Examples with RDDObject org.apache.sysml.runtime.instructions.spark.data.RDDObject used on opensource projects

Example 26 with RDDObject

use of org.apache.sysml.runtime.instructions.spark.data.RDDObject in project incubator-systemml by apache.

the class CheckpointSPInstruction method processInstruction.

@Override
@SuppressWarnings("unchecked")
public void processInstruction(ExecutionContext ec) {
    SparkExecutionContext sec = (SparkExecutionContext) ec;
    // this is valid if relevant branches are never entered)
    if (sec.getVariable(input1.getName()) == null || sec.getVariable(input1.getName()) instanceof BooleanObject) {
        // add a dummy entry to the input, which will be immediately overwritten by the null output.
        sec.setVariable(input1.getName(), new BooleanObject(false));
        sec.setVariable(output.getName(), new BooleanObject(false));
        return;
    }
    // -------
    // (for csv input files with unknown dimensions, we might have generated a checkpoint after
    // csvreblock although not necessary because the csvreblock was subject to in-memory reblock)
    CacheableData<?> obj = sec.getCacheableData(input1.getName());
    if (obj.isCached(true)) {
        // available in memory
        sec.setVariable(output.getName(), obj);
        return;
    }
    // get input rdd handle (for matrix or frame)
    JavaPairRDD<?, ?> in = sec.getRDDHandleForVariable(input1.getName(), InputInfo.BinaryBlockInputInfo);
    MatrixCharacteristics mcIn = sec.getMatrixCharacteristics(input1.getName());
    // Step 2: Checkpoint given rdd (only if currently in different storage level to prevent redundancy)
    // -------
    // Note that persist is an transformation which will be triggered on-demand with the next rdd operations
    // This prevents unnecessary overhead if the dataset is only consumed by cp operations.
    JavaPairRDD<?, ?> out = null;
    if (!in.getStorageLevel().equals(_level)) {
        // (trigger coalesce if intended number of partitions exceeded by 20%
        // and not hash partitioned to avoid losing the existing partitioner)
        int numPartitions = SparkUtils.getNumPreferredPartitions(mcIn, in);
        boolean coalesce = (1.2 * numPartitions < in.getNumPartitions() && !SparkUtils.isHashPartitioned(in) && in.getNumPartitions() > SparkExecutionContext.getDefaultParallelism(true));
        // checkpoint pre-processing rdd operations
        if (coalesce) {
            // merge partitions without shuffle if too many partitions
            out = in.coalesce(numPartitions);
        } else {
            // apply a narrow shallow copy to allow for short-circuit collects
            if (input1.getDataType() == DataType.MATRIX)
                out = SparkUtils.copyBinaryBlockMatrix((JavaPairRDD<MatrixIndexes, MatrixBlock>) in, false);
            else if (input1.getDataType() == DataType.FRAME)
                out = ((JavaPairRDD<Long, FrameBlock>) in).mapValues(new CopyFrameBlockFunction(false));
        }
        // convert mcsr into memory-efficient csr if potentially sparse
        if (input1.getDataType() == DataType.MATRIX && OptimizerUtils.checkSparseBlockCSRConversion(mcIn) && !_level.equals(Checkpoint.SER_STORAGE_LEVEL)) {
            out = ((JavaPairRDD<MatrixIndexes, MatrixBlock>) out).mapValues(new CreateSparseBlockFunction(SparseBlock.Type.CSR));
        }
        // actual checkpoint into given storage level
        out = out.persist(_level);
        // otherwise these their nnz would never be evaluated due to lazy evaluation in spark
        if (input1.isMatrix() && mcIn.dimsKnown() && !mcIn.dimsKnown(true) && !OptimizerUtils.isValidCPDimensions(mcIn)) {
            mcIn.setNonZeros(SparkUtils.getNonZeros((JavaPairRDD<MatrixIndexes, MatrixBlock>) out));
        }
    } else {
        // pass-through
        out = in;
    }
    // Step 3: In-place update of input matrix/frame rdd handle and set as output
    // -------
    // We use this in-place approach for two reasons. First, it is correct because our checkpoint
    // injection rewrites guarantee that after checkpoint instructions there are no consumers on the
    // given input. Second, it is beneficial because otherwise we need to pass in-memory objects and
    // filenames to the new matrix object in order to prevent repeated reads from hdfs and unnecessary
    // caching and subsequent collects. Note that in-place update requires us to explicitly handle
    // lineage information in order to prevent cycles on cleanup.
    CacheableData<?> cd = sec.getCacheableData(input1.getName());
    if (out != in) {
        // prevent unnecessary lineage info
        // guaranteed to exist (see above)
        RDDObject inro = cd.getRDDHandle();
        // create new rdd object
        RDDObject outro = new RDDObject(out);
        // mark as checkpointed
        outro.setCheckpointRDD(true);
        // keep lineage to prevent cycles on cleanup
        outro.addLineageChild(inro);
        cd.setRDDHandle(outro);
    }
    sec.setVariable(output.getName(), cd);
}

Example 27 with RDDObject

use of org.apache.sysml.runtime.instructions.spark.data.RDDObject in project incubator-systemml by apache.

the class SparkExecutionContext method cleanupMatrixObject.

@Override
public void cleanupMatrixObject(MatrixObject mo) throws DMLRuntimeException {
    try {
        if (mo.isCleanupEnabled()) {
            //compute ref count only if matrix cleanup actually necessary
            if (!getVariables().hasReferences(mo)) {
                //clean cached data
                mo.clearData();
                //clean hdfs data if no pending rdd operations on it
                if (mo.isHDFSFileExists() && mo.getFileName() != null) {
                    if (mo.getRDDHandle() == null) {
                        MapReduceTool.deleteFileWithMTDIfExistOnHDFS(mo.getFileName());
                    } else {
                        //deferred file removal
                        RDDObject rdd = mo.getRDDHandle();
                        rdd.setHDFSFilename(mo.getFileName());
                    }
                }
                //note: requires that mo.clearData already removed back references
                if (mo.getRDDHandle() != null) {
                    rCleanupLineageObject(mo.getRDDHandle());
                }
                if (mo.getBroadcastHandle() != null) {
                    rCleanupLineageObject(mo.getBroadcastHandle());
                }
            }
        }
    } catch (Exception ex) {
        throw new DMLRuntimeException(ex);
    }
}

Example 28 with RDDObject

use of org.apache.sysml.runtime.instructions.spark.data.RDDObject in project incubator-systemml by apache.

the class MLContextConversionUtil method javaRDDStringIJVToMatrixObject.

/**
	 * Convert a {@code JavaRDD<String>} in IJV format to a {@code MatrixObject}
	 * . Note that metadata is required for IJV format.
	 * 
	 * @param variableName
	 *            name of the variable associated with the matrix
	 * @param javaRDD
	 *            the Java RDD of strings
	 * @param matrixMetadata
	 *            matrix metadata
	 * @return the {@code JavaRDD<String>} converted to a {@code MatrixObject}
	 */
public static MatrixObject javaRDDStringIJVToMatrixObject(String variableName, JavaRDD<String> javaRDD, MatrixMetadata matrixMetadata) {
    JavaPairRDD<LongWritable, Text> javaPairRDD = javaRDD.mapToPair(new ConvertStringToLongTextPair());
    MatrixCharacteristics mc = (matrixMetadata != null) ? matrixMetadata.asMatrixCharacteristics() : new MatrixCharacteristics();
    MatrixObject matrixObject = new MatrixObject(ValueType.DOUBLE, OptimizerUtils.getUniqueTempFileName(), new MatrixFormatMetaData(mc, OutputInfo.TextCellOutputInfo, InputInfo.TextCellInputInfo));
    JavaPairRDD<LongWritable, Text> javaPairRDD2 = javaPairRDD.mapToPair(new CopyTextInputFunction());
    matrixObject.setRDDHandle(new RDDObject(javaPairRDD2, variableName));
    return matrixObject;
}

Example 29 with RDDObject

use of org.apache.sysml.runtime.instructions.spark.data.RDDObject in project incubator-systemml by apache.

the class MLContextConversionUtil method javaRDDStringCSVToMatrixObject.

/**
	 * Convert a {@code JavaRDD<String>} in CSV format to a {@code MatrixObject}
	 * 
	 * @param variableName
	 *            name of the variable associated with the matrix
	 * @param javaRDD
	 *            the Java RDD of strings
	 * @param matrixMetadata
	 *            matrix metadata
	 * @return the {@code JavaRDD<String>} converted to a {@code MatrixObject}
	 */
public static MatrixObject javaRDDStringCSVToMatrixObject(String variableName, JavaRDD<String> javaRDD, MatrixMetadata matrixMetadata) {
    JavaPairRDD<LongWritable, Text> javaPairRDD = javaRDD.mapToPair(new ConvertStringToLongTextPair());
    MatrixCharacteristics mc = (matrixMetadata != null) ? matrixMetadata.asMatrixCharacteristics() : new MatrixCharacteristics();
    MatrixObject matrixObject = new MatrixObject(ValueType.DOUBLE, OptimizerUtils.getUniqueTempFileName(), new MatrixFormatMetaData(mc, OutputInfo.CSVOutputInfo, InputInfo.CSVInputInfo));
    JavaPairRDD<LongWritable, Text> javaPairRDD2 = javaPairRDD.mapToPair(new CopyTextInputFunction());
    matrixObject.setRDDHandle(new RDDObject(javaPairRDD2, variableName));
    return matrixObject;
}

Example 30 with RDDObject

use of org.apache.sysml.runtime.instructions.spark.data.RDDObject in project incubator-systemml by apache.

the class MLContextConversionUtil method javaRDDStringIJVToFrameObject.

/**
	 * Convert a {@code JavaRDD<String>} in IJV format to a {@code FrameObject}
	 * . Note that metadata is required for IJV format.
	 * 
	 * @param variableName
	 *            name of the variable associated with the frame
	 * @param javaRDD
	 *            the Java RDD of strings
	 * @param frameMetadata
	 *            frame metadata
	 * @return the {@code JavaRDD<String>} converted to a {@code FrameObject}
	 */
public static FrameObject javaRDDStringIJVToFrameObject(String variableName, JavaRDD<String> javaRDD, FrameMetadata frameMetadata) {
    JavaPairRDD<LongWritable, Text> javaPairRDD = javaRDD.mapToPair(new ConvertStringToLongTextPair());
    MatrixCharacteristics mc = (frameMetadata != null) ? frameMetadata.asMatrixCharacteristics() : new MatrixCharacteristics();
    JavaPairRDD<LongWritable, Text> javaPairRDDText = javaPairRDD.mapToPair(new CopyTextInputFunction());
    FrameObject frameObject = new FrameObject(OptimizerUtils.getUniqueTempFileName(), new MatrixFormatMetaData(mc, OutputInfo.BinaryBlockOutputInfo, InputInfo.BinaryBlockInputInfo), frameMetadata.getFrameSchema().getSchema().toArray(new ValueType[0]));
    JavaPairRDD<Long, FrameBlock> rdd;
    try {
        ValueType[] lschema = null;
        if (lschema == null)
            lschema = UtilFunctions.nCopies((int) mc.getCols(), ValueType.STRING);
        rdd = FrameRDDConverterUtils.textCellToBinaryBlock(jsc(), javaPairRDDText, mc, lschema);
    } catch (DMLRuntimeException e) {
        e.printStackTrace();
        return null;
    }
    frameObject.setRDDHandle(new RDDObject(rdd, variableName));
    return frameObject;
}