List of usage examples for org.apache.hadoop.mapred RunningJob isSuccessful
public boolean isSuccessful() throws IOException;
From source file:org.apache.sysml.runtime.matrix.ReblockMR.java
License:Apache License
public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, long[] nnz, String instructionsInMapper, String reblockInstructions, String otherInstructionsInReducer, int numReducers, int replication, boolean jvmReuse, byte[] resultIndexes, String[] outputs, OutputInfo[] outputInfos) throws Exception { JobConf job = new JobConf(ReblockMR.class); job.setJobName("Reblock-MR"); byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;//from w ww. j a va 2 s . com //set up the input files and their format information //(internally used input converters: text2bc for text, identity for binary inputs) MRJobConfiguration.setUpMultipleInputsReblock(job, realIndexes, inputs, inputInfos, brlens, bclens); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens, nnz); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); //set up unary instructions that will perform in the mapper MRJobConfiguration.setInstructionsInMapper(job, instructionsInMapper); //set up the aggregate instructions that will happen in the combiner and reducer MRJobConfiguration.setReblockInstructions(job, reblockInstructions); //set up the instructions that will happen in the reducer, after the aggregation instrucions MRJobConfiguration.setInstructionsInReducer(job, otherInstructionsInReducer); //set up the replication factor for the results job.setInt(MRConfigurationNames.DFS_REPLICATION, replication); //disable automatic tasks timeouts and speculative task exec job.setInt(MRConfigurationNames.MR_TASK_TIMEOUT, 0); job.setMapSpeculativeExecution(false); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); //set up custom map/reduce configurations DMLConfig config = ConfigurationManager.getDMLConfig(); MRJobConfiguration.setupCustomMRConfigurations(job, config); //enable jvm reuse (based on SystemML configuration) if (jvmReuse) job.setNumTasksToExecutePerJvm(-1); //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, instructionsInMapper, reblockInstructions, null, otherInstructionsInReducer, resultIndexes); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, instructionsInMapper, reblockInstructions, null, null, otherInstructionsInReducer, resultIndexes, mapoutputIndexes, false); MatrixCharacteristics[] stats = ret.stats; //set up the number of reducers (according to output size) int numRed = determineNumReducers(rlens, clens, nnz, config.getIntValue(DMLConfig.NUM_REDUCERS), ret.numReducerGroups); job.setNumReduceTasks(numRed); //setup in-memory reduce buffers budget (reblock reducer dont need much memory) //job.set(MRConfigurationNames.MR_REDUCE_INPUT_BUFFER_PERCENT, "0.70"); // Print the complete instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); // Update resultDimsUnknown based on computed "stats" byte[] resultDimsUnknown = new byte[resultIndexes.length]; for (int i = 0; i < resultIndexes.length; i++) { if (stats[i].getRows() == -1 || stats[i].getCols() == -1) { resultDimsUnknown[i] = (byte) 1; } else { resultDimsUnknown[i] = (byte) 0; } } //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, true, true); // configure mapper and the mapper output key value pairs job.setMapperClass(ReblockMapper.class); job.setMapOutputKeyClass(MatrixIndexes.class); //represent key offsets for block job.setMapOutputValueClass(TaggedAdaptivePartialBlock.class); //binary cell/block //configure reducer job.setReducerClass(ReblockReducer.class); // By default, the job executes in "cluster" mode. // Determine if we can optimize and run it in "local" mode. // at this point, both reblock_binary and reblock_text are similar MatrixCharacteristics[] inputStats = new MatrixCharacteristics[inputs.length]; for (int i = 0; i < inputs.length; i++) { inputStats[i] = new MatrixCharacteristics(rlens[i], clens[i], brlens[i], bclens[i]); } //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); RunningJob runjob = JobClient.runJob(job); /* Process different counters */ Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i].setNonZeros(group.getCounter(Integer.toString(i))); // System.out.println("result #"+resultIndexes[i]+" ===>\n"+stats[i]); } return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:org.apache.sysml.runtime.matrix.SortMR.java
License:Apache License
@SuppressWarnings({ "unchecked", "rawtypes" })
public static JobReturn runJob(MRJobInstruction inst, String input, InputInfo inputInfo, long rlen, long clen,
int brlen, int bclen, String combineInst, String sortInst, int numReducers, int replication,
String output, OutputInfo outputInfo, boolean valueIsWeight) throws Exception {
boolean sortIndexes = getSortInstructionType(sortInst) == SortKeys.OperationTypes.Indexes;
String tmpOutput = sortIndexes ? MRJobConfiguration.constructTempOutputFilename() : output;
JobConf job = new JobConf(SortMR.class);
job.setJobName("SortMR");
//setup partition file
String pfname = MRJobConfiguration.setUpSortPartitionFilename(job);
Path partitionFile = new Path(pfname);
URI partitionUri = new URI(partitionFile.toString());
//setup input/output paths
Path inputDir = new Path(input);
inputDir = inputDir.makeQualified(inputDir.getFileSystem(job));
FileInputFormat.setInputPaths(job, inputDir);
Path outpath = new Path(tmpOutput);
FileOutputFormat.setOutputPath(job, outpath);
MapReduceTool.deleteFileIfExistOnHDFS(outpath, job);
//set number of reducers (1 if local mode)
if (!InfrastructureAnalyzer.isLocalMode(job)) {
MRJobConfiguration.setNumReducers(job, numReducers, numReducers);
//ensure partition size <= 10M records to avoid scalability bottlenecks
//on cp-side qpick instructions for quantile/iqm/median (~128MB)
if (!(getSortInstructionType(sortInst) == SortKeys.OperationTypes.Indexes))
job.setNumReduceTasks((int) Math.max(job.getNumReduceTasks(), rlen / 10000000));
} else //in case of local mode
job.setNumReduceTasks(1);//from www. j a va 2 s . c om
//setup input/output format
job.setInputFormat(SamplingSortMRInputFormat.class);
SamplingSortMRInputFormat.setTargetKeyValueClasses(job,
(Class<? extends WritableComparable>) outputInfo.outputKeyClass, outputInfo.outputValueClass);
//setup instructions and meta information
if (combineInst != null && !combineInst.trim().isEmpty())
job.set(COMBINE_INSTRUCTION, combineInst);
job.set(SORT_INSTRUCTION, sortInst);
job.setBoolean(VALUE_IS_WEIGHT, valueIsWeight);
boolean desc = getSortInstructionDescending(sortInst);
job.setBoolean(SORT_DECREASING, desc);
MRJobConfiguration.setBlockSize(job, (byte) 0, brlen, bclen);
MRJobConfiguration.setInputInfo(job, (byte) 0, inputInfo, brlen, bclen, ConvertTarget.CELL);
int partitionWith0 = SamplingSortMRInputFormat.writePartitionFile(job, partitionFile);
//setup mapper/reducer/partitioner/output classes
if (getSortInstructionType(sortInst) == SortKeys.OperationTypes.Indexes) {
MRJobConfiguration.setInputInfo(job, (byte) 0, inputInfo, brlen, bclen, ConvertTarget.CELL);
job.setOutputFormat(OutputInfo.BinaryBlockOutputInfo.outputFormatClass);
job.setMapperClass(IndexSortMapper.class);
job.setReducerClass(IndexSortReducer.class);
job.setMapOutputKeyClass(!desc ? IndexSortComparable.class : IndexSortComparableDesc.class);
job.setMapOutputValueClass(LongWritable.class);
job.setOutputKeyClass(MatrixIndexes.class);
job.setOutputValueClass(MatrixBlock.class);
} else { //default case: SORT w/wo weights
MRJobConfiguration.setInputInfo(job, (byte) 0, inputInfo, brlen, bclen, ConvertTarget.CELL);
job.setOutputFormat(CompactOutputFormat.class);
job.setMapperClass(ValueSortMapper.class);
job.setReducerClass(ValueSortReducer.class);
job.setOutputKeyClass(outputInfo.outputKeyClass); //double
job.setOutputValueClass(outputInfo.outputValueClass); //int
}
job.setPartitionerClass(TotalOrderPartitioner.class);
//setup distributed cache
DistributedCache.addCacheFile(partitionUri, job);
DistributedCache.createSymlink(job);
//setup replication factor
job.setInt(MRConfigurationNames.DFS_REPLICATION, replication);
//set up custom map/reduce configurations
DMLConfig config = ConfigurationManager.getDMLConfig();
MRJobConfiguration.setupCustomMRConfigurations(job, config);
MatrixCharacteristics[] s = new MatrixCharacteristics[1];
s[0] = new MatrixCharacteristics(rlen, clen, brlen, bclen);
// Print the complete instruction
if (LOG.isTraceEnabled())
inst.printCompleteMRJobInstruction(s);
//set unique working dir
MRJobConfiguration.setUniqueWorkingDir(job);
//run mr job
RunningJob runjob = JobClient.runJob(job);
Group group = runjob.getCounters().getGroup(NUM_VALUES_PREFIX);
numReducers = job.getNumReduceTasks();
//process final meta data
long[] counts = new long[numReducers];
long total = 0;
for (int i = 0; i < numReducers; i++) {
counts[i] = group.getCounter(Integer.toString(i));
total += counts[i];
}
//add missing 0s back to the results
long missing0s = 0;
if (total < rlen * clen) {
if (partitionWith0 < 0)
throw new RuntimeException("no partition contains 0, which is wrong!");
missing0s = rlen * clen - total;
counts[partitionWith0] += missing0s;
} else
partitionWith0 = -1;
if (sortIndexes) {
//run builtin job for shifting partially sorted blocks according to global offsets
//we do this in this custom form since it would not fit into the current structure
//of systemml to output two intermediates (partially sorted data, offsets) out of a
//single SortKeys lop
boolean success = runjob.isSuccessful();
if (success) {
success = runStitchupJob(tmpOutput, rlen, clen, brlen, bclen, counts, numReducers, replication,
output);
}
MapReduceTool.deleteFileIfExistOnHDFS(tmpOutput);
MapReduceTool.deleteFileIfExistOnHDFS(pfname);
return new JobReturn(s[0], OutputInfo.BinaryBlockOutputInfo, success);
} else {
MapReduceTool.deleteFileIfExistOnHDFS(pfname);
return new JobReturn(s[0], counts, partitionWith0, missing0s, runjob.isSuccessful());
}
}
From source file:org.apache.sysml.runtime.matrix.SortMR.java
License:Apache License
private static boolean runStitchupJob(String input, long rlen, long clen, int brlen, int bclen, long[] counts, int numReducers, int replication, String output) throws Exception { JobConf job = new JobConf(SortMR.class); job.setJobName("SortIndexesMR"); //setup input/output paths Path inpath = new Path(input); Path outpath = new Path(output); FileInputFormat.setInputPaths(job, inpath); FileOutputFormat.setOutputPath(job, outpath); MapReduceTool.deleteFileIfExistOnHDFS(outpath, job); //set number of reducers (1 if local mode) if (InfrastructureAnalyzer.isLocalMode(job)) job.setNumReduceTasks(1);/*from ww w .ja v a 2 s. c o m*/ else MRJobConfiguration.setNumReducers(job, numReducers, numReducers); //setup input/output format InputInfo iinfo = InputInfo.BinaryBlockInputInfo; OutputInfo oinfo = OutputInfo.BinaryBlockOutputInfo; job.setInputFormat(iinfo.inputFormatClass); job.setOutputFormat(oinfo.outputFormatClass); CompactInputFormat.setKeyValueClasses(job, MatrixIndexes.class, MatrixBlock.class); //setup mapper/reducer/output classes MRJobConfiguration.setInputInfo(job, (byte) 0, InputInfo.BinaryBlockInputInfo, brlen, bclen, ConvertTarget.BLOCK); job.setMapperClass(IndexSortStitchupMapper.class); job.setReducerClass(IndexSortStitchupReducer.class); job.setOutputKeyClass(oinfo.outputKeyClass); job.setOutputValueClass(oinfo.outputValueClass); MRJobConfiguration.setBlockSize(job, (byte) 0, brlen, bclen); MRJobConfiguration.setMatricesDimensions(job, new byte[] { 0 }, new long[] { rlen }, new long[] { clen }); //compute shifted prefix sum of offsets and put into configuration long[] cumsumCounts = new long[counts.length]; long sum = 0; for (int i = 0; i < counts.length; i++) { cumsumCounts[i] = sum; sum += counts[i]; } job.set(SORT_INDEXES_OFFSETS, Arrays.toString(cumsumCounts)); //setup replication factor job.setInt(MRConfigurationNames.DFS_REPLICATION, replication); //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); //run mr job RunningJob runJob = JobClient.runJob(job); return runJob.isSuccessful(); }
From source file:org.apache.sysml.runtime.matrix.WriteCSVMR.java
License:Apache License
public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String csvWriteInstructions, int numReducers, int replication, byte[] resultIndexes, String[] outputs) throws Exception { JobConf job = new JobConf(WriteCSVMR.class); job.setJobName("WriteCSV-MR"); byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;/* w w w . j a va 2 s. c o m*/ //set up the input files and their format information MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, true, ConvertTarget.CSVWRITE); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); MRJobConfiguration.setCSVWriteInstructions(job, csvWriteInstructions); //set up the replication factor for the results job.setInt(MRConfigurationNames.DFS_REPLICATION, replication); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); //set up custom map/reduce configurations DMLConfig config = ConfigurationManager.getDMLConfig(); MRJobConfiguration.setupCustomMRConfigurations(job, config); long maxRlen = 0; for (long rlen : rlens) if (rlen > maxRlen) maxRlen = rlen; //set up the number of reducers (according to output size) int numRed = determineNumReducers(rlens, clens, config.getIntValue(DMLConfig.NUM_REDUCERS), (int) maxRlen); job.setNumReduceTasks(numRed); byte[] resultDimsUnknown = new byte[resultIndexes.length]; MatrixCharacteristics[] stats = new MatrixCharacteristics[resultIndexes.length]; OutputInfo[] outputInfos = new OutputInfo[outputs.length]; HashMap<Byte, Integer> indexmap = new HashMap<>(); for (int i = 0; i < stats.length; i++) { indexmap.put(resultIndexes[i], i); resultDimsUnknown[i] = (byte) 0; stats[i] = new MatrixCharacteristics(); outputInfos[i] = OutputInfo.CSVOutputInfo; } CSVWriteInstruction[] ins = MRInstructionParser.parseCSVWriteInstructions(csvWriteInstructions); for (CSVWriteInstruction in : ins) stats[indexmap.get(in.output)].set(rlens[in.input], clens[in.input], -1, -1); // Print the complete instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); //set up what matrices are needed to pass from the mapper to reducer MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, "", "", csvWriteInstructions, resultIndexes); //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, true, true); // configure mapper and the mapper output key value pairs job.setMapperClass(CSVWriteMapper.class); job.setMapOutputKeyClass(TaggedFirstSecondIndexes.class); job.setMapOutputValueClass(MatrixBlock.class); //configure reducer job.setReducerClass(CSVWriteReducer.class); job.setOutputKeyComparatorClass(TaggedFirstSecondIndexes.Comparator.class); job.setPartitionerClass(TaggedFirstSecondIndexes.FirstIndexRangePartitioner.class); //job.setOutputFormat(UnPaddedOutputFormat.class); MatrixCharacteristics[] inputStats = new MatrixCharacteristics[inputs.length]; for (int i = 0; i < inputs.length; i++) { inputStats[i] = new MatrixCharacteristics(rlens[i], clens[i], brlens[i], bclens[i]); } //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); RunningJob runjob = JobClient.runJob(job); /* Process different counters */ Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i].setNonZeros(group.getCounter(Integer.toString(i))); } return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:org.apache.sysml.runtime.transform.ApplyTfBBMR.java
License:Apache License
public static JobReturn runJob(String inputPath, String rblkInst, String otherInst, String spec, String mapsPath, String tmpPath, String outputPath, String partOffsetsFile, CSVFileFormatProperties inputDataProperties, long numRows, long numColsBefore, long numColsAfter, int replication, String headerLine) throws Exception { CSVReblockInstruction rblk = (CSVReblockInstruction) InstructionParser.parseSingleInstruction(rblkInst); long[] rlens = new long[] { numRows }; long[] clens = new long[] { numColsAfter }; int[] brlens = new int[] { rblk.brlen }; int[] bclens = new int[] { rblk.bclen }; byte[] realIndexes = new byte[] { rblk.input }; byte[] resultIndexes = new byte[] { rblk.output }; JobConf job = new JobConf(ApplyTfBBMR.class); job.setJobName("ApplyTfBB"); /* Setup MapReduce Job */ job.setJarByClass(ApplyTfBBMR.class); // set relevant classes job.setMapperClass(ApplyTfBBMapper.class); MRJobConfiguration.setUpMultipleInputs(job, realIndexes, new String[] { inputPath }, new InputInfo[] { InputInfo.CSVInputInfo }, brlens, bclens, false, ConvertTarget.CELL); MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); MRJobConfiguration.setCSVReblockInstructions(job, rblkInst); //set up the instructions that will happen in the reducer, after the aggregation instrucions MRJobConfiguration.setInstructionsInReducer(job, otherInst); job.setInt(MRConfigurationNames.DFS_REPLICATION, replication); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, null, rblkInst, null, otherInst, resultIndexes); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, null, rblkInst, null, null, null, resultIndexes, mapoutputIndexes, false); //set up the number of reducers int numRed = WriteCSVMR.determineNumReducers(rlens, clens, ConfigurationManager.getNumReducers(), ret.numReducerGroups);/*from ww w .j a v a2 s .c o m*/ job.setNumReduceTasks(numRed); //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, new byte[] { rblk.output }, new byte[] { 0 }, new String[] { outputPath }, new OutputInfo[] { OutputInfo.BinaryBlockOutputInfo }, true, false); // configure mapper and the mapper output key value pairs job.setMapperClass(ApplyTfBBMapper.class); job.setMapOutputKeyClass(TaggedFirstSecondIndexes.class); job.setMapOutputValueClass(BlockRow.class); //configure reducer job.setReducerClass(CSVReblockReducer.class); //turn off adaptivemr job.setBoolean("adaptivemr.map.enable", false); //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); // Add transformation metadata file as well as partOffsetsFile to Distributed cache DistributedCache.addCacheFile((new Path(mapsPath)).toUri(), job); DistributedCache.createSymlink(job); Path cachefile = new Path(new Path(partOffsetsFile), "part-00000"); DistributedCache.addCacheFile(cachefile.toUri(), job); DistributedCache.createSymlink(job); job.set(MRJobConfiguration.TF_HAS_HEADER, Boolean.toString(inputDataProperties.hasHeader())); job.set(MRJobConfiguration.TF_DELIM, inputDataProperties.getDelim()); // Adding "dummy" string to handle the case of na_strings = "" if (inputDataProperties.getNAStrings() != null) job.set(MRJobConfiguration.TF_NA_STRINGS, TfUtils.prepNAStrings(inputDataProperties.getNAStrings())); job.set(MRJobConfiguration.TF_SPEC, spec); job.set(MRJobConfiguration.TF_SMALLEST_FILE, CSVReblockMR.findSmallestFile(job, inputPath)); job.set(MRJobConfiguration.OUTPUT_MATRICES_DIRS_CONFIG, outputPath); job.setLong(MRJobConfiguration.TF_NUM_COLS, numColsBefore); job.set(MRJobConfiguration.TF_TXMTD_PATH, mapsPath); job.set(MRJobConfiguration.TF_HEADER, headerLine); job.set(CSVReblockMR.ROWID_FILE_NAME, cachefile.toString()); job.set(MRJobConfiguration.TF_TMP_LOC, tmpPath); RunningJob runjob = JobClient.runJob(job); MapReduceTool.deleteFileIfExistOnHDFS(cachefile, job); Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { ret.stats[i].setNonZeros(group.getCounter(Integer.toString(i))); } return new JobReturn(ret.stats, runjob.isSuccessful()); }
From source file:org.apache.sysml.runtime.transform.ApplyTfCSVMR.java
License:Apache License
public static JobReturn runJob(String inputPath, String spec, String mapsPath, String tmpPath, String outputPath, String partOffsetsFile, CSVFileFormatProperties inputDataProperties, long numCols, int replication, String headerLine) throws IOException, ClassNotFoundException, InterruptedException { JobConf job = new JobConf(ApplyTfCSVMR.class); job.setJobName("ApplyTfCSV"); /* Setup MapReduce Job */ job.setJarByClass(ApplyTfCSVMR.class); // set relevant classes job.setMapperClass(ApplyTfCSVMapper.class); job.setNumReduceTasks(0);//from w w w . ja v a 2 s . c o m // Add transformation metadata file as well as partOffsetsFile to Distributed cache DistributedCache.addCacheFile((new Path(mapsPath)).toUri(), job); DistributedCache.createSymlink(job); Path cachefile = new Path(partOffsetsFile); DistributedCache.addCacheFile(cachefile.toUri(), job); DistributedCache.createSymlink(job); // set input and output properties job.setInputFormat(TextInputFormat.class); job.setOutputFormat(TextOutputFormat.class); job.setMapOutputKeyClass(NullWritable.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(Text.class); job.setInt(MRConfigurationNames.DFS_REPLICATION, replication); FileInputFormat.addInputPath(job, new Path(inputPath)); // delete outputPath, if exists already. Path outPath = new Path(outputPath); FileSystem fs = FileSystem.get(job); fs.delete(outPath, true); FileOutputFormat.setOutputPath(job, outPath); job.set(MRJobConfiguration.TF_HAS_HEADER, Boolean.toString(inputDataProperties.hasHeader())); job.set(MRJobConfiguration.TF_DELIM, inputDataProperties.getDelim()); if (inputDataProperties.getNAStrings() != null) // Adding "dummy" string to handle the case of na_strings = "" job.set(MRJobConfiguration.TF_NA_STRINGS, TfUtils.prepNAStrings(inputDataProperties.getNAStrings())); job.set(MRJobConfiguration.TF_SPEC, spec); job.set(MRJobConfiguration.TF_SMALLEST_FILE, CSVReblockMR.findSmallestFile(job, inputPath)); job.set(MRJobConfiguration.OUTPUT_MATRICES_DIRS_CONFIG, outputPath); job.setLong(MRJobConfiguration.TF_NUM_COLS, numCols); job.set(MRJobConfiguration.TF_TXMTD_PATH, mapsPath); job.set(MRJobConfiguration.TF_HEADER, headerLine); job.set(CSVReblockMR.ROWID_FILE_NAME, cachefile.toString()); job.set(MRJobConfiguration.TF_TMP_LOC, tmpPath); //turn off adaptivemr job.setBoolean("adaptivemr.map.enable", false); // Run the job RunningJob runjob = JobClient.runJob(job); // Since transform CSV produces part files w/ prefix transform-part-*, // delete all the "default" part-..... files deletePartFiles(fs, outPath); MatrixCharacteristics mc = new MatrixCharacteristics(); return new JobReturn(new MatrixCharacteristics[] { mc }, runjob.isSuccessful()); }
From source file:org.archive.hadoop.jobs.ArchiveFileExtractor.java
License:Apache License
/** * Run the job.//from w w w . ja va 2s . co m */ public int run(String[] args) throws Exception { if (args.length < 2) { printUsage(); return 1; } // Create a job configuration JobConf job = new JobConf(getConf()); // Job name uses output dir to help identify it to the operator. job.setJobName("Archive File Extractor"); // This is a map-only job, no reducers. job.setNumReduceTasks(0); // turn off speculative execution job.setBoolean("mapred.map.tasks.speculative.execution", false); // set timeout to a high value - 20 hours job.setInt("mapred.task.timeout", 72000000); //tolerate task exceptions job.setBoolean("soft", false); int arg = 0; int numMaps = 10; String DEFAULT_WARC_PATTERN = "software: %s Extractor\r\n" + "format: WARC File Format 1.0\r\n" + "conformsTo: http://bibnum.bnf.fr/WARC/WARC_ISO_28500_version1_latestdraft.pdf\r\n" + "publisher: Internet Archive\r\n" + "created: %s\r\n\r\n"; String warcHeaderString = String.format(DEFAULT_WARC_PATTERN, IAUtils.COMMONS_VERSION, DateUtils.getLog17Date(System.currentTimeMillis())); while (arg < args.length - 1) { if (args[arg].equals("-soft")) { job.setBoolean("soft", true); arg++; } else if (args[arg].equals("-mappers")) { arg++; numMaps = Integer.parseInt(args[arg]); job.setNumMapTasks(numMaps); arg++; } else if (args[arg].equals("-timestamp14")) { arg++; String timestamp14 = DateUtils.get14DigitDate(DateUtils.parse14DigitDate(args[arg])); job.set("timestamp14", timestamp14); arg++; } else if (args[arg].equals("-warc-header-local-file")) { arg++; File f = new File(args[arg]); FileInputStream fis = new FileInputStream(f); warcHeaderString = IOUtils.toString(fis, "UTF-8"); arg++; } else if (args[arg].equals("-hmacname")) { arg++; String hmacName = args[arg]; job.set("hmacName", hmacName); arg++; } else if (args[arg].equals("-hmacsignature")) { arg++; String hmacSignature = args[arg]; job.set("hmacSignature", hmacSignature); arg++; } else if (args[arg].equals("-timeout")) { arg++; int taskTimeout = Integer.parseInt(args[arg]); job.setInt("mapred.task.timeout", taskTimeout); arg++; } else if (args[arg].equals("-failpct")) { arg++; int failPct = Integer.parseInt(args[arg]); job.setInt("mapred.max.map.failures.percent", failPct); arg++; } else { break; } } job.set("warcHeaderString", warcHeaderString); if (args.length - 2 != arg) { printUsage(); return 1; } Path inputPath = new Path(args[arg]); arg++; String outputDir = args[arg]; arg++; job.set("outputDir", outputDir); Path outputPath = new Path(outputDir); job.setInputFormat(TextInputFormat.class); job.setOutputFormat(TextOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(ArchiveFileExtractorMapper.class); job.setJarByClass(ArchiveFileExtractor.class); TextInputFormat.addInputPath(job, inputPath); FileOutputFormat.setOutputPath(job, outputPath); // Run the job! RunningJob rj = JobClient.runJob(job); if (!rj.isSuccessful()) { LOG.error("FAILED: " + rj.getID()); return 2; } return 0; }
From source file:org.archive.hadoop.jobs.CDXGenerator.java
License:Apache License
/** * Run the job./*www.j av a 2 s . c om*/ */ public int run(String[] args) throws Exception { if (args.length < 2) { usage(); return 1; } // Create a job configuration JobConf job = new JobConf(getConf()); // Job name uses output dir to help identify it to the operator. job.setJobName("CDX Generator " + args[0]); // The inputs are a list of filenames, use the // FilenameInputFormat to pass them to the mappers. job.setInputFormat(FilenameInputFormat.class); // This is a map-only job, no reducers. job.setNumReduceTasks(0); // set timeout to a high value - 20 hours job.setInt("mapred.task.timeout", 72000000); // keep job running despite some failures in generating CDXs job.setBoolean("strictMode", false); job.setOutputFormat(TextOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(CDXGeneratorMapper.class); job.setJarByClass(CDXGenerator.class); int arg = 0; if (args[arg].equals("-strictMode")) { job.setBoolean("strictMode", true); arg++; } String outputDir = args[arg]; arg++; job.set("outputDir", outputDir); FileOutputFormat.setOutputPath(job, new Path(outputDir)); boolean atLeastOneInput = false; for (int i = arg; i < args.length; i++) { FileSystem inputfs = FileSystem.get(new java.net.URI(args[i]), getConf()); for (FileStatus status : inputfs.globStatus(new Path(args[i]))) { Path inputPath = status.getPath(); atLeastOneInput = true; LOG.info("Add input path: " + inputPath); FileInputFormat.addInputPath(job, inputPath); } } if (!atLeastOneInput) { LOG.info("No input files to CDXGenerator."); return 0; } // Run the job! RunningJob rj = JobClient.runJob(job); if (!rj.isSuccessful()) { LOG.error("FAILED: " + rj.getID()); return 2; } return 0; }
From source file:org.archive.hadoop.jobs.WARCMetadataRecordGenerator.java
License:Apache License
/** * Run the job.//from w w w.java2s . co m */ public int run(String[] args) throws Exception { if (args.length < 2) { usage(); return 1; } // Create a job configuration JobConf job = new JobConf(getConf()); // Job name uses output dir to help identify it to the operator. job.setJobName("WARCMetadataRecord Generator " + args[0]); // The inputs are a list of filenames, use the // FilenameInputFormat to pass them to the mappers. job.setInputFormat(FilenameInputFormat.class); // This is a map-only job, no reducers. job.setNumReduceTasks(0); // set timeout to a high value - 20 hours job.setInt("mapred.task.timeout", 72000000); job.setOutputFormat(TextOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(WARCMetadataRecordGeneratorMapper.class); job.setJarByClass(WARCMetadataRecordGenerator.class); //extract outlinks by default job.set("outputType", "outlinks"); int arg = 0; if (args[arg].equals("-hopinfo")) { job.set("outputType", "hopinfo"); arg++; } String outputDir = args[arg]; arg++; job.set("outputDir", outputDir); FileOutputFormat.setOutputPath(job, new Path(outputDir)); boolean atLeastOneInput = false; for (int i = arg; i < args.length; i++) { FileSystem inputfs = FileSystem.get(new java.net.URI(args[i]), getConf()); for (FileStatus status : inputfs.globStatus(new Path(args[i]))) { Path inputPath = status.getPath(); atLeastOneInput = true; LOG.info("Add input path: " + inputPath); FileInputFormat.addInputPath(job, inputPath); } } if (!atLeastOneInput) { LOG.info("No input files to WARCMetadataRecordGenerator."); return 0; } // Run the job! RunningJob rj = JobClient.runJob(job); if (!rj.isSuccessful()) { LOG.error("FAILED: " + rj.getID()); return 2; } return 0; }
From source file:org.archive.hadoop.jobs.WATGenerator.java
License:Apache License
/** * Run the job./*w w w . ja v a 2 s .c o m*/ */ public int run(String[] args) throws Exception { if (args.length < 2) { usage(); return 1; } // Create a job configuration JobConf job = new JobConf(getConf()); // Job name uses output dir to help identify it to the operator. job.setJobName("WAT Generator " + args[0]); // The inputs are a list of filenames, use the // FilenameInputFormat to pass them to the mappers. job.setInputFormat(FilenameInputFormat.class); // This is a map-only job, no reducers. job.setNumReduceTasks(0); // set timeout to a high value - 20 hours job.setInt("mapred.task.timeout", 72000000); // keep job running despite some failures in generating WATs job.setBoolean("strictMode", false); job.setOutputFormat(TextOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(WATGeneratorMapper.class); job.setJarByClass(WATGenerator.class); int arg = 0; if (args[arg].equals("-strictMode")) { job.setBoolean("strictMode", true); arg++; } String outputDir = args[arg]; arg++; job.set("outputDir", outputDir); FileOutputFormat.setOutputPath(job, new Path(outputDir)); boolean atLeastOneInput = false; for (int i = arg; i < args.length; i++) { FileSystem inputfs = FileSystem.get(new java.net.URI(args[i]), getConf()); for (FileStatus status : inputfs.globStatus(new Path(args[i]))) { Path inputPath = status.getPath(); atLeastOneInput = true; LOG.info("Add input path: " + inputPath); FileInputFormat.addInputPath(job, inputPath); } } if (!atLeastOneInput) { LOG.info("No input files to WATGenerator."); return 0; } // Run the job! RunningJob rj = JobClient.runJob(job); if (!rj.isSuccessful()) { LOG.error("FAILED: " + rj.getID()); return 2; } return 0; }