Examples with JavaPairRDD org.apache.spark.api.java.JavaPairRDD used on opensource projects

Example 81 with JavaPairRDD

use of org.apache.spark.api.java.JavaPairRDD in project systemml by apache.

the class ResultMergeRemoteSpark method setRDDHandleForMerge.

@SuppressWarnings("unchecked")
private static void setRDDHandleForMerge(MatrixObject mo, SparkExecutionContext sec) {
    InputInfo iinfo = InputInfo.BinaryBlockInputInfo;
    JavaSparkContext sc = sec.getSparkContext();
    JavaPairRDD<MatrixIndexes, MatrixBlock> rdd = (JavaPairRDD<MatrixIndexes, MatrixBlock>) sc.hadoopFile(mo.getFileName(), iinfo.inputFormatClass, iinfo.inputKeyClass, iinfo.inputValueClass);
    RDDObject rddhandle = new RDDObject(rdd);
    rddhandle.setHDFSFile(true);
    mo.setRDDHandle(rddhandle);
}

Example 82 with JavaPairRDD

use of org.apache.spark.api.java.JavaPairRDD in project systemml by apache.

the class ResultMergeRemoteSpark method executeMerge.

@SuppressWarnings("unchecked")
protected RDDObject executeMerge(MatrixObject compare, MatrixObject[] inputs, long rlen, long clen, int brlen, int bclen) {
    String jobname = "ParFor-RMSP";
    long t0 = DMLScript.STATISTICS ? System.nanoTime() : 0;
    SparkExecutionContext sec = (SparkExecutionContext) _ec;
    boolean withCompare = (compare != null);
    RDDObject ret = null;
    // determine degree of parallelism
    int numRed = (int) determineNumReducers(rlen, clen, brlen, bclen, _numReducers);
    // sanity check for empty src files
    if (inputs == null || inputs.length == 0)
        throw new DMLRuntimeException("Execute merge should never be called with no inputs.");
    try {
        // note: initial implementation via union over all result rdds discarded due to
        // stack overflow errors with many parfor tasks, and thus many rdds
        // Step 1: construct input rdd from all result files of parfor workers
        // a) construct job conf with all files
        InputInfo ii = InputInfo.BinaryBlockInputInfo;
        JobConf job = new JobConf(ResultMergeRemoteMR.class);
        job.setJobName(jobname);
        job.setInputFormat(ii.inputFormatClass);
        Path[] paths = new Path[inputs.length];
        for (int i = 0; i < paths.length; i++) {
            // ensure input exists on hdfs (e.g., if in-memory or RDD)
            inputs[i].exportData();
            paths[i] = new Path(inputs[i].getFileName());
            // update rdd handle to allow lazy evaluation by guarding
            // against cleanup of temporary result files
            setRDDHandleForMerge(inputs[i], sec);
        }
        FileInputFormat.setInputPaths(job, paths);
        // b) create rdd from input files w/ deep copy of keys and blocks
        JavaPairRDD<MatrixIndexes, MatrixBlock> rdd = sec.getSparkContext().hadoopRDD(job, ii.inputFormatClass, ii.inputKeyClass, ii.inputValueClass).mapPartitionsToPair(new CopyBlockPairFunction(true), true);
        // Step 2a: merge with compare
        JavaPairRDD<MatrixIndexes, MatrixBlock> out = null;
        if (withCompare) {
            JavaPairRDD<MatrixIndexes, MatrixBlock> compareRdd = (JavaPairRDD<MatrixIndexes, MatrixBlock>) sec.getRDDHandleForMatrixObject(compare, InputInfo.BinaryBlockInputInfo);
            // merge values which differ from compare values
            ResultMergeRemoteSparkWCompare cfun = new ResultMergeRemoteSparkWCompare(_isAccum);
            out = // group all result blocks per key
            rdd.groupByKey(numRed).join(// join compare block and result blocks
            compareRdd).mapToPair(// merge result blocks w/ compare
            cfun);
        } else // Step 2b: merge without compare
        {
            // direct merge in any order (disjointness guaranteed)
            out = _isAccum ? RDDAggregateUtils.sumByKeyStable(rdd, false) : RDDAggregateUtils.mergeByKey(rdd, false);
        }
        // Step 3: create output rdd handle w/ lineage
        ret = new RDDObject(out);
        for (int i = 0; i < paths.length; i++) ret.addLineageChild(inputs[i].getRDDHandle());
        if (withCompare)
            ret.addLineageChild(compare.getRDDHandle());
    } catch (Exception ex) {
        throw new DMLRuntimeException(ex);
    }
    // maintain statistics
    Statistics.incrementNoOfCompiledSPInst();
    Statistics.incrementNoOfExecutedSPInst();
    if (DMLScript.STATISTICS) {
        Statistics.maintainCPHeavyHitters(jobname, System.nanoTime() - t0);
    }
    return ret;
}

Example 83 with JavaPairRDD

use of org.apache.spark.api.java.JavaPairRDD in project systemml by apache.

the class RemoteDPParForSpark method getPartitionedInput.

@SuppressWarnings("unchecked")
private static JavaPairRDD<Long, Writable> getPartitionedInput(SparkExecutionContext sec, String matrixvar, OutputInfo oi, PartitionFormat dpf) {
    InputInfo ii = InputInfo.BinaryBlockInputInfo;
    MatrixObject mo = sec.getMatrixObject(matrixvar);
    MatrixCharacteristics mc = mo.getMatrixCharacteristics();
    // NOTE: there will always be a checkpoint rdd on top of the input rdd and the dataset
    if (hasInputDataSet(dpf, mo)) {
        DatasetObject dsObj = (DatasetObject) mo.getRDDHandle().getLineageChilds().get(0).getLineageChilds().get(0);
        Dataset<Row> in = dsObj.getDataset();
        // construct or reuse row ids
        JavaPairRDD<Row, Long> prepinput = dsObj.containsID() ? in.javaRDD().mapToPair(new DataFrameExtractIDFunction(in.schema().fieldIndex(RDDConverterUtils.DF_ID_COLUMN))) : // zip row index
        in.javaRDD().zipWithIndex();
        // convert row to row in matrix block format
        return prepinput.mapToPair(new DataFrameToRowBinaryBlockFunction(mc.getCols(), dsObj.isVectorBased(), dsObj.containsID()));
    } else // binary block input rdd without grouping
    if (!requiresGrouping(dpf, mo)) {
        // get input rdd and data partitioning
        JavaPairRDD<MatrixIndexes, MatrixBlock> in = sec.getBinaryBlockRDDHandleForVariable(matrixvar);
        DataPartitionerRemoteSparkMapper dpfun = new DataPartitionerRemoteSparkMapper(mc, ii, oi, dpf._dpf, dpf._N);
        return in.flatMapToPair(dpfun);
    } else // default binary block input rdd with grouping
    {
        // get input rdd, avoid unnecessary caching if input is checkpoint and not cached yet
        // to reduce memory pressure for shuffle and subsequent
        JavaPairRDD<MatrixIndexes, MatrixBlock> in = sec.getBinaryBlockRDDHandleForVariable(matrixvar);
        if (mo.getRDDHandle().isCheckpointRDD() && !sec.isRDDCached(in.id()))
            in = (JavaPairRDD<MatrixIndexes, MatrixBlock>) ((RDDObject) mo.getRDDHandle().getLineageChilds().get(0)).getRDD();
        // data partitioning of input rdd
        DataPartitionerRemoteSparkMapper dpfun = new DataPartitionerRemoteSparkMapper(mc, ii, oi, dpf._dpf, dpf._N);
        return in.flatMapToPair(dpfun);
    }
}

Example 84 with JavaPairRDD

use of org.apache.spark.api.java.JavaPairRDD in project systemml by apache.

the class SparkExecutionContext method getRDDHandleForFrameObject.

/**
 * FIXME: currently this implementation assumes matrix representations but frame signature
 * in order to support the old transform implementation.
 *
 * @param fo frame object
 * @param inputInfo input info
 * @return JavaPairRDD handle for a frame object
 */
@SuppressWarnings("unchecked")
public JavaPairRDD<?, ?> getRDDHandleForFrameObject(FrameObject fo, InputInfo inputInfo) {
    // NOTE: MB this logic should be integrated into FrameObject
    // However, for now we cannot assume that spark libraries are
    // always available and hence only store generic references in
    // matrix object while all the logic is in the SparkExecContext
    InputInfo inputInfo2 = (inputInfo == InputInfo.BinaryBlockInputInfo) ? InputInfo.BinaryBlockFrameInputInfo : inputInfo;
    JavaSparkContext sc = getSparkContext();
    JavaPairRDD<?, ?> rdd = null;
    // rdd operations if already executed and cached
    if (fo.getRDDHandle() != null && (fo.getRDDHandle().isCheckpointRDD() || !fo.isCached(false))) {
        // return existing rdd handling (w/o input format change)
        rdd = fo.getRDDHandle().getRDD();
    } else // CASE 2: dirty in memory data or cached result of rdd operations
    if (fo.isDirty() || fo.isCached(false)) {
        // get in-memory matrix block and parallelize it
        // w/ guarded parallelize (fallback to export, rdd from file if too large)
        MatrixCharacteristics mc = fo.getMatrixCharacteristics();
        boolean fromFile = false;
        if (!OptimizerUtils.checkSparkCollectMemoryBudget(mc, 0) || !_parRDDs.reserve(OptimizerUtils.estimatePartitionedSizeExactSparsity(mc))) {
            if (fo.isDirty()) {
                // write only if necessary
                fo.exportData();
            }
            rdd = sc.hadoopFile(fo.getFileName(), inputInfo2.inputFormatClass, inputInfo2.inputKeyClass, inputInfo2.inputValueClass);
            // cp is workaround for read bug
            rdd = ((JavaPairRDD<LongWritable, FrameBlock>) rdd).mapToPair(new CopyFrameBlockPairFunction());
            fromFile = true;
        } else {
            // default case
            // pin frame in memory
            FrameBlock fb = fo.acquireRead();
            rdd = toFrameJavaPairRDD(sc, fb);
            // unpin frame
            fo.release();
            _parRDDs.registerRDD(rdd.id(), OptimizerUtils.estimatePartitionedSizeExactSparsity(mc), true);
        }
        // keep rdd handle for future operations on it
        RDDObject rddhandle = new RDDObject(rdd);
        rddhandle.setHDFSFile(fromFile);
        fo.setRDDHandle(rddhandle);
    } else // CASE 3: non-dirty (file exists on HDFS)
    {
        // For binary block, these are: SequenceFileInputFormat.class, MatrixIndexes.class, MatrixBlock.class
        if (inputInfo2 == InputInfo.BinaryBlockFrameInputInfo) {
            rdd = sc.hadoopFile(fo.getFileName(), inputInfo2.inputFormatClass, inputInfo2.inputKeyClass, inputInfo2.inputValueClass);
            // note: this copy is still required in Spark 1.4 because spark hands out whatever the inputformat
            // recordreader returns; the javadoc explicitly recommend to copy all key/value pairs
            // cp is workaround for read bug
            rdd = ((JavaPairRDD<LongWritable, FrameBlock>) rdd).mapToPair(new CopyFrameBlockPairFunction());
        } else if (inputInfo2 == InputInfo.TextCellInputInfo || inputInfo2 == InputInfo.CSVInputInfo || inputInfo2 == InputInfo.MatrixMarketInputInfo) {
            rdd = sc.hadoopFile(fo.getFileName(), inputInfo2.inputFormatClass, inputInfo2.inputKeyClass, inputInfo2.inputValueClass);
            // cp is workaround for read bug
            rdd = ((JavaPairRDD<LongWritable, Text>) rdd).mapToPair(new CopyTextInputFunction());
        } else if (inputInfo2 == InputInfo.BinaryCellInputInfo) {
            throw new DMLRuntimeException("Binarycell not supported for frames.");
        } else {
            throw new DMLRuntimeException("Incorrect input format in getRDDHandleForVariable");
        }
        // keep rdd handle for future operations on it
        RDDObject rddhandle = new RDDObject(rdd);
        rddhandle.setHDFSFile(true);
        fo.setRDDHandle(rddhandle);
    }
    return rdd;
}

Example 85 with JavaPairRDD

use of org.apache.spark.api.java.JavaPairRDD in project systemml by apache.

the class SparkExecutionContext method cacheMatrixObject.

@SuppressWarnings("unchecked")
public void cacheMatrixObject(String var) {
    // get input rdd and default storage level
    MatrixObject mo = getMatrixObject(var);
    // double check size to avoid unnecessary spark context creation
    if (!OptimizerUtils.exceedsCachingThreshold(mo.getNumColumns(), (double) OptimizerUtils.estimateSizeExactSparsity(mo.getMatrixCharacteristics())))
        return;
    JavaPairRDD<MatrixIndexes, MatrixBlock> in = (JavaPairRDD<MatrixIndexes, MatrixBlock>) getRDDHandleForMatrixObject(mo, InputInfo.BinaryBlockInputInfo);
    // persist rdd (force rdd caching, if not already cached)
    if (!isRDDCached(in.id()))
        // trigger caching to prevent contention
        in.count();
}