Search in sources :

Example 66 with RunningJob

use of org.apache.hadoop.mapred.RunningJob in project systemml by apache.

the class CombineMR method runJob.

public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String combineInstructions, int numReducers, int replication, byte[] resultIndexes, String[] outputs, OutputInfo[] outputInfos) throws Exception {
    JobConf job;
    job = new JobConf(CombineMR.class);
    job.setJobName("Standalone-MR");
    boolean inBlockRepresentation = MRJobConfiguration.deriveRepresentation(inputInfos);
    // whether use block representation or cell representation
    MRJobConfiguration.setMatrixValueClass(job, inBlockRepresentation);
    byte[] inputIndexes = new byte[inputs.length];
    for (byte b = 0; b < inputs.length; b++) inputIndexes[b] = b;
    // set up the input files and their format information
    MRJobConfiguration.setUpMultipleInputs(job, inputIndexes, inputs, inputInfos, brlens, bclens, true, inBlockRepresentation ? ConvertTarget.BLOCK : ConvertTarget.CELL);
    // set up the dimensions of input matrices
    MRJobConfiguration.setMatricesDimensions(job, inputIndexes, rlens, clens);
    // set up the block size
    MRJobConfiguration.setBlocksSizes(job, inputIndexes, brlens, bclens);
    // set up unary instructions that will perform in the mapper
    MRJobConfiguration.setInstructionsInMapper(job, "");
    // set up the aggregate instructions that will happen in the combiner and reducer
    MRJobConfiguration.setAggregateInstructions(job, "");
    // set up the instructions that will happen in the reducer, after the aggregation instrucions
    MRJobConfiguration.setInstructionsInReducer(job, "");
    MRJobConfiguration.setCombineInstructions(job, combineInstructions);
    // 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 what matrices are needed to pass from the mapper to reducer
    HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, inputIndexes, null, null, combineInstructions, resultIndexes);
    // set up the multiple output files, and their format information
    MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, null, outputs, outputInfos, inBlockRepresentation);
    // configure mapper and the mapper output key value pairs
    job.setMapperClass(GMRMapper.class);
    job.setMapOutputKeyClass(MatrixIndexes.class);
    if (inBlockRepresentation)
        job.setMapOutputValueClass(TaggedMatrixBlock.class);
    else
        job.setMapOutputValueClass(TaggedMatrixCell.class);
    // configure reducer
    job.setReducerClass(InnerReducer.class);
    // job.setReducerClass(PassThroughReducer.class);
    MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, inputIndexes, null, null, null, combineInstructions, 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);
    // 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);
    return new JobReturn(stats, runjob.isSuccessful());
}
Also used : DMLConfig(org.apache.sysml.conf.DMLConfig) TaggedMatrixBlock(org.apache.sysml.runtime.matrix.data.TaggedMatrixBlock) MatrixChar_N_ReducerGroups(org.apache.sysml.runtime.matrix.mapred.MRJobConfiguration.MatrixChar_N_ReducerGroups) TaggedMatrixCell(org.apache.sysml.runtime.matrix.data.TaggedMatrixCell) RunningJob(org.apache.hadoop.mapred.RunningJob) JobConf(org.apache.hadoop.mapred.JobConf)

Example 67 with RunningJob

use of org.apache.hadoop.mapred.RunningJob in project 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());
}
Also used : Group(org.apache.hadoop.mapred.Counters.Group) DataGenMRInstruction(org.apache.sysml.runtime.instructions.mr.DataGenMRInstruction) InputInfo(org.apache.sysml.runtime.matrix.data.InputInfo) GMRCombiner(org.apache.sysml.runtime.matrix.mapred.GMRCombiner) FileSystem(org.apache.hadoop.fs.FileSystem) DataGenMRInstruction(org.apache.sysml.runtime.instructions.mr.DataGenMRInstruction) MRInstruction(org.apache.sysml.runtime.instructions.mr.MRInstruction) JobConf(org.apache.hadoop.mapred.JobConf) PrintWriter(java.io.PrintWriter) Path(org.apache.hadoop.fs.Path) DMLConfig(org.apache.sysml.conf.DMLConfig) SeqInstruction(org.apache.sysml.runtime.instructions.mr.SeqInstruction) RandInstruction(org.apache.sysml.runtime.instructions.mr.RandInstruction) MRType(org.apache.sysml.runtime.instructions.mr.MRInstruction.MRType) DMLRuntimeException(org.apache.sysml.runtime.DMLRuntimeException) MatrixChar_N_ReducerGroups(org.apache.sysml.runtime.matrix.mapred.MRJobConfiguration.MatrixChar_N_ReducerGroups) RunningJob(org.apache.hadoop.mapred.RunningJob) Well1024a(org.apache.commons.math3.random.Well1024a)

Example 68 with RunningJob

use of org.apache.hadoop.mapred.RunningJob in project systemml by apache.

the class GMR method runJob.

/**
 * Execute job.
 *
 * @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());
}
Also used : Group(org.apache.hadoop.mapred.Counters.Group) PickByCountInstruction(org.apache.sysml.runtime.instructions.mr.PickByCountInstruction) TaggedMatrixPackedCell(org.apache.sysml.runtime.matrix.data.TaggedMatrixPackedCell) InputInfo(org.apache.sysml.runtime.matrix.data.InputInfo) JobConf(org.apache.hadoop.mapred.JobConf) DMLConfig(org.apache.sysml.conf.DMLConfig) TaggedMatrixBlock(org.apache.sysml.runtime.matrix.data.TaggedMatrixBlock) MatrixChar_N_ReducerGroups(org.apache.sysml.runtime.matrix.mapred.MRJobConfiguration.MatrixChar_N_ReducerGroups) RunningJob(org.apache.hadoop.mapred.RunningJob)

Example 69 with RunningJob

use of org.apache.hadoop.mapred.RunningJob in project systemml by apache.

the class GroupedAggMR method runJob.

public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String grpAggInstructions, String simpleReduceInstructions, /*only scalar or reorg instructions allowed*/
int numReducers, int replication, byte[] resultIndexes, String dimsUnknownFilePrefix, String[] outputs, OutputInfo[] outputInfos) throws Exception {
    JobConf job = new JobConf(GroupedAggMR.class);
    job.setJobName("GroupedAgg-MR");
    // whether use block representation or cell representation
    // MRJobConfiguration.setMatrixValueClassForCM_N_COM(job, true);
    MRJobConfiguration.setMatrixValueClass(job, false);
    // 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;
    // set up the input files and their format information
    MRJobConfiguration.setUpMultipleInputs(job, realIndexes, realinputs, realinputInfos, realbrlens, realbclens, true, ConvertTarget.WEIGHTEDCELL);
    // 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 the grouped aggregate instructions that will happen in the combiner and reducer
    MRJobConfiguration.setGroupedAggInstructions(job, grpAggInstructions);
    // set up the instructions that will happen in the reducer, after the aggregation instrucions
    MRJobConfiguration.setInstructionsInReducer(job, simpleReduceInstructions);
    // set up the number of reducers
    MRJobConfiguration.setNumReducers(job, numReducers, numReducers);
    // 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 what matrices are needed to pass from the mapper to reducer
    MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, null, null, grpAggInstructions, resultIndexes);
    MatrixCharacteristics[] stats = new MatrixCharacteristics[resultIndexes.length];
    for (int i = 0; i < resultIndexes.length; i++) stats[i] = new MatrixCharacteristics();
    // Print the complete instruction
    if (LOG.isTraceEnabled())
        inst.printCompleteMRJobInstruction(stats);
    byte[] resultDimsUnknown = new byte[resultIndexes.length];
    // Update resultDimsUnknown based on computed "stats"
    for (int i = 0; i < resultIndexes.length; i++) resultDimsUnknown[i] = (byte) 2;
    // set up the multiple output files, and their format information
    MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, false);
    // configure mapper and the mapper output key value pairs
    job.setMapperClass(GroupedAggMRMapper.class);
    job.setCombinerClass(GroupedAggMRCombiner.class);
    job.setMapOutputKeyClass(TaggedMatrixIndexes.class);
    job.setMapOutputValueClass(WeightedCell.class);
    // configure reducer
    job.setReducerClass(GroupedAggMRReducer.class);
    // set unique working dir
    MRJobConfiguration.setUniqueWorkingDir(job);
    // execute job
    RunningJob runjob = JobClient.runJob(job);
    // get important output statistics
    Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS);
    for (int i = 0; i < resultIndexes.length; i++) {
        // number of non-zeros
        stats[i] = new MatrixCharacteristics();
        stats[i].setNonZeros(group.getCounter(Integer.toString(i)));
    }
    String dir = dimsUnknownFilePrefix + "/" + runjob.getID().toString() + "_dimsFile";
    stats = MapReduceTool.processDimsFiles(dir, stats);
    MapReduceTool.deleteFileIfExistOnHDFS(dir);
    return new JobReturn(stats, outputInfos, runjob.isSuccessful());
}
Also used : Group(org.apache.hadoop.mapred.Counters.Group) DMLConfig(org.apache.sysml.conf.DMLConfig) InputInfo(org.apache.sysml.runtime.matrix.data.InputInfo) RunningJob(org.apache.hadoop.mapred.RunningJob) JobConf(org.apache.hadoop.mapred.JobConf)

Example 70 with RunningJob

use of org.apache.hadoop.mapred.RunningJob in project systemml by apache.

the class MMCJMR 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 aggBinInstrction, int numReducers, int replication, String output, OutputInfo outputinfo) throws Exception {
    JobConf job = new JobConf(MMCJMR.class);
    // TODO: check w/ yuanyuan. This job always runs in blocked mode, and hence derivation is not necessary.
    boolean inBlockRepresentation = MRJobConfiguration.deriveRepresentation(inputInfos);
    // by default, assume that dimensions of MMCJ's output are known at compile time
    byte resultDimsUnknown = (byte) 0;
    MatrixCharacteristics[] stats = commonSetup(job, inBlockRepresentation, inputs, inputInfos, rlens, clens, brlens, bclens, instructionsInMapper, aggInstructionsInReducer, aggBinInstrction, numReducers, replication, resultDimsUnknown, output, outputinfo);
    // Print the complete instruction
    if (LOG.isTraceEnabled())
        inst.printCompleteMRJobInstruction(stats);
    // There is always a single output
    if (stats[0].getRows() == -1 || stats[0].getCols() == -1) {
        resultDimsUnknown = (byte) 1;
        // if the dimensions are unknown, then setup done in commonSetup() must be updated
        byte[] resultIndexes = new byte[] { MRInstructionParser.parseSingleInstruction(aggBinInstrction).output };
        byte[] resultDimsUnknown_Array = new byte[] { resultDimsUnknown };
        // set up the multiple output files, and their format information
        MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown_Array, new String[] { output }, new OutputInfo[] { outputinfo }, inBlockRepresentation);
    }
    AggregateBinaryInstruction ins = (AggregateBinaryInstruction) MRInstructionParser.parseSingleInstruction(aggBinInstrction);
    MatrixCharacteristics dim1 = MRJobConfiguration.getMatrixCharactristicsForBinAgg(job, ins.input1);
    MatrixCharacteristics dim2 = MRJobConfiguration.getMatrixCharactristicsForBinAgg(job, ins.input2);
    if (dim1.getRowsPerBlock() > dim1.getRows())
        dim1.setRowsPerBlock((int) dim1.getRows());
    if (dim1.getColsPerBlock() > dim1.getCols())
        dim1.setColsPerBlock((int) dim1.getCols());
    if (dim2.getRowsPerBlock() > dim2.getRows())
        dim2.setRowsPerBlock((int) dim2.getRows());
    if (dim2.getColsPerBlock() > dim2.getCols())
        dim2.setColsPerBlock((int) dim2.getCols());
    long blockSize1 = 77 + 8 * dim1.getRowsPerBlock() * dim1.getColsPerBlock();
    long blockSize2 = 77 + 8 * dim2.getRowsPerBlock() * dim2.getColsPerBlock();
    long blockSizeResult = 77 + 8 * dim1.getRowsPerBlock() * dim2.getColsPerBlock();
    long cacheSize = -1;
    // cache the first result
    if (dim1.getRows() < dim2.getCols()) {
        long numBlocks = (long) Math.ceil((double) dim1.getRows() / (double) dim1.getRowsPerBlock());
        cacheSize = numBlocks * (20 + blockSize1) + 32;
    } else // cache the second result
    {
        long numBlocks = (long) Math.ceil((double) dim2.getCols() / (double) dim2.getColsPerBlock());
        cacheSize = numBlocks * (20 + blockSize2) + 32;
    }
    // add known memory consumption (will be substracted from output buffer)
    cacheSize += // the cached key-value pair  (plus input instance)
    2 * Math.max(blockSize1, blockSize2) + // the cached single result
    blockSizeResult + // misc memory requirement by hadoop
    MRJobConfiguration.getMiscMemRequired(job);
    MRJobConfiguration.setMMCJCacheSize(job, (int) cacheSize);
    // set unique working dir
    MRJobConfiguration.setUniqueWorkingDir(job);
    // run mmcj job
    RunningJob runjob = JobClient.runJob(job);
    /* Process different counters */
    // NOTE: MMCJ job always has only a single output.
    // Hence, no need to scan resultIndexes[] like other jobs
    int outputIndex = 0;
    Byte outputMatrixID = MRInstructionParser.parseSingleInstruction(aggBinInstrction).output;
    Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS);
    // number of non-zeros
    stats[outputIndex].setNonZeros(group.getCounter(Byte.toString(outputMatrixID)));
    return new JobReturn(stats[outputIndex], outputinfo, runjob.isSuccessful());
}
Also used : Group(org.apache.hadoop.mapred.Counters.Group) AggregateBinaryInstruction(org.apache.sysml.runtime.instructions.mr.AggregateBinaryInstruction) RunningJob(org.apache.hadoop.mapred.RunningJob) JobConf(org.apache.hadoop.mapred.JobConf)

Aggregations

RunningJob (org.apache.hadoop.mapred.RunningJob)93 JobConf (org.apache.hadoop.mapred.JobConf)65 Path (org.apache.hadoop.fs.Path)49 JobClient (org.apache.hadoop.mapred.JobClient)33 IOException (java.io.IOException)28 FileSystem (org.apache.hadoop.fs.FileSystem)28 DMLConfig (org.apache.sysml.conf.DMLConfig)27 Group (org.apache.hadoop.mapred.Counters.Group)26 Counters (org.apache.hadoop.mapred.Counters)17 Configuration (org.apache.hadoop.conf.Configuration)14 MatrixChar_N_ReducerGroups (org.apache.sysml.runtime.matrix.mapred.MRJobConfiguration.MatrixChar_N_ReducerGroups)13 InputInfo (org.apache.sysml.runtime.matrix.data.InputInfo)10 DMLRuntimeException (org.apache.sysml.runtime.DMLRuntimeException)8 File (java.io.File)6 TaggedMatrixBlock (org.apache.sysml.runtime.matrix.data.TaggedMatrixBlock)6 DataOutputStream (java.io.DataOutputStream)5 URI (java.net.URI)5 FSDataOutputStream (org.apache.hadoop.fs.FSDataOutputStream)5 Context (org.apache.hadoop.hive.ql.Context)5 Text (org.apache.hadoop.io.Text)5