Examples with Group org.apache.hadoop.mapred.Counters.Group used on opensource projects

Example 11 with Group

use of org.apache.hadoop.mapred.Counters.Group in project incubator-systemml by apache.

the class CSVReblockMR method runAssignRowIDMRJob.

public static AssignRowIDMRReturn runAssignRowIDMRJob(String[] inputs, InputInfo[] inputInfos, int[] brlens, int[] bclens, String reblockInstructions, int replication, String[] smallestFiles) throws Exception {
    AssignRowIDMRReturn ret = new AssignRowIDMRReturn();
    JobConf job;
    job = new JobConf(CSVReblockMR.class);
    job.setJobName("Assign-RowID-MR");
    byte[] realIndexes = new byte[inputs.length];
    for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;
    // set up the input files and their format information
    MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, false, ConvertTarget.CELL);
    job.setStrings(SMALLEST_FILE_NAME_PER_INPUT, smallestFiles);
    // set up the aggregate instructions that will happen in the combiner and reducer
    MRJobConfiguration.setCSVReblockInstructions(job, reblockInstructions);
    // set up the replication factor for the results
    job.setInt(MRConfigurationNames.DFS_REPLICATION, replication);
    // set up custom map/reduce configurations
    DMLConfig config = ConfigurationManager.getDMLConfig();
    MRJobConfiguration.setupCustomMRConfigurations(job, config);
    // set up the number of reducers
    job.setNumReduceTasks(1);
    // Print the complete instruction
    // if (LOG.isTraceEnabled())
    // inst.printCompelteMRJobInstruction();
    // configure mapper and the mapper output key value pairs
    job.setMapperClass(CSVAssignRowIDMapper.class);
    job.setMapOutputKeyClass(ByteWritable.class);
    job.setMapOutputValueClass(OffsetCount.class);
    // configure reducer
    job.setReducerClass(CSVAssignRowIDReducer.class);
    // turn off adaptivemr
    job.setBoolean("adaptivemr.map.enable", false);
    // set unique working dir
    MRJobConfiguration.setUniqueWorkingDir(job);
    // set up the output file
    ret.counterFile = new Path(MRJobConfiguration.constructTempOutputFilename());
    job.setOutputFormat(SequenceFileOutputFormat.class);
    FileOutputFormat.setOutputPath(job, ret.counterFile);
    job.setOutputKeyClass(ByteWritable.class);
    job.setOutputValueClass(OffsetCount.class);
    RunningJob runjob = JobClient.runJob(job);
    /* Process different counters */
    Group rgroup = runjob.getCounters().getGroup(NUM_ROWS_IN_MATRIX);
    Group cgroup = runjob.getCounters().getGroup(NUM_COLS_IN_MATRIX);
    ret.rlens = new long[inputs.length];
    ret.clens = new long[inputs.length];
    for (int i = 0; i < inputs.length; i++) {
        // number of non-zeros
        ret.rlens[i] = rgroup.getCounter(Integer.toString(i));
        ret.clens[i] = cgroup.getCounter(Integer.toString(i));
    }
    return ret;
}

Example 12 with Group

use of org.apache.hadoop.mapred.Counters.Group in project incubator-systemml by apache.

the class DataGenMR method runJob.

/**
 * <p>Starts a Rand MapReduce job which will produce one or more random objects.</p>
 *
 * @param inst MR job instruction
 * @param dataGenInstructions array of data gen instructions
 * @param instructionsInMapper instructions in mapper
 * @param aggInstructionsInReducer aggregate instructions in reducer
 * @param otherInstructionsInReducer other instructions in reducer
 * @param numReducers number of reducers
 * @param replication file replication
 * @param resultIndexes result indexes for each random object
 * @param dimsUnknownFilePrefix file path prefix when dimensions unknown
 * @param outputs output file for each random object
 * @param outputInfos output information for each random object
 * @return matrix characteristics for each random object
 * @throws Exception if Exception occurs
 */
public static JobReturn runJob(MRJobInstruction inst, String[] dataGenInstructions, String instructionsInMapper, String aggInstructionsInReducer, String otherInstructionsInReducer, int numReducers, int replication, byte[] resultIndexes, String dimsUnknownFilePrefix, String[] outputs, OutputInfo[] outputInfos) throws Exception {
    JobConf job = new JobConf(DataGenMR.class);
    job.setJobName("DataGen-MR");
    // whether use block representation or cell representation
    MRJobConfiguration.setMatrixValueClass(job, true);
    byte[] realIndexes = new byte[dataGenInstructions.length];
    for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;
    String[] inputs = new String[dataGenInstructions.length];
    InputInfo[] inputInfos = new InputInfo[dataGenInstructions.length];
    long[] rlens = new long[dataGenInstructions.length];
    long[] clens = new long[dataGenInstructions.length];
    int[] brlens = new int[dataGenInstructions.length];
    int[] bclens = new int[dataGenInstructions.length];
    FileSystem fs = FileSystem.get(job);
    String dataGenInsStr = "";
    int numblocks = 0;
    int maxbrlen = -1, maxbclen = -1;
    double maxsparsity = -1;
    for (int i = 0; i < dataGenInstructions.length; i++) {
        dataGenInsStr = dataGenInsStr + Lop.INSTRUCTION_DELIMITOR + dataGenInstructions[i];
        MRInstruction mrins = MRInstructionParser.parseSingleInstruction(dataGenInstructions[i]);
        MRType mrtype = mrins.getMRInstructionType();
        DataGenMRInstruction genInst = (DataGenMRInstruction) mrins;
        rlens[i] = genInst.getRows();
        clens[i] = genInst.getCols();
        brlens[i] = genInst.getRowsInBlock();
        bclens[i] = genInst.getColsInBlock();
        maxbrlen = Math.max(maxbrlen, brlens[i]);
        maxbclen = Math.max(maxbclen, bclens[i]);
        if (mrtype == MRType.Rand) {
            RandInstruction randInst = (RandInstruction) mrins;
            inputs[i] = LibMatrixDatagen.generateUniqueSeedPath(genInst.getBaseDir());
            maxsparsity = Math.max(maxsparsity, randInst.getSparsity());
            PrintWriter pw = null;
            try {
                pw = new PrintWriter(fs.create(new Path(inputs[i])));
                // for obj reuse and preventing repeated buffer re-allocations
                StringBuilder sb = new StringBuilder();
                // seed generation
                Well1024a bigrand = LibMatrixDatagen.setupSeedsForRand(randInst.getSeed());
                for (long r = 0; r < Math.max(rlens[i], 1); r += brlens[i]) {
                    long curBlockRowSize = Math.min(brlens[i], (rlens[i] - r));
                    for (long c = 0; c < Math.max(clens[i], 1); c += bclens[i]) {
                        long curBlockColSize = Math.min(bclens[i], (clens[i] - c));
                        sb.append((r / brlens[i]) + 1);
                        sb.append(',');
                        sb.append((c / bclens[i]) + 1);
                        sb.append(',');
                        sb.append(curBlockRowSize);
                        sb.append(',');
                        sb.append(curBlockColSize);
                        sb.append(',');
                        sb.append(bigrand.nextLong());
                        pw.println(sb.toString());
                        sb.setLength(0);
                        numblocks++;
                    }
                }
            } finally {
                IOUtilFunctions.closeSilently(pw);
            }
            inputInfos[i] = InputInfo.TextCellInputInfo;
        } else if (mrtype == MRType.Seq) {
            SeqInstruction seqInst = (SeqInstruction) mrins;
            inputs[i] = genInst.getBaseDir() + System.currentTimeMillis() + ".seqinput";
            // always dense
            maxsparsity = 1.0;
            double from = seqInst.fromValue;
            double to = seqInst.toValue;
            double incr = seqInst.incrValue;
            // handle default 1 to -1 for special case of from>to
            incr = LibMatrixDatagen.updateSeqIncr(from, to, incr);
            // Correctness checks on (from, to, incr)
            boolean neg = (from > to);
            if (incr == 0)
                throw new DMLRuntimeException("Invalid value for \"increment\" in seq().");
            if (neg != (incr < 0))
                throw new DMLRuntimeException("Wrong sign for the increment in a call to seq()");
            // Compute the number of rows in the sequence
            long numrows = UtilFunctions.getSeqLength(from, to, incr);
            if (rlens[i] > 0) {
                if (numrows != rlens[i])
                    throw new DMLRuntimeException("Unexpected error while processing sequence instruction. Expected number of rows does not match given number: " + rlens[i] + " != " + numrows);
            } else {
                rlens[i] = numrows;
            }
            if (clens[i] > 0 && clens[i] != 1)
                throw new DMLRuntimeException("Unexpected error while processing sequence instruction. Number of columns (" + clens[i] + ") must be equal to 1.");
            else
                clens[i] = 1;
            PrintWriter pw = null;
            try {
                pw = new PrintWriter(fs.create(new Path(inputs[i])));
                StringBuilder sb = new StringBuilder();
                double temp = from;
                double block_from, block_to;
                for (long r = 0; r < rlens[i]; r += brlens[i]) {
                    long curBlockRowSize = Math.min(brlens[i], (rlens[i] - r));
                    // block (bid_i,bid_j) generates a sequence from the interval [block_from, block_to] (inclusive of both end points of the interval)
                    long bid_i = ((r / brlens[i]) + 1);
                    long bid_j = 1;
                    block_from = temp;
                    block_to = temp + (curBlockRowSize - 1) * incr;
                    // next block starts from here
                    temp = block_to + incr;
                    sb.append(bid_i);
                    sb.append(',');
                    sb.append(bid_j);
                    sb.append(',');
                    sb.append(block_from);
                    sb.append(',');
                    sb.append(block_to);
                    sb.append(',');
                    sb.append(incr);
                    pw.println(sb.toString());
                    sb.setLength(0);
                    numblocks++;
                }
            } finally {
                IOUtilFunctions.closeSilently(pw);
            }
            inputInfos[i] = InputInfo.TextCellInputInfo;
        } else {
            throw new DMLRuntimeException("Unexpected Data Generation Instruction Type: " + mrtype);
        }
    }
    // remove the first ","
    dataGenInsStr = dataGenInsStr.substring(1);
    RunningJob runjob;
    MatrixCharacteristics[] stats;
    try {
        // set up the block size
        MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens);
        // set up the input files and their format information
        MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, false, ConvertTarget.BLOCK);
        // set up the dimensions of input matrices
        MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens);
        MRJobConfiguration.setDimsUnknownFilePrefix(job, dimsUnknownFilePrefix);
        // set up the block size
        MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens);
        // set up the rand Instructions
        MRJobConfiguration.setRandInstructions(job, dataGenInsStr);
        // 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 instrucions
        MRJobConfiguration.setInstructionsInReducer(job, otherInstructionsInReducer);
        // set up the replication factor for the results
        job.setInt(MRConfigurationNames.DFS_REPLICATION, replication);
        // 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);
        // determine degree of parallelism (nmappers: 1<=n<=capacity)
        // TODO use maxsparsity whenever we have a way of generating sparse rand data
        int capacity = InfrastructureAnalyzer.getRemoteParallelMapTasks();
        long dfsblocksize = InfrastructureAnalyzer.getHDFSBlockSize();
        // correction max number of mappers on yarn clusters
        if (InfrastructureAnalyzer.isYarnEnabled())
            capacity = (int) Math.max(capacity, YarnClusterAnalyzer.getNumCores());
        int nmapers = Math.max(Math.min((int) (8 * maxbrlen * maxbclen * (long) numblocks / dfsblocksize), capacity), 1);
        job.setNumMapTasks(nmapers);
        // set up what matrices are needed to pass from the mapper to reducer
        HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, dataGenInsStr, instructionsInMapper, null, aggInstructionsInReducer, otherInstructionsInReducer, resultIndexes);
        MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, dataGenInsStr, instructionsInMapper, null, aggInstructionsInReducer, null, otherInstructionsInReducer, resultIndexes, mapoutputIndexes, false);
        stats = ret.stats;
        // set up the number of reducers
        MRJobConfiguration.setNumReducers(job, ret.numReducerGroups, numReducers);
        // print the complete MRJob 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;
            }
        }
        boolean mayContainCtable = instructionsInMapper.contains("ctabletransform") || instructionsInMapper.contains("groupedagg");
        // set up the multiple output files, and their format information
        MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, true, mayContainCtable);
        // configure mapper and the mapper output key value pairs
        job.setMapperClass(DataGenMapper.class);
        if (numReducers == 0) {
            job.setMapOutputKeyClass(Writable.class);
            job.setMapOutputValueClass(Writable.class);
        } else {
            job.setMapOutputKeyClass(MatrixIndexes.class);
            job.setMapOutputValueClass(TaggedMatrixBlock.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);
        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)));
        }
        String dir = dimsUnknownFilePrefix + "/" + runjob.getID().toString() + "_dimsFile";
        stats = MapReduceTool.processDimsFiles(dir, stats);
        MapReduceTool.deleteFileIfExistOnHDFS(dir);
    } finally {
        for (String input : inputs) MapReduceTool.deleteFileIfExistOnHDFS(new Path(input), job);
    }
    return new JobReturn(stats, outputInfos, runjob.isSuccessful());
}

Example 13 with Group

use of org.apache.hadoop.mapred.Counters.Group in project incubator-systemml by apache.

the class MMRJMR method runJob.

public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String instructionsInMapper, String aggInstructionsInReducer, String aggBinInstrctions, String otherInstructionsInReducer, int numReducers, int replication, byte[] resultIndexes, String[] outputs, OutputInfo[] outputInfos) throws Exception {
    JobConf job = new JobConf(MMRJMR.class);
    job.setJobName("MMRJ-MR");
    if (numReducers <= 0)
        throw new Exception("MMRJ-MR has to have at least one reduce task!");
    // TODO: check w/ yuanyuan. This job always runs in blocked mode, and hence derivation is not necessary.
    boolean inBlockRepresentation = MRJobConfiguration.deriveRepresentation(inputInfos);
    // 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;
    // 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, aggBinInstrctions);
    // 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);
    // 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);
    // 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, aggBinInstrctions, resultIndexes);
    MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, aggBinInstrctions, 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);
    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;
        }
    }
    // set up the multiple output files, and their format information
    MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, dimsUnknown, outputs, outputInfos, inBlockRepresentation);
    // configure mapper
    job.setMapperClass(MMRJMRMapper.class);
    job.setMapOutputKeyClass(TripleIndexes.class);
    if (inBlockRepresentation)
        job.setMapOutputValueClass(TaggedMatrixBlock.class);
    else
        job.setMapOutputValueClass(TaggedMatrixCell.class);
    job.setOutputKeyComparatorClass(TripleIndexes.Comparator.class);
    job.setPartitionerClass(TripleIndexes.FirstTwoIndexesPartitioner.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);
    // configure reducer
    job.setReducerClass(MMRJMRReducer.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);
    /* 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());
}

Example 14 with Group

use of org.apache.hadoop.mapred.Counters.Group in project incubator-systemml by apache.

the class ReblockMR method runJob.

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;
    // 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);
    // 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);
    // represent key offsets for block
    job.setMapOutputKeyClass(MatrixIndexes.class);
    // binary cell/block
    job.setMapOutputValueClass(TaggedAdaptivePartialBlock.class);
    // 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++) {
        stats[i].setNonZeros(group.getCounter(Integer.toString(i)));
    }
    return new JobReturn(stats, outputInfos, runjob.isSuccessful());
}

Example 15 with Group

use of org.apache.hadoop.mapred.Counters.Group in project incubator-systemml by apache.

the class SortMR method runJob.

@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);
        // 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);
    // 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);
        // double
        job.setOutputKeyClass(outputInfo.outputKeyClass);
        // int
        job.setOutputValueClass(outputInfo.outputValueClass);
    }
    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());
    }
}