile(dictionary, dictionaryHdfs); } hdfsDocs = new Path(localDocs.getName()); fs.mkdirs(hdfsDocs); fs.deleteOnExit(hdfsDocs); File[] stats = new File(localDocs.toString()).listFiles(); for (File stat : stats) { Path filePath = new Path(stat.getAbsolutePath()); if (FilenameUtils.getExtension(filePath.getName()).endsWith("txt")) { Path dest = new Path(hdfsDocs.toUri() + "/" + filePath.getName()); fs.copyFromLocalFile(filePath, dest); } } stopwordsHDFS = new Path(stopwordsLocal.getName()); if (!fs.exists(stopwordsHDFS)) { fs.copyFromLocalFile(stopwordsLocal, stopwordsHDFS); } } FileStatus stopwordsStatus = fs.getFileStatus(stopwordsHDFS); stopwordsHDFS = stopwordsStatus.getPath(); job.addCacheFile(stopwordsHDFS.toUri()); job.addCacheFile(hdfsDocs.toUri()); job.setJarByClass(TermWordFrequency.class); job.setJobName("Word Frequency Term Driver"); FileInputFormat.setInputPaths(job, dictionaryHdfs); FileOutputFormat.setOutputPath(job, new Path(args[1])); // job.setInputFormatClass(TextInputFormat.class); job.setInputFormatClass(NLineInputFormat.class); NLineInputFormat.addInputPath(job, dictionaryHdfs); NLineInputFormat.setNumLinesPerSplit(job, Integer.valueOf(args[4])); NLineInputFormat.setMaxInputSplitSize(job, 500); job.setMapperClass(TermWordFrequencyMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Integer.class); job.setReducerClass(TermWordFrequencyReducer.class); return (job.waitForCompletion(true) ? 0 : 1); }
From source file:eu.edisonproject.classification.tfidf.mapreduce.WordFrequencyInDocDriver.java
License:Apache License
@Override public int run(String[] args) throws Exception { // itemset = new LinkedList<String>(); // BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(args[2]))); // String line; // while ((line = br.readLine()) != null) { // String[] components = line.split("/"); // itemset.add(components[0]); // }/*from w ww . j a v a2s . c o m*/ Configuration conf = getConf(); Job job = Job.getInstance(conf); job.setJarByClass(WordFrequencyInDocDriver.class); job.setJobName("Word Frequency In Doc Driver"); FileSystem fs = FileSystem.get(conf); fs.delete(new Path(args[1]), true); Path in = new Path(args[0]); Path inHdfs = in; Path dictionaryLocal = new Path(args[2]); Path dictionaryHDFS = dictionaryLocal; Path stopwordsLocal = new Path(args[3]); Path stopwordsHDFS = stopwordsLocal; if (!conf.get(FileSystem.FS_DEFAULT_NAME_KEY).startsWith("file")) { inHdfs = new Path(in.getName()); fs.delete(inHdfs, true); fs.copyFromLocalFile(in, inHdfs); fs.deleteOnExit(inHdfs); dictionaryHDFS = new Path(dictionaryLocal.getName()); if (!fs.exists(dictionaryHDFS)) { fs.copyFromLocalFile(dictionaryLocal, dictionaryHDFS); } stopwordsHDFS = new Path(stopwordsLocal.getName()); if (!fs.exists(stopwordsHDFS)) { fs.copyFromLocalFile(stopwordsLocal, stopwordsHDFS); } } FileStatus dictionaryStatus = fs.getFileStatus(dictionaryHDFS); dictionaryHDFS = dictionaryStatus.getPath(); job.addCacheFile(dictionaryHDFS.toUri()); FileStatus stopwordsStatus = fs.getFileStatus(stopwordsHDFS); stopwordsHDFS = stopwordsStatus.getPath(); job.addCacheFile(stopwordsHDFS.toUri()); FileInputFormat.setInputPaths(job, inHdfs); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setInputFormatClass(AvroKeyInputFormat.class); job.setMapperClass(WordFrequencyInDocMapper.class); AvroJob.setInputKeySchema(job, Document.getClassSchema()); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Integer.class); job.setReducerClass(WordFrequencyInDocReducer.class); return (job.waitForCompletion(true) ? 0 : 1); }
From source file:eu.edisonproject.training.tfidf.mapreduce.TermWordFrequency.java
License:Apache License
@Override public int run(String[] args) throws Exception { Configuration jobconf = getConf(); FileSystem fs = FileSystem.get(jobconf); fs.delete(new Path(args[1]), true); Path in = new Path(args[0]); Path inHdfs = in;//from ww w . j av a 2s . com if (!jobconf.get(FileSystem.FS_DEFAULT_NAME_KEY).startsWith("file")) { inHdfs = new Path(in.getName()); fs.delete(inHdfs, true); fs.copyFromLocalFile(in, inHdfs); fs.deleteOnExit(inHdfs); FileStatus inHdfsStatus = fs.getFileStatus(inHdfs); // Logger.getLogger(TermWordFrequency.class.getName()).log(Level.INFO, "Copied: {0} to: {1}", new Object[]{in.toUri(), inHdfsStatus.getPath().toUri()}); } Job job = Job.getInstance(jobconf); Path stopwordsLocal = new Path(args[3]); stopwords = new Path(stopwordsLocal.getName()); fs.delete(stopwords, true); fs.copyFromLocalFile(stopwordsLocal, stopwords); fs.deleteOnExit(stopwords); FileStatus stopwordsStatus = fs.getFileStatus(stopwords); stopwords = stopwordsStatus.getPath(); job.addCacheFile(stopwords.toUri()); Path localDocs = new Path(args[2]); Path hdfsDocs = new Path(localDocs.getName()); fs.mkdirs(hdfsDocs); hdfsDocs = fs.getFileStatus(hdfsDocs).getPath(); fs.delete(hdfsDocs, true); // FileStatus[] stats = fs.listStatus(localDocs); File[] stats = new File(localDocs.toString()).listFiles(); for (File stat : stats) { // for (FileStatus stat : stats) { Path filePath = new Path(stat.getAbsolutePath()); if (FilenameUtils.getExtension(filePath.getName()).endsWith("txt")) { Path dest = new Path(hdfsDocs.toUri() + "/" + filePath.getName()); fs.copyFromLocalFile(filePath, dest); } } job.addCacheFile(hdfsDocs.toUri()); job.setJarByClass(TermWordFrequency.class); job.setJobName("Word Frequency Term Driver"); FileInputFormat.setInputPaths(job, inHdfs); FileOutputFormat.setOutputPath(job, new Path(args[1])); // job.setInputFormatClass(TextInputFormat.class); job.setInputFormatClass(NLineInputFormat.class); NLineInputFormat.addInputPath(job, inHdfs); NLineInputFormat.setNumLinesPerSplit(job, Integer.valueOf(args[4])); NLineInputFormat.setMaxInputSplitSize(job, 500); Logger.getLogger(TermWordFrequency.class.getName()).log(Level.INFO, "Num. of lines: {0}", NLineInputFormat.getNumLinesPerSplit(job)); job.setMapperClass(TermWordFrequencyMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Integer.class); job.setReducerClass(TermWordFrequencyReducer.class); return (job.waitForCompletion(true) ? 0 : 1); }
From source file:org.apache.accumulo.start.classloader.vfs.AccumuloVFSClassLoader.java
License:Apache License
public static ClassLoader getClassLoader() throws IOException { ReloadingClassLoader localLoader = loader; while (null == localLoader) { synchronized (lock) { if (null == loader) { FileSystemManager vfs = generateVfs(); // Set up the 2nd tier class loader if (null == parent) { parent = AccumuloClassLoader.getClassLoader(); }//from w ww . j a va2 s. co m FileObject[] vfsCP = resolve(vfs, AccumuloClassLoader.getAccumuloString(VFS_CLASSLOADER_SYSTEM_CLASSPATH_PROPERTY, "")); if (vfsCP.length == 0) { localLoader = createDynamicClassloader(parent); loader = localLoader; return localLoader.getClassLoader(); } // Create the Accumulo Context ClassLoader using the DEFAULT_CONTEXT localLoader = createDynamicClassloader(new VFSClassLoader(vfsCP, vfs, parent)); loader = localLoader; // An HDFS FileSystem and Configuration object were created for each unique HDFS namespace in the call to resolve above. // The HDFS Client did us a favor and cached these objects so that the next time someone calls FileSystem.get(uri), they // get the cached object. However, these objects were created not with the system VFS classloader, but the classloader above // it. We need to override the classloader on the Configuration objects. Ran into an issue were log recovery was being attempted // and SequenceFile$Reader was trying to instantiate the key class via WritableName.getClass(String, Configuration) for (FileObject fo : vfsCP) { if (fo instanceof HdfsFileObject) { String uri = fo.getName().getRootURI(); Configuration c = new Configuration(true); c.set(FileSystem.FS_DEFAULT_NAME_KEY, uri); FileSystem fs = FileSystem.get(c); fs.getConf().setClassLoader(loader.getClassLoader()); } } } } } return localLoader.getClassLoader(); }