Examples with SparkBatchSinkFactory io.cdap.cdap.etl.spark.batch.SparkBatchSinkFactory used on opensource projects

Example 1 with SparkBatchSinkFactory

use of io.cdap.cdap.etl.spark.batch.SparkBatchSinkFactory in project cdap by caskdata.

the class StreamingMultiSinkFunction method call.

@Override
public void call(JavaRDD<RecordInfo<Object>> data, Time batchTime) throws Exception {
    long logicalStartTime = batchTime.milliseconds();
    MacroEvaluator evaluator = new DefaultMacroEvaluator(new BasicArguments(sec), logicalStartTime, sec.getSecureStore(), sec.getServiceDiscoverer(), sec.getNamespace());
    PluginContext pluginContext = new SparkPipelinePluginContext(sec.getPluginContext(), sec.getMetrics(), phaseSpec.isStageLoggingEnabled(), phaseSpec.isProcessTimingEnabled());
    SparkBatchSinkFactory sinkFactory = new SparkBatchSinkFactory();
    PipelineRuntime pipelineRuntime = new SparkPipelineRuntime(sec, logicalStartTime);
    Map<String, SubmitterLifecycle<?>> stages = createStages(evaluator);
    // call prepareRun() on all the stages in the group
    // need to call it in an order that guarantees that inputs are called before outputs
    // this is because plugins can call getArguments().set() in the prepareRun() method,
    // which downstream stages should be able to read
    List<String> traversalOrder = new ArrayList(group.size());
    for (String stageName : phaseSpec.getPhase().getDag().getTopologicalOrder()) {
        if (group.contains(stageName)) {
            traversalOrder.add(stageName);
        }
    }
    for (String stageName : traversalOrder) {
        SubmitterLifecycle<?> plugin = stages.get(stageName);
        StageSpec stageSpec = phaseSpec.getPhase().getStage(stageName);
        try {
            prepareRun(pipelineRuntime, sinkFactory, stageSpec, plugin);
        } catch (Exception e) {
            LOG.error("Error preparing sink {} for the batch for time {}.", stageName, logicalStartTime, e);
            return;
        }
    }
    // run the actual transforms and sinks in this group
    boolean ranSuccessfully = true;
    try {
        MultiSinkFunction multiSinkFunction = new MultiSinkFunction(sec, phaseSpec, group, collectors);
        Set<String> outputNames = sinkFactory.writeCombinedRDD(data.flatMapToPair(multiSinkFunction), sec, sinkNames);
        sec.execute(new TxRunnable() {

            @Override
            public void run(DatasetContext context) throws Exception {
                for (String outputName : outputNames) {
                    ExternalDatasets.registerLineage(sec.getAdmin(), outputName, AccessType.WRITE, null, () -> context.getDataset(outputName));
                }
            }
        });
    } catch (Exception e) {
        LOG.error("Error writing to sinks {} for the batch for time {}.", sinkNames, logicalStartTime, e);
        ranSuccessfully = false;
    }
    // run onRunFinish() for each sink
    for (String stageName : traversalOrder) {
        SubmitterLifecycle<?> plugin = stages.get(stageName);
        StageSpec stageSpec = phaseSpec.getPhase().getStage(stageName);
        try {
            onRunFinish(pipelineRuntime, sinkFactory, stageSpec, plugin, ranSuccessfully);
        } catch (Exception e) {
            LOG.warn("Unable to execute onRunFinish for sink {}", stageName, e);
        }
    }
}

Example 2 with SparkBatchSinkFactory

use of io.cdap.cdap.etl.spark.batch.SparkBatchSinkFactory in project cdap by caskdata.

the class StreamingBatchSinkFunction method call.

@Override
public void call(JavaRDD<T> data, Time batchTime) throws Exception {
    final long logicalStartTime = batchTime.milliseconds();
    MacroEvaluator evaluator = new DefaultMacroEvaluator(new BasicArguments(sec), logicalStartTime, sec.getSecureStore(), sec.getServiceDiscoverer(), sec.getNamespace());
    PluginContext pluginContext = new SparkPipelinePluginContext(sec.getPluginContext(), sec.getMetrics(), stageSpec.isStageLoggingEnabled(), stageSpec.isProcessTimingEnabled());
    final SparkBatchSinkFactory sinkFactory = new SparkBatchSinkFactory();
    final String stageName = stageSpec.getName();
    final BatchSink<Object, Object, Object> batchSink = pluginContext.newPluginInstance(stageName, evaluator);
    final PipelineRuntime pipelineRuntime = new SparkPipelineRuntime(sec, logicalStartTime);
    boolean isPrepared = false;
    boolean isDone = false;
    try {
        sec.execute(new TxRunnable() {

            @Override
            public void run(DatasetContext datasetContext) throws Exception {
                SparkBatchSinkContext sinkContext = new SparkBatchSinkContext(sinkFactory, sec, datasetContext, pipelineRuntime, stageSpec);
                batchSink.prepareRun(sinkContext);
            }
        });
        isPrepared = true;
        PluginFunctionContext pluginFunctionContext = new PluginFunctionContext(stageSpec, sec, pipelineRuntime.getArguments().asMap(), batchTime.milliseconds(), new NoopStageStatisticsCollector());
        Set<String> outputNames = sinkFactory.writeFromRDD(data.flatMapToPair(new BatchSinkFunction<T, Object, Object>(pluginFunctionContext, functionCache)), sec, stageName);
        sec.execute(new TxRunnable() {

            @Override
            public void run(DatasetContext context) throws Exception {
                for (String outputName : outputNames) {
                    ExternalDatasets.registerLineage(sec.getAdmin(), outputName, AccessType.WRITE, null, () -> context.getDataset(outputName));
                }
            }
        });
        isDone = true;
        sec.execute(new TxRunnable() {

            @Override
            public void run(DatasetContext datasetContext) throws Exception {
                SparkBatchSinkContext sinkContext = new SparkBatchSinkContext(sinkFactory, sec, datasetContext, pipelineRuntime, stageSpec);
                batchSink.onRunFinish(true, sinkContext);
            }
        });
    } catch (Exception e) {
        LOG.error("Error writing to sink {} for the batch for time {}.", stageName, logicalStartTime, e);
    } finally {
        if (isPrepared && !isDone) {
            sec.execute(new TxRunnable() {

                @Override
                public void run(DatasetContext datasetContext) throws Exception {
                    SparkBatchSinkContext sinkContext = new SparkBatchSinkContext(sinkFactory, sec, datasetContext, pipelineRuntime, stageSpec);
                    batchSink.onRunFinish(false, sinkContext);
                }
            });
        }
    }
}

Example 3 with SparkBatchSinkFactory

use of io.cdap.cdap.etl.spark.batch.SparkBatchSinkFactory in project cdap by caskdata.

the class AbstractSparkPreparer method prepare.

@Override
public List<Finisher> prepare(PhaseSpec phaseSpec) throws TransactionFailureException, InstantiationException, IOException {
    stageOperations = new HashMap<>();
    stagePartitions = new HashMap<>();
    sourceFactory = new SparkBatchSourceFactory();
    sinkFactory = new SparkBatchSinkFactory();
    return super.prepare(phaseSpec);
}