List of usage examples for org.apache.hadoop.mapred JobConf setNumTasksToExecutePerJvm
public void setNumTasksToExecutePerJvm(int numTasks)
From source file:org.apache.sysml.runtime.controlprogram.parfor.RemoteDPParForMR.java
License:Apache License
public static RemoteParForJobReturn runJob(long pfid, String itervar, String matrixvar, String program, String resultFile, MatrixObject input, PartitionFormat dpf, OutputInfo oi, boolean tSparseCol, //config params boolean enableCPCaching, int numReducers, int replication) //opt params throws DMLRuntimeException { RemoteParForJobReturn ret = null;//w ww . j a va 2s .c o m String jobname = "ParFor-DPEMR"; long t0 = DMLScript.STATISTICS ? System.nanoTime() : 0; JobConf job; job = new JobConf(RemoteDPParForMR.class); job.setJobName(jobname + pfid); //maintain dml script counters Statistics.incrementNoOfCompiledMRJobs(); try { ///// //configure the MR job //set arbitrary CP program blocks that will perform in the reducers MRJobConfiguration.setProgramBlocks(job, program); //enable/disable caching MRJobConfiguration.setParforCachingConfig(job, enableCPCaching); //setup input matrix Path path = new Path(input.getFileName()); long rlen = input.getNumRows(); long clen = input.getNumColumns(); int brlen = (int) input.getNumRowsPerBlock(); int bclen = (int) input.getNumColumnsPerBlock(); MRJobConfiguration.setPartitioningInfo(job, rlen, clen, brlen, bclen, InputInfo.BinaryBlockInputInfo, oi, dpf._dpf, dpf._N, input.getFileName(), itervar, matrixvar, tSparseCol); job.setInputFormat(InputInfo.BinaryBlockInputInfo.inputFormatClass); FileInputFormat.setInputPaths(job, path); //set mapper and reducers classes job.setMapperClass(DataPartitionerRemoteMapper.class); job.setReducerClass(RemoteDPParWorkerReducer.class); //set output format job.setOutputFormat(SequenceFileOutputFormat.class); //set output path MapReduceTool.deleteFileIfExistOnHDFS(resultFile); FileOutputFormat.setOutputPath(job, new Path(resultFile)); //set the output key, value schema //parfor partitioning outputs (intermediates) job.setMapOutputKeyClass(LongWritable.class); if (oi == OutputInfo.BinaryBlockOutputInfo) job.setMapOutputValueClass(PairWritableBlock.class); else if (oi == OutputInfo.BinaryCellOutputInfo) job.setMapOutputValueClass(PairWritableCell.class); else throw new DMLRuntimeException("Unsupported intermrediate output info: " + oi); //parfor exec output job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); ////// //set optimization parameters //set the number of mappers and reducers job.setNumReduceTasks(numReducers); //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 map/reduce memory configurations (if in AM context) DMLConfig config = ConfigurationManager.getDMLConfig(); DMLAppMasterUtils.setupMRJobRemoteMaxMemory(job, config); //set up custom map/reduce configurations MRJobConfiguration.setupCustomMRConfigurations(job, config); //disable JVM reuse job.setNumTasksToExecutePerJvm(1); //-1 for unlimited //set the replication factor for the results job.setInt(MRConfigurationNames.DFS_REPLICATION, replication); //set the max number of retries per map task //note: currently disabled to use cluster config //job.setInt(MRConfigurationNames.MR_MAP_MAXATTEMPTS, max_retry); //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); ///// // execute the MR job RunningJob runjob = JobClient.runJob(job); // Process different counters Statistics.incrementNoOfExecutedMRJobs(); Group pgroup = runjob.getCounters().getGroup(ParForProgramBlock.PARFOR_COUNTER_GROUP_NAME); int numTasks = (int) pgroup.getCounter(Stat.PARFOR_NUMTASKS.toString()); int numIters = (int) pgroup.getCounter(Stat.PARFOR_NUMITERS.toString()); if (DMLScript.STATISTICS && !InfrastructureAnalyzer.isLocalMode()) { Statistics.incrementJITCompileTime(pgroup.getCounter(Stat.PARFOR_JITCOMPILE.toString())); Statistics.incrementJVMgcCount(pgroup.getCounter(Stat.PARFOR_JVMGC_COUNT.toString())); Statistics.incrementJVMgcTime(pgroup.getCounter(Stat.PARFOR_JVMGC_TIME.toString())); Group cgroup = runjob.getCounters().getGroup(CacheableData.CACHING_COUNTER_GROUP_NAME.toString()); CacheStatistics .incrementMemHits((int) cgroup.getCounter(CacheStatistics.Stat.CACHE_HITS_MEM.toString())); CacheStatistics.incrementFSBuffHits( (int) cgroup.getCounter(CacheStatistics.Stat.CACHE_HITS_FSBUFF.toString())); CacheStatistics .incrementFSHits((int) cgroup.getCounter(CacheStatistics.Stat.CACHE_HITS_FS.toString())); CacheStatistics.incrementHDFSHits( (int) cgroup.getCounter(CacheStatistics.Stat.CACHE_HITS_HDFS.toString())); CacheStatistics.incrementFSBuffWrites( (int) cgroup.getCounter(CacheStatistics.Stat.CACHE_WRITES_FSBUFF.toString())); CacheStatistics.incrementFSWrites( (int) cgroup.getCounter(CacheStatistics.Stat.CACHE_WRITES_FS.toString())); CacheStatistics.incrementHDFSWrites( (int) cgroup.getCounter(CacheStatistics.Stat.CACHE_WRITES_HDFS.toString())); CacheStatistics .incrementAcquireRTime(cgroup.getCounter(CacheStatistics.Stat.CACHE_TIME_ACQR.toString())); CacheStatistics .incrementAcquireMTime(cgroup.getCounter(CacheStatistics.Stat.CACHE_TIME_ACQM.toString())); CacheStatistics .incrementReleaseTime(cgroup.getCounter(CacheStatistics.Stat.CACHE_TIME_RLS.toString())); CacheStatistics .incrementExportTime(cgroup.getCounter(CacheStatistics.Stat.CACHE_TIME_EXP.toString())); } // read all files of result variables and prepare for return LocalVariableMap[] results = readResultFile(job, resultFile); ret = new RemoteParForJobReturn(runjob.isSuccessful(), numTasks, numIters, results); } catch (Exception ex) { throw new DMLRuntimeException(ex); } finally { // remove created files try { MapReduceTool.deleteFileIfExistOnHDFS(new Path(resultFile), job); } catch (IOException ex) { throw new DMLRuntimeException(ex); } } if (DMLScript.STATISTICS) { long t1 = System.nanoTime(); Statistics.maintainCPHeavyHitters("MR-Job_" + jobname, t1 - t0); } return ret; }
From source file:org.apache.sysml.runtime.controlprogram.parfor.RemoteParForMR.java
License:Apache License
public static RemoteParForJobReturn runJob(long pfid, String program, String taskFile, String resultFile, MatrixObject colocatedDPMatrixObj, //inputs boolean enableCPCaching, int numMappers, int replication, int max_retry, long minMem, boolean jvmReuse) //opt params throws DMLRuntimeException { RemoteParForJobReturn ret = null;//from w ww .j av a2 s. c o m String jobname = "ParFor-EMR"; long t0 = DMLScript.STATISTICS ? System.nanoTime() : 0; JobConf job; job = new JobConf(RemoteParForMR.class); job.setJobName(jobname + pfid); //maintain dml script counters Statistics.incrementNoOfCompiledMRJobs(); try { ///// //configure the MR job //set arbitrary CP program blocks that will perform in the mapper MRJobConfiguration.setProgramBlocks(job, program); //enable/disable caching MRJobConfiguration.setParforCachingConfig(job, enableCPCaching); //set mappers, reducers, combiners job.setMapperClass(RemoteParWorkerMapper.class); //map-only //set input format (one split per row, NLineInputFormat default N=1) if (ParForProgramBlock.ALLOW_DATA_COLOCATION && colocatedDPMatrixObj != null) { job.setInputFormat(RemoteParForColocatedNLineInputFormat.class); MRJobConfiguration.setPartitioningFormat(job, colocatedDPMatrixObj.getPartitionFormat()); MatrixCharacteristics mc = colocatedDPMatrixObj.getMatrixCharacteristics(); MRJobConfiguration.setPartitioningBlockNumRows(job, mc.getRowsPerBlock()); MRJobConfiguration.setPartitioningBlockNumCols(job, mc.getColsPerBlock()); MRJobConfiguration.setPartitioningFilename(job, colocatedDPMatrixObj.getFileName()); } else //default case { job.setInputFormat(NLineInputFormat.class); } //set the input path and output path FileInputFormat.setInputPaths(job, new Path(taskFile)); //set output format job.setOutputFormat(SequenceFileOutputFormat.class); //set output path MapReduceTool.deleteFileIfExistOnHDFS(resultFile); FileOutputFormat.setOutputPath(job, new Path(resultFile)); //set the output key, value schema job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); ////// //set optimization parameters //set the number of mappers and reducers job.setNumMapTasks(numMappers); //numMappers job.setNumReduceTasks(0); //job.setInt("mapred.map.tasks.maximum", 1); //system property //job.setInt("mapred.tasktracker.tasks.maximum",1); //system property //job.setInt("mapred.jobtracker.maxtasks.per.job",1); //system property //set jvm memory size (if require) String memKey = MRConfigurationNames.MR_CHILD_JAVA_OPTS; if (minMem > 0 && minMem > InfrastructureAnalyzer.extractMaxMemoryOpt(job.get(memKey))) { InfrastructureAnalyzer.setMaxMemoryOpt(job, memKey, minMem); LOG.warn("Forcing '" + memKey + "' to -Xmx" + minMem / (1024 * 1024) + "M."); } //disable automatic tasks timeouts and speculative task exec job.setInt(MRConfigurationNames.MR_TASK_TIMEOUT, 0); job.setMapSpeculativeExecution(false); //set up map/reduce memory configurations (if in AM context) DMLConfig config = ConfigurationManager.getDMLConfig(); DMLAppMasterUtils.setupMRJobRemoteMaxMemory(job, config); //set up custom map/reduce configurations MRJobConfiguration.setupCustomMRConfigurations(job, config); //enables the reuse of JVMs (multiple tasks per MR task) if (jvmReuse) job.setNumTasksToExecutePerJvm(-1); //unlimited //set sort io buffer (reduce unnecessary large io buffer, guaranteed memory consumption) job.setInt(MRConfigurationNames.MR_TASK_IO_SORT_MB, 8); //8MB //set the replication factor for the results job.setInt(MRConfigurationNames.DFS_REPLICATION, replication); //set the max number of retries per map task // disabled job-level configuration to respect cluster configuration // note: this refers to hadoop2, hence it never had effect on mr1 //job.setInt(MRConfigurationNames.MR_MAP_MAXATTEMPTS, max_retry); //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); ///// // execute the MR job RunningJob runjob = JobClient.runJob(job); // Process different counters Statistics.incrementNoOfExecutedMRJobs(); Group pgroup = runjob.getCounters().getGroup(ParForProgramBlock.PARFOR_COUNTER_GROUP_NAME); int numTasks = (int) pgroup.getCounter(Stat.PARFOR_NUMTASKS.toString()); int numIters = (int) pgroup.getCounter(Stat.PARFOR_NUMITERS.toString()); if (DMLScript.STATISTICS && !InfrastructureAnalyzer.isLocalMode()) { Statistics.incrementJITCompileTime(pgroup.getCounter(Stat.PARFOR_JITCOMPILE.toString())); Statistics.incrementJVMgcCount(pgroup.getCounter(Stat.PARFOR_JVMGC_COUNT.toString())); Statistics.incrementJVMgcTime(pgroup.getCounter(Stat.PARFOR_JVMGC_TIME.toString())); Group cgroup = runjob.getCounters().getGroup(CacheableData.CACHING_COUNTER_GROUP_NAME.toString()); CacheStatistics .incrementMemHits((int) cgroup.getCounter(CacheStatistics.Stat.CACHE_HITS_MEM.toString())); CacheStatistics.incrementFSBuffHits( (int) cgroup.getCounter(CacheStatistics.Stat.CACHE_HITS_FSBUFF.toString())); CacheStatistics .incrementFSHits((int) cgroup.getCounter(CacheStatistics.Stat.CACHE_HITS_FS.toString())); CacheStatistics.incrementHDFSHits( (int) cgroup.getCounter(CacheStatistics.Stat.CACHE_HITS_HDFS.toString())); CacheStatistics.incrementFSBuffWrites( (int) cgroup.getCounter(CacheStatistics.Stat.CACHE_WRITES_FSBUFF.toString())); CacheStatistics.incrementFSWrites( (int) cgroup.getCounter(CacheStatistics.Stat.CACHE_WRITES_FS.toString())); CacheStatistics.incrementHDFSWrites( (int) cgroup.getCounter(CacheStatistics.Stat.CACHE_WRITES_HDFS.toString())); CacheStatistics .incrementAcquireRTime(cgroup.getCounter(CacheStatistics.Stat.CACHE_TIME_ACQR.toString())); CacheStatistics .incrementAcquireMTime(cgroup.getCounter(CacheStatistics.Stat.CACHE_TIME_ACQM.toString())); CacheStatistics .incrementReleaseTime(cgroup.getCounter(CacheStatistics.Stat.CACHE_TIME_RLS.toString())); CacheStatistics .incrementExportTime(cgroup.getCounter(CacheStatistics.Stat.CACHE_TIME_EXP.toString())); } // read all files of result variables and prepare for return LocalVariableMap[] results = readResultFile(job, resultFile); ret = new RemoteParForJobReturn(runjob.isSuccessful(), numTasks, numIters, results); } catch (Exception ex) { throw new DMLRuntimeException(ex); } finally { // remove created files try { MapReduceTool.deleteFileIfExistOnHDFS(new Path(taskFile), job); MapReduceTool.deleteFileIfExistOnHDFS(new Path(resultFile), job); } catch (IOException ex) { throw new DMLRuntimeException(ex); } } if (DMLScript.STATISTICS) { long t1 = System.nanoTime(); Statistics.maintainCPHeavyHitters("MR-Job_" + jobname, t1 - t0); } return ret; }
From source file:org.apache.sysml.runtime.controlprogram.parfor.ResultMergeRemoteMR.java
License:Apache License
@SuppressWarnings({ "unused", "deprecation" })
protected void executeMerge(String fname, String fnameNew, String[] srcFnames, InputInfo ii, OutputInfo oi,
long rlen, long clen, int brlen, int bclen) throws DMLRuntimeException {
String jobname = "ParFor-RMMR";
long t0 = DMLScript.STATISTICS ? System.nanoTime() : 0;
JobConf job = new JobConf(ResultMergeRemoteMR.class);
job.setJobName(jobname + _pfid);/*from ww w. j a v a 2 s.co m*/
//maintain dml script counters
Statistics.incrementNoOfCompiledMRJobs();
//warning for textcell/binarycell without compare
boolean withCompare = (fname != null);
if ((oi == OutputInfo.TextCellOutputInfo || oi == OutputInfo.BinaryCellOutputInfo) && !withCompare
&& ResultMergeLocalFile.ALLOW_COPY_CELLFILES)
LOG.warn("Result merge for " + OutputInfo.outputInfoToString(oi)
+ " without compare can be realized more efficiently with LOCAL_FILE than REMOTE_MR.");
try {
Path pathCompare = null;
Path pathNew = new Path(fnameNew);
/////
//configure the MR job
if (withCompare) {
FileSystem fs = IOUtilFunctions.getFileSystem(pathNew, job);
pathCompare = new Path(fname).makeQualified(fs);
MRJobConfiguration.setResultMergeInfo(job, pathCompare.toString(), ii,
LocalFileUtils.getWorkingDir(LocalFileUtils.CATEGORY_RESULTMERGE), rlen, clen, brlen,
bclen);
} else
MRJobConfiguration.setResultMergeInfo(job, "null", ii,
LocalFileUtils.getWorkingDir(LocalFileUtils.CATEGORY_RESULTMERGE), rlen, clen, bclen,
bclen);
//set mappers, reducers, combiners
job.setMapperClass(ResultMergeRemoteMapper.class);
job.setReducerClass(ResultMergeRemoteReducer.class);
if (oi == OutputInfo.TextCellOutputInfo) {
job.setMapOutputKeyClass(MatrixIndexes.class);
job.setMapOutputValueClass(TaggedMatrixCell.class);
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(Text.class);
} else if (oi == OutputInfo.BinaryCellOutputInfo) {
job.setMapOutputKeyClass(MatrixIndexes.class);
job.setMapOutputValueClass(TaggedMatrixCell.class);
job.setOutputKeyClass(MatrixIndexes.class);
job.setOutputValueClass(MatrixCell.class);
} else if (oi == OutputInfo.BinaryBlockOutputInfo) {
//setup partitioning, grouping, sorting for composite key (old API)
job.setPartitionerClass(ResultMergeRemotePartitioning.class); //partitioning
job.setOutputValueGroupingComparator(ResultMergeRemoteGrouping.class); //grouping
job.setOutputKeyComparatorClass(ResultMergeRemoteSorting.class); //sorting
job.setMapOutputKeyClass(ResultMergeTaggedMatrixIndexes.class);
job.setMapOutputValueClass(TaggedMatrixBlock.class);
job.setOutputKeyClass(MatrixIndexes.class);
job.setOutputValueClass(MatrixBlock.class);
}
//set input format
job.setInputFormat(ii.inputFormatClass);
//set the input path
Path[] paths = null;
if (withCompare) {
paths = new Path[srcFnames.length + 1];
paths[0] = pathCompare;
for (int i = 1; i < paths.length; i++)
paths[i] = new Path(srcFnames[i - 1]);
} else {
paths = new Path[srcFnames.length];
for (int i = 0; i < paths.length; i++)
paths[i] = new Path(srcFnames[i]);
}
FileInputFormat.setInputPaths(job, paths);
//set output format
job.setOutputFormat(oi.outputFormatClass);
//set output path
MapReduceTool.deleteFileIfExistOnHDFS(fnameNew);
FileOutputFormat.setOutputPath(job, pathNew);
//////
//set optimization parameters
//set the number of mappers and reducers
//job.setNumMapTasks( _numMappers ); //use default num mappers
long reducerGroups = _numReducers;
if (oi == OutputInfo.BinaryBlockOutputInfo)
reducerGroups = Math.max(rlen / brlen, 1) * Math.max(clen / bclen, 1);
else //textcell/binarycell
reducerGroups = Math.max((rlen * clen) / StagingFileUtils.CELL_BUFFER_SIZE, 1);
job.setNumReduceTasks((int) Math.min(_numReducers, reducerGroups));
//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);
//enables the reuse of JVMs (multiple tasks per MR task)
if (_jvmReuse)
job.setNumTasksToExecutePerJvm(-1); //unlimited
//enables compression - not conclusive for different codecs (empirically good compression ratio, but significantly slower)
//job.set(MRConfigurationNames.MR_MAP_OUTPUT_COMPRESS, "true");
//job.set(MRConfigurationNames.MR_MAP_OUTPUT_COMPRESS_CODEC, "org.apache.hadoop.io.compress.GzipCodec");
//set the replication factor for the results
job.setInt(MRConfigurationNames.DFS_REPLICATION, _replication);
//set the max number of retries per map task
// disabled job-level configuration to respect cluster configuration
// note: this refers to hadoop2, hence it never had effect on mr1
//job.setInt(MRConfigurationNames.MR_MAP_MAXATTEMPTS, _max_retry);
//set unique working dir
MRJobConfiguration.setUniqueWorkingDir(job);
/////
// execute the MR job
JobClient.runJob(job);
//maintain dml script counters
Statistics.incrementNoOfExecutedMRJobs();
} catch (Exception ex) {
throw new DMLRuntimeException(ex);
}
if (DMLScript.STATISTICS) {
long t1 = System.nanoTime();
Statistics.maintainCPHeavyHitters("MR-Job_" + jobname, t1 - t0);
}
}
From source file:org.apache.sysml.runtime.matrix.GMR.java
License:Apache License
/** * Execute job.//from w ww . ja v a 2 s .c o m * * @param inst MR job instruction * @param inputs input matrices, the inputs are indexed by 0, 1, 2, .. based on the position in this string * @param inputInfos the input format information for the input matrices * @param rlens array of number of rows * @param clens array of number of columns * @param brlens array of number of rows in block * @param bclens array of number of columns in block * @param partitioned boolean array of partitioned status * @param pformats array of data partition formats * @param psizes does nothing * @param recordReaderInstruction record reader instruction * @param instructionsInMapper in Mapper, the set of unary operations that need to be performed on each input matrix * @param aggInstructionsInReducer in Reducer, right after sorting, the set of aggreagte operations * that need to be performed on each input matrix * @param otherInstructionsInReducer the mixed operations that need to be performed on matrices after the aggregate operations * @param numReducers the number of reducers * @param replication the replication factor for the output * @param jvmReuse if true, reuse JVM * @param resultIndexes the indexes of the result matrices that needs to be outputted * @param dimsUnknownFilePrefix file path prefix when dimensions unknown * @param outputs the names for the output directories, one for each result index * @param outputInfos output format information for the output matrices * @return job return object * @throws Exception if Exception occurs */ @SuppressWarnings({ "unchecked", "rawtypes" }) public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, boolean[] partitioned, PDataPartitionFormat[] pformats, int[] psizes, String recordReaderInstruction, String instructionsInMapper, String aggInstructionsInReducer, String otherInstructionsInReducer, int numReducers, int replication, boolean jvmReuse, byte[] resultIndexes, String dimsUnknownFilePrefix, String[] outputs, OutputInfo[] outputInfos) throws Exception { JobConf job = new JobConf(GMR.class); job.setJobName("G-MR"); boolean inBlockRepresentation = MRJobConfiguration.deriveRepresentation(inputInfos); //whether use block representation or cell representation MRJobConfiguration.setMatrixValueClass(job, inBlockRepresentation); //added for handling recordreader instruction String[] realinputs = inputs; InputInfo[] realinputInfos = inputInfos; long[] realrlens = rlens; long[] realclens = clens; int[] realbrlens = brlens; int[] realbclens = bclens; byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b; if (recordReaderInstruction != null && !recordReaderInstruction.isEmpty()) { assert (inputs.length <= 2); PickByCountInstruction ins = (PickByCountInstruction) PickByCountInstruction .parseInstruction(recordReaderInstruction); PickFromCompactInputFormat.setKeyValueClasses(job, (Class<? extends WritableComparable>) inputInfos[ins.input1].inputKeyClass, inputInfos[ins.input1].inputValueClass); job.setInputFormat(PickFromCompactInputFormat.class); PickFromCompactInputFormat.setZeroValues(job, (MetaDataNumItemsByEachReducer) inputInfos[ins.input1].metadata); if (ins.isValuePick) { double[] probs = MapReduceTool.readColumnVectorFromHDFS(inputs[ins.input2], inputInfos[ins.input2], rlens[ins.input2], clens[ins.input2], brlens[ins.input2], bclens[ins.input2]); PickFromCompactInputFormat.setPickRecordsInEachPartFile(job, (MetaDataNumItemsByEachReducer) inputInfos[ins.input1].metadata, probs); realinputs = new String[inputs.length - 1]; realinputInfos = new InputInfo[inputs.length - 1]; realrlens = new long[inputs.length - 1]; realclens = new long[inputs.length - 1]; realbrlens = new int[inputs.length - 1]; realbclens = new int[inputs.length - 1]; realIndexes = new byte[inputs.length - 1]; byte realIndex = 0; for (byte i = 0; i < inputs.length; i++) { if (i == ins.input2) continue; realinputs[realIndex] = inputs[i]; realinputInfos[realIndex] = inputInfos[i]; if (i == ins.input1) { realrlens[realIndex] = rlens[ins.input2]; realclens[realIndex] = clens[ins.input2]; realbrlens[realIndex] = 1; realbclens[realIndex] = 1; realIndexes[realIndex] = ins.output; } else { realrlens[realIndex] = rlens[i]; realclens[realIndex] = clens[i]; realbrlens[realIndex] = brlens[i]; realbclens[realIndex] = bclens[i]; realIndexes[realIndex] = i; } realIndex++; } } else { //PickFromCompactInputFormat.setPickRecordsInEachPartFile(job, (NumItemsByEachReducerMetaData) inputInfos[ins.input1].metadata, ins.cst, 1-ins.cst); PickFromCompactInputFormat.setRangePickPartFiles(job, (MetaDataNumItemsByEachReducer) inputInfos[ins.input1].metadata, ins.cst, 1 - ins.cst); realrlens[ins.input1] = UtilFunctions.getLengthForInterQuantile( (MetaDataNumItemsByEachReducer) inputInfos[ins.input1].metadata, ins.cst); realclens[ins.input1] = clens[ins.input1]; realbrlens[ins.input1] = 1; realbclens[ins.input1] = 1; realIndexes[ins.input1] = ins.output; } } boolean resetDistCache = setupDistributedCache(job, instructionsInMapper, otherInstructionsInReducer, realinputs, realrlens, realclens); //set up the input files and their format information boolean[] distCacheOnly = getDistCacheOnlyInputs(realIndexes, recordReaderInstruction, instructionsInMapper, aggInstructionsInReducer, otherInstructionsInReducer); MRJobConfiguration.setUpMultipleInputs(job, realIndexes, realinputs, realinputInfos, realbrlens, realbclens, distCacheOnly, true, inBlockRepresentation ? ConvertTarget.BLOCK : ConvertTarget.CELL); MRJobConfiguration.setInputPartitioningInfo(job, pformats); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, realrlens, realclens); MRJobConfiguration.setDimsUnknownFilePrefix(job, dimsUnknownFilePrefix); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, realbrlens, realbclens); //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 instructions that will happen in the reducer, after the aggregation instructions MRJobConfiguration.setInstructionsInReducer(job, otherInstructionsInReducer); //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 map/reduce memory configurations (if in AM context) DMLConfig config = ConfigurationManager.getDMLConfig(); DMLAppMasterUtils.setupMRJobRemoteMaxMemory(job, config); //set up custom map/reduce configurations MRJobConfiguration.setupCustomMRConfigurations(job, config); //set up jvm reuse (incl. reuse of loaded dist cache matrices) 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, aggInstructionsInReducer, otherInstructionsInReducer, resultIndexes); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, null, otherInstructionsInReducer, resultIndexes, mapoutputIndexes, false); MatrixCharacteristics[] stats = ret.stats; //set up the number of reducers MRJobConfiguration.setNumReducers(job, ret.numReducerGroups, numReducers); // Print the complete instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); // Update resultDimsUnknown based on computed "stats" byte[] dimsUnknown = new byte[resultIndexes.length]; for (int i = 0; i < resultIndexes.length; i++) { if (stats[i].getRows() == -1 || stats[i].getCols() == -1) { dimsUnknown[i] = (byte) 1; } else { dimsUnknown[i] = (byte) 0; } } //MRJobConfiguration.updateResultDimsUnknown(job,resultDimsUnknown); //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, dimsUnknown, outputs, outputInfos, inBlockRepresentation, true); // configure mapper and the mapper output key value pairs job.setMapperClass(GMRMapper.class); if (numReducers == 0) { job.setMapOutputKeyClass(Writable.class); job.setMapOutputValueClass(Writable.class); } else { job.setMapOutputKeyClass(MatrixIndexes.class); if (inBlockRepresentation) job.setMapOutputValueClass(TaggedMatrixBlock.class); else job.setMapOutputValueClass(TaggedMatrixPackedCell.class); } //set up combiner if (numReducers != 0 && aggInstructionsInReducer != null && !aggInstructionsInReducer.isEmpty()) { job.setCombinerClass(GMRCombiner.class); } //configure reducer job.setReducerClass(GMRReducer.class); //job.setReducerClass(PassThroughReducer.class); // By default, the job executes in "cluster" mode. // Determine if we can optimize and run it in "local" mode. 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); Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) stats[i].setNonZeros(group.getCounter(Integer.toString(i))); //cleanups String dir = dimsUnknownFilePrefix + "/" + runjob.getID().toString() + "_dimsFile"; stats = MapReduceTool.processDimsFiles(dir, stats); MapReduceTool.deleteFileIfExistOnHDFS(dir); if (resetDistCache) MRBaseForCommonInstructions.resetDistCache(); return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
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 w w .ja v a 2 s. c om*/ //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.commoncrawl.mapred.segmenter.Segmenter.java
License:Open Source License
public static boolean generateCrawlSegments(long timestamp, String[] crawlerArray, Path bundleInputPath, Path finalOutputPath) {/*from w ww .ja va2s .c om*/ try { FileSystem fs = CrawlEnvironment.getDefaultFileSystem(); Configuration conf = CrawlEnvironment.getHadoopConfig(); final Path tempOutputDir = new Path( CrawlEnvironment.getHadoopConfig().get("mapred.temp.dir", ".") + System.currentTimeMillis()); JobConf job = new JobConf(conf); // compute crawlers string ... String crawlers = new String(); for (int i = 0; i < crawlerArray.length; ++i) { if (i != 0) crawlers += ","; crawlers += crawlerArray[i]; } LOG.info("Segment Generator: crawlers:" + crawlers); job.set(CrawlEnvironment.PROPERTY_CRAWLERS, crawlers); LOG.info("Crawler Count:" + crawlerArray.length); job.setInt(CrawlEnvironment.PROPERTY_NUM_CRAWLERS, crawlerArray.length); LOG.info("Num Buckets Per Crawler:" + NUM_BUCKETS_PER_CRAWLER); job.setInt(CrawlEnvironment.PROPERTY_NUM_BUCKETS_PER_CRAWLER, NUM_BUCKETS_PER_CRAWLER); job.setJobName("Generate Segments"); for (FileStatus candidate : fs.globStatus(new Path(bundleInputPath, "part-*"))) { LOG.info("Adding File:" + candidate.getPath()); job.addInputPath(candidate.getPath()); } // multi file merger job.setInputFormat(SequenceFileInputFormat.class); job.setMapOutputKeyClass(SegmentGeneratorBundleKey.class); job.setMapOutputValueClass(SegmentGeneratorItemBundle.class); job.setMapperClass(IdentityMapper.class); job.setReducerClass(SegmenterReducer.class); job.setPartitionerClass(BundleKeyPartitioner.class); job.setOutputKeyComparatorClass(BundleKeyComparator.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(NullWritable.class); job.setOutputFormat(SequenceFileOutputFormat.class); job.setOutputPath(tempOutputDir); job.setNumTasksToExecutePerJvm(1000); job.setNumReduceTasks(crawlerArray.length * NUM_BUCKETS_PER_CRAWLER); LOG.info("Running Segmenter OutputDir:" + tempOutputDir); JobClient.runJob(job); LOG.info("Finished Running Segmenter OutputDir:" + tempOutputDir + " Final Output Dir:" + finalOutputPath); fs.rename(tempOutputDir, finalOutputPath); return true; } catch (IOException e) { LOG.error(CCStringUtils.stringifyException(e)); return false; } }