List of usage examples for org.apache.hadoop.mapred JobClient getFs
public synchronized FileSystem getFs() throws IOException
From source file:org.apache.whirr.examples.HadoopClusterExample.java
License:Apache License
private void waitToExitSafeMode(JobClient client) throws IOException { LOG.info("Waiting to exit safe mode..."); FileSystem fs = client.getFs(); DistributedFileSystem dfs = (DistributedFileSystem) fs; boolean inSafeMode = true; while (inSafeMode) { inSafeMode = dfs.setSafeMode(FSConstants.SafeModeAction.SAFEMODE_GET); try {/*from w w w. j av a2 s .c om*/ Thread.sleep(1000); } catch (InterruptedException e) { break; } } LOG.info("Exited safe mode"); }
From source file:org.apache.whirr.service.hadoop.integration.HadoopServiceController.java
License:Apache License
private static void waitToExitSafeMode(JobClient client) throws IOException { LOG.info("Waiting to exit safe mode..."); FileSystem fs = client.getFs(); DistributedFileSystem dfs = (DistributedFileSystem) fs; boolean inSafeMode = true; while (inSafeMode) { inSafeMode = dfs.setSafeMode(FSConstants.SafeModeAction.SAFEMODE_GET); try {/*from ww w .j av a 2 s .c om*/ System.out.print("."); Thread.sleep(1000); } catch (InterruptedException e) { break; } } LOG.info("Exited safe mode"); }
From source file:org.jd.copier.mapred.DistCp.java
License:Apache License
/** * Initialize DFSCopyFileMapper specific job-configuration. * @param conf : The dfs/mapred configuration. * @param jobConf : The handle to the jobConf object to be initialized. * @param args Arguments//from w w w. j av a2 s .co m * @return true if it is necessary to launch a job. */ private static boolean setup(Configuration conf, JobConf jobConf, final Arguments args) throws IOException { jobConf.set(DST_DIR_LABEL, args.dst.toUri().toString()); //set boolean values final boolean update = args.flags.contains(Options.UPDATE); final boolean skipCRCCheck = args.flags.contains(Options.SKIPCRC); final boolean overwrite = !update && args.flags.contains(Options.OVERWRITE); jobConf.setBoolean(Options.UPDATE.propertyname, update); jobConf.setBoolean(Options.SKIPCRC.propertyname, skipCRCCheck); jobConf.setBoolean(Options.OVERWRITE.propertyname, overwrite); jobConf.setBoolean(Options.IGNORE_READ_FAILURES.propertyname, args.flags.contains(Options.IGNORE_READ_FAILURES)); jobConf.setBoolean(Options.PRESERVE_STATUS.propertyname, args.flags.contains(Options.PRESERVE_STATUS)); final String randomId = getRandomId(); JobClient jClient = new JobClient(jobConf); Path stagingArea; try { stagingArea = JobSubmissionFiles.getStagingDir(jClient, conf); } catch (InterruptedException e) { throw new IOException(e); } Path jobDirectory = new Path(stagingArea + NAME + "_" + randomId); FsPermission mapredSysPerms = new FsPermission(JobSubmissionFiles.JOB_DIR_PERMISSION); FileSystem.mkdirs(jClient.getFs(), jobDirectory, mapredSysPerms); jobConf.set(JOB_DIR_LABEL, jobDirectory.toString()); long maxBytesPerMap = conf.getLong(BYTES_PER_MAP_LABEL, BYTES_PER_MAP); FileSystem dstfs = args.dst.getFileSystem(conf); // get tokens for all the required FileSystems.. TokenCache.obtainTokensForNamenodes(jobConf.getCredentials(), new Path[] { args.dst }, conf); boolean dstExists = dstfs.exists(args.dst); boolean dstIsDir = false; if (dstExists) { dstIsDir = dstfs.getFileStatus(args.dst).isDir(); } // default logPath Path logPath = args.log; if (logPath == null) { String filename = "_distcp_logs_" + randomId; if (!dstExists || !dstIsDir) { Path parent = args.dst.getParent(); if (null == parent) { // If dst is '/' on S3, it might not exist yet, but dst.getParent() // will return null. In this case, use '/' as its own parent to prevent // NPE errors below. parent = args.dst; } if (!dstfs.exists(parent)) { dstfs.mkdirs(parent); } logPath = new Path(parent, filename); } else { logPath = new Path(args.dst, filename); } } FileOutputFormat.setOutputPath(jobConf, logPath); // create src list, dst list FileSystem jobfs = jobDirectory.getFileSystem(jobConf); Path srcfilelist = new Path(jobDirectory, "_distcp_src_files"); jobConf.set(SRC_LIST_LABEL, srcfilelist.toString()); SequenceFile.Writer src_writer = SequenceFile.createWriter(jobfs, jobConf, srcfilelist, LongWritable.class, FilePair.class, SequenceFile.CompressionType.NONE); Path dstfilelist = new Path(jobDirectory, "_distcp_dst_files"); SequenceFile.Writer dst_writer = SequenceFile.createWriter(jobfs, jobConf, dstfilelist, Text.class, Text.class, SequenceFile.CompressionType.NONE); Path dstdirlist = new Path(jobDirectory, "_distcp_dst_dirs"); jobConf.set(DST_DIR_LIST_LABEL, dstdirlist.toString()); SequenceFile.Writer dir_writer = SequenceFile.createWriter(jobfs, jobConf, dstdirlist, Text.class, FilePair.class, SequenceFile.CompressionType.NONE); // handle the case where the destination directory doesn't exist // and we've only a single src directory OR we're updating/overwriting // the contents of the destination directory. final boolean special = (args.srcs.size() == 1 && !dstExists) || update || overwrite; int srcCount = 0, cnsyncf = 0, dirsyn = 0; long fileCount = 0L, byteCount = 0L, cbsyncs = 0L; try { for (Iterator<Path> srcItr = args.srcs.iterator(); srcItr.hasNext();) { final Path src = srcItr.next(); FileSystem srcfs = src.getFileSystem(conf); FileStatus srcfilestat = srcfs.getFileStatus(src); Path root = special && srcfilestat.isDir() ? src : src.getParent(); if (srcfilestat.isDir()) { ++srcCount; } Stack<FileStatus> pathstack = new Stack<FileStatus>(); for (pathstack.push(srcfilestat); !pathstack.empty();) { FileStatus cur = pathstack.pop(); FileStatus[] children = srcfs.listStatus(cur.getPath()); for (int i = 0; i < children.length; i++) { boolean skipfile = false; final FileStatus child = children[i]; final String dst = makeRelative(root, child.getPath()); ++srcCount; if (child.isDir()) { pathstack.push(child); } else { //skip file if the src and the dst files are the same. skipfile = update && sameFile(srcfs, child, dstfs, new Path(args.dst, dst), skipCRCCheck); //skip file if it exceed file limit or size limit skipfile |= fileCount == args.filelimit || byteCount + child.getLen() > args.sizelimit; if (!skipfile) { ++fileCount; byteCount += child.getLen(); if (LOG.isTraceEnabled()) { LOG.trace("adding file " + child.getPath()); } ++cnsyncf; cbsyncs += child.getLen(); if (cnsyncf > SYNC_FILE_MAX || cbsyncs > maxBytesPerMap) { src_writer.sync(); dst_writer.sync(); cnsyncf = 0; cbsyncs = 0L; } } } if (!skipfile) { src_writer.append(new LongWritable(child.isDir() ? 0 : child.getLen()), new FilePair(child, dst)); } dst_writer.append(new Text(dst), new Text(child.getPath().toString())); } if (cur.isDir()) { String dst = makeRelative(root, cur.getPath()); dir_writer.append(new Text(dst), new FilePair(cur, dst)); if (++dirsyn > SYNC_FILE_MAX) { dirsyn = 0; dir_writer.sync(); } } } } } finally { checkAndClose(src_writer); checkAndClose(dst_writer); checkAndClose(dir_writer); } FileStatus dststatus = null; try { dststatus = dstfs.getFileStatus(args.dst); } catch (FileNotFoundException fnfe) { LOG.info(args.dst + " does not exist."); } // create dest path dir if copying > 1 file if (dststatus == null) { if (srcCount > 1 && !dstfs.mkdirs(args.dst)) { throw new IOException("Failed to create" + args.dst); } } final Path sorted = new Path(jobDirectory, "_distcp_sorted"); checkDuplication(jobfs, dstfilelist, sorted, conf); if (dststatus != null && args.flags.contains(Options.DELETE)) { deleteNonexisting(dstfs, dststatus, sorted, jobfs, jobDirectory, jobConf, conf); } Path tmpDir = new Path( (dstExists && !dstIsDir) || (!dstExists && srcCount == 1) ? args.dst.getParent() : args.dst, "_distcp_tmp_" + randomId); jobConf.set(TMP_DIR_LABEL, tmpDir.toUri().toString()); // Explicitly create the tmpDir to ensure that it can be cleaned // up by fullyDelete() later. tmpDir.getFileSystem(conf).mkdirs(tmpDir); LOG.info("sourcePathsCount=" + srcCount); LOG.info("filesToCopyCount=" + fileCount); LOG.info("bytesToCopyCount=" + StringUtils.humanReadableInt(byteCount)); jobConf.setInt(SRC_COUNT_LABEL, srcCount); jobConf.setLong(TOTAL_SIZE_LABEL, byteCount); setMapCount(byteCount, jobConf); return fileCount > 0; }
From source file:org.smartfrog.services.hadoop.components.cluster.ClusterStatusCheckerImpl.java
License:Open Source License
/** * Check the cluster status//from ww w . j av a 2 s.com * * @throws SFHadoopException on any problem with the checks * @return a cluster status string */ private String checkClusterStatus() throws SmartFrogException { try { JobClient cluster = createClientOnDemand(); ClusterStatus status = cluster.getClusterStatus(); StringBuilder result = new StringBuilder(); if (supportedFileSystem) { Path sysDir = cluster.getSystemDir(); URI uri = sysDir.toUri(); sfLog().info("Checking filesystem " + uri); ManagedConfiguration conf = (ManagedConfiguration) cluster.getConf(); String impl = "fs." + uri.getScheme() + ".impl"; String classname = conf.get(impl); if (classname == null) { maybeDumpConfiguration(conf); throw new SFHadoopException("File system " + uri + " will not load " + " - no configuration mapping for " + impl + " in " + conf.dump(), this, conf); } try { conf.getClassByName(classname); } catch (ClassNotFoundException e) { throw new SFHadoopException("File system " + uri + " will not load " + " - unable to locate class " + impl + " : " + e, e, this, conf); } try { result.append("Filesystem: ").append(uri).append(" ; "); FileSystem fs = cluster.getFs(); } catch (IOException e) { throw new SFHadoopException("File system " + uri + " will not load " + e, e, this, conf); } catch (IllegalArgumentException e) { throw new SFHadoopException("Bad File system URI" + e, e, this, conf); } } if (jobtrackerLive) { sfLog().info("Checking jobTracker "); JobTracker.State state = status.getJobTrackerState(); if (!state.equals(JobTracker.State.RUNNING)) { throw new SFHadoopException( "Job Tracker at " + jobtracker + " is not running. It is in the state " + state, this); } result.append("Job tracker is in state ").append(status); } checkRange(minActiveMapTasks, maxActiveMapTasks, status.getMapTasks(), "map task"); checkRange(minActiveReduceTasks, maxActiveReduceTasks, status.getReduceTasks(), "reduce task"); checkMax(maxSupportedMapTasks, status.getMaxMapTasks(), "supported max map task"); checkMax(maxSupportedReduceTasks, status.getMaxReduceTasks(), "supported max reduce task"); result.append(" Map Tasks = ").append(status.getMapTasks()); result.append(" Reduce Tasks = ").append(status.getReduceTasks()); return result.toString(); } catch (IOException e) { throw new SFHadoopException("Cannot connect to" + jobtracker, e, this); } }