List of usage examples for org.apache.hadoop.mapred JobConf setNumReduceTasks
public void setNumReduceTasks(int n)
From source file:com.ibm.bi.dml.runtime.matrix.mapred.MRJobConfiguration.java
License:Open Source License
public static void setNumReducers(JobConf job, long numReducerGroups, int numFromCompiler) throws IOException { JobClient client = new JobClient(job); int n = client.getClusterStatus().getMaxReduceTasks(); //correction max number of reducers on yarn clusters if (InfrastructureAnalyzer.isYarnEnabled()) n = (int) Math.max(n, YarnClusterAnalyzer.getNumCores() / 2); n = Math.min(n, ConfigurationManager.getConfig().getIntValue(DMLConfig.NUM_REDUCERS)); n = Math.min(n, numFromCompiler); if (numReducerGroups > 0) n = (int) Math.min(n, numReducerGroups); job.setNumReduceTasks(n); }
From source file:com.ibm.bi.dml.runtime.matrix.MMCJMR.java
License:Open Source License
private static MatrixCharacteristics[] commonSetup(JobConf job, boolean inBlockRepresentation, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String instructionsInMapper, String aggInstructionsInReducer, String aggBinInstrction, int numReducers, int replication, byte resultDimsUnknown, String output, OutputInfo outputinfo) throws Exception { job.setJobName("MMCJ-MR"); if (numReducers <= 0) throw new Exception("MMCJ-MR has to have at least one reduce task!"); //whether use block representation or cell representation MRJobConfiguration.setMatrixValueClass(job, inBlockRepresentation); byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;/*from w w w. j a v a 2 s . co m*/ //set up the input files and their format information MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, true, inBlockRepresentation ? ConvertTarget.BLOCK : ConvertTarget.CELL); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); //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.setAggregateInstructions(job, aggInstructionsInReducer); //set up the aggregate binary operation for the mmcj job MRJobConfiguration.setAggregateBinaryInstructions(job, aggBinInstrction); //set up the replication factor for the results job.setInt("dfs.replication", replication); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); //set up map/reduce memory configurations (if in AM context) DMLConfig config = ConfigurationManager.getConfig(); DMLAppMasterUtils.setupMRJobRemoteMaxMemory(job, config); byte[] resultIndexes = new byte[] { MRInstructionParser.parseSingleInstruction(aggBinInstrction).output }; byte[] resultDimsUnknown_Array = new byte[] { resultDimsUnknown }; // byte[] resultIndexes=new byte[]{AggregateBinaryInstruction.parseMRInstruction(aggBinInstrction).output}; //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, aggBinInstrction, resultIndexes); //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown_Array, new String[] { output }, new OutputInfo[] { outputinfo }, inBlockRepresentation); // configure mapper job.setMapperClass(MMCJMRMapper.class); job.setMapOutputKeyClass(TaggedFirstSecondIndexes.class); if (inBlockRepresentation) job.setMapOutputValueClass(MatrixBlock.class); else job.setMapOutputValueClass(MatrixCell.class); job.setOutputKeyComparatorClass(TaggedFirstSecondIndexes.Comparator.class); job.setPartitionerClass(TaggedFirstSecondIndexes.FirstIndexPartitioner.class); //configure combiner //TODO: cannot set up combiner, because it will destroy the stable numerical algorithms // for sum or for central moments //if(aggInstructionsInReducer!=null && !aggInstructionsInReducer.isEmpty()) // job.setCombinerClass(MMCJMRCombiner.class); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, aggBinInstrction, null, resultIndexes, mapoutputIndexes, true); //set up the number of reducers if (AUTOMATIC_CONFIG_NUM_REDUCERS) { int numRed = determineNumReducers(rlens, clens, numReducers, ret.numReducerGroups); job.setNumReduceTasks(numRed); } else MRJobConfiguration.setNumReducers(job, ret.numReducerGroups, numReducers); //configure reducer // note: the alternative MMCJMRReducer is not maintained job.setReducerClass(MMCJMRReducerWithAggregator.class); return ret.stats; }
From source file:com.ibm.bi.dml.runtime.matrix.ReblockMR.java
License:Open Source 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 w w .j a v a2 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("dfs.replication", replication); //disable automatic tasks timeouts and speculative task exec job.setInt("mapred.task.timeout", 0); job.setMapSpeculativeExecution(false); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); //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, ConfigurationManager.getConfig().getIntValue(DMLConfig.NUM_REDUCERS), ret.numReducerGroups); job.setNumReduceTasks(numRed); //setup in-memory reduce buffers budget (reblock reducer dont need much memory) //job.set("mapred.job.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:com.ibm.bi.dml.runtime.matrix.SortMR.java
License:Open Source 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));
SamplingSortMRInputFormat.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))
job.setNumReduceTasks(1);
else//from w w w .ja v a 2s . c o m
MRJobConfiguration.setNumReducers(job, numReducers, numReducers);
//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("dfs.replication", replication);
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:com.ibm.bi.dml.runtime.matrix.SortMR.java
License:Open Source License
/** * /*from w w w . j av a 2 s . c om*/ * @param input * @param rlen * @param clen * @param brlen * @param bclen * @param counts * @param numReducers * @param replication * @param output * @throws Exception */ 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); 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("dfs.replication", replication); //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); //run mr job RunningJob runJob = JobClient.runJob(job); return runJob.isSuccessful(); }
From source file:com.ibm.bi.dml.runtime.matrix.WriteCSVMR.java
License:Open Source 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;// ww w .j av a 2 s.c om //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("dfs.replication", replication); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); 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, ConfigurationManager.getConfig().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<Byte, Integer>(); 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:com.ibm.bi.dml.runtime.transform.ApplyTfBBMR.java
License:Open Source License
public static JobReturn runJob(String inputPath, String rblkInst, String otherInst, String specPath, 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("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.getConfig().getIntValue(DMLConfig.NUM_REDUCERS), ret.numReducerGroups); 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()); 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_FILE, specPath); 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))); }/* w w w. j a va 2 s . c o m*/ return new JobReturn(ret.stats, runjob.isSuccessful()); }
From source file:com.ibm.bi.dml.runtime.transform.ApplyTfCSVMR.java
License:Open Source License
public static JobReturn runJob(String inputPath, String specPath, 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); // 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("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);//from w w w . jav a 2 s. co m 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_FILE, specPath); 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:com.jyz.study.hadoop.mapreduce.datajoin.DataJoinJob.java
License:Apache License
public static JobConf createDataJoinJob(String args[]) throws IOException { String inputDir = args[0];/*from w ww . j ava 2 s. c o m*/ String outputDir = args[1]; Class inputFormat = SequenceFileInputFormat.class; if (args[2].compareToIgnoreCase("text") != 0) { System.out.println("Using SequenceFileInputFormat: " + args[2]); } else { System.out.println("Using TextInputFormat: " + args[2]); inputFormat = TextInputFormat.class; } int numOfReducers = Integer.parseInt(args[3]); Class mapper = getClassByName(args[4]); Class reducer = getClassByName(args[5]); Class mapoutputValueClass = getClassByName(args[6]); Class outputFormat = TextOutputFormat.class; Class outputValueClass = Text.class; if (args[7].compareToIgnoreCase("text") != 0) { System.out.println("Using SequenceFileOutputFormat: " + args[7]); outputFormat = SequenceFileOutputFormat.class; outputValueClass = getClassByName(args[7]); } else { System.out.println("Using TextOutputFormat: " + args[7]); } long maxNumOfValuesPerGroup = 100; String jobName = ""; if (args.length > 8) { maxNumOfValuesPerGroup = Long.parseLong(args[8]); } if (args.length > 9) { jobName = args[9]; } Configuration defaults = new Configuration(); JobConf job = new JobConf(defaults, DataJoinJob.class); job.setJobName("DataJoinJob: " + jobName); FileSystem fs = FileSystem.get(defaults); fs.delete(new Path(outputDir), true); FileInputFormat.setInputPaths(job, inputDir); job.setInputFormat(inputFormat); job.setMapperClass(mapper); FileOutputFormat.setOutputPath(job, new Path(outputDir)); job.setOutputFormat(outputFormat); SequenceFileOutputFormat.setOutputCompressionType(job, SequenceFile.CompressionType.BLOCK); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(mapoutputValueClass); job.setOutputKeyClass(Text.class); job.setOutputValueClass(outputValueClass); job.setReducerClass(reducer); job.setNumMapTasks(1); job.setNumReduceTasks(numOfReducers); job.setLong("datajoin.maxNumOfValuesPerGroup", maxNumOfValuesPerGroup); return job; }
From source file:com.kadwa.hadoop.DistExec.java
License:Open Source License
private static JobConf createJobConf(Configuration conf) { JobConf jobconf = new JobConf(conf, DistExec.class); jobconf.setJobName(NAME);/*from ww w . j a v a2 s . c om*/ // turn off speculative execution, because DFS doesn't handle // multiple writers to the same file. jobconf.setMapSpeculativeExecution(false); jobconf.setInputFormat(ExecInputFormat.class); jobconf.setOutputKeyClass(Text.class); jobconf.setOutputValueClass(Text.class); jobconf.setMapperClass(ExecFilesMapper.class); jobconf.setNumReduceTasks(0); // TODO implement singleOut by setting single reducer and prepending file name to output return jobconf; }