Examples with SparkPipelineRuntime co.cask.cdap.etl.spark.SparkPipelineRuntime used on opensource projects

Example 1 with SparkPipelineRuntime

use of co.cask.cdap.etl.spark.SparkPipelineRuntime in project cdap by caskdata.

the class StreamingBatchSinkFunction method call.

@Override
public Void call(JavaRDD<T> data, Time batchTime) throws Exception {
    if (data.isEmpty()) {
        return null;
    }
    final long logicalStartTime = batchTime.milliseconds();
    MacroEvaluator evaluator = new DefaultMacroEvaluator(new BasicArguments(sec), logicalStartTime, sec.getSecureStore(), 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());
        PairFlatMapFunc<T, Object, Object> sinkFunction = new BatchSinkFunction<T, Object, Object>(pluginFunctionContext);
        sinkFactory.writeFromRDD(data.flatMapToPair(Compat.convert(sinkFunction)), sec, stageName, Object.class, Object.class);
        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);
                }
            });
        }
    }
    return null;
}

Example 2 with SparkPipelineRuntime

use of co.cask.cdap.etl.spark.SparkPipelineRuntime in project cdap by caskdata.

the class DStreamCollection method compute.

@Override
public <U> SparkCollection<U> compute(final StageSpec stageSpec, SparkCompute<T, U> compute) throws Exception {
    final SparkCompute<T, U> wrappedCompute = new DynamicSparkCompute<>(new DynamicDriverContext(stageSpec, sec, new NoopStageStatisticsCollector()), compute);
    Transactionals.execute(sec, new TxRunnable() {

        @Override
        public void run(DatasetContext datasetContext) throws Exception {
            PipelineRuntime pipelineRuntime = new SparkPipelineRuntime(sec);
            SparkExecutionPluginContext sparkPluginContext = new BasicSparkExecutionPluginContext(sec, JavaSparkContext.fromSparkContext(stream.context().sparkContext()), datasetContext, pipelineRuntime, stageSpec);
            wrappedCompute.initialize(sparkPluginContext);
        }
    }, Exception.class);
    return wrap(stream.transform(new ComputeTransformFunction<>(sec, stageSpec, wrappedCompute)));
}

Example 3 with SparkPipelineRuntime

use of co.cask.cdap.etl.spark.SparkPipelineRuntime in project cdap by caskdata.

the class StreamingSparkSinkFunction method call.

@Override
public Void call(JavaRDD<T> data, Time batchTime) throws Exception {
    if (data.isEmpty()) {
        return null;
    }
    final long logicalStartTime = batchTime.milliseconds();
    MacroEvaluator evaluator = new DefaultMacroEvaluator(new BasicArguments(sec), logicalStartTime, sec.getSecureStore(), sec.getNamespace());
    final PluginContext pluginContext = new SparkPipelinePluginContext(sec.getPluginContext(), sec.getMetrics(), stageSpec.isStageLoggingEnabled(), stageSpec.isProcessTimingEnabled());
    final PipelineRuntime pipelineRuntime = new SparkPipelineRuntime(sec, batchTime.milliseconds());
    final String stageName = stageSpec.getName();
    final SparkSink<T> sparkSink = pluginContext.newPluginInstance(stageName, evaluator);
    boolean isPrepared = false;
    boolean isDone = false;
    try {
        sec.execute(new TxRunnable() {

            @Override
            public void run(DatasetContext datasetContext) throws Exception {
                SparkPluginContext context = new BasicSparkPluginContext(null, pipelineRuntime, stageSpec, datasetContext, sec.getAdmin());
                sparkSink.prepareRun(context);
            }
        });
        isPrepared = true;
        final SparkExecutionPluginContext sparkExecutionPluginContext = new SparkStreamingExecutionContext(sec, JavaSparkContext.fromSparkContext(data.rdd().context()), logicalStartTime, stageSpec);
        final JavaRDD<T> countedRDD = data.map(new CountingFunction<T>(stageName, sec.getMetrics(), "records.in", null)).cache();
        sec.execute(new TxRunnable() {

            @Override
            public void run(DatasetContext context) throws Exception {
                sparkSink.run(sparkExecutionPluginContext, countedRDD);
            }
        });
        isDone = true;
        sec.execute(new TxRunnable() {

            @Override
            public void run(DatasetContext datasetContext) throws Exception {
                SparkPluginContext context = new BasicSparkPluginContext(null, pipelineRuntime, stageSpec, datasetContext, sec.getAdmin());
                sparkSink.onRunFinish(true, context);
            }
        });
    } catch (Exception e) {
        LOG.error("Error while executing 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 {
                    SparkPluginContext context = new BasicSparkPluginContext(null, pipelineRuntime, stageSpec, datasetContext, sec.getAdmin());
                    sparkSink.onRunFinish(false, context);
                }
            });
        }
    }
    return null;
}

Example 4 with SparkPipelineRuntime

use of co.cask.cdap.etl.spark.SparkPipelineRuntime in project cdap by caskdata.

the class RDDCollection method publishAlerts.

@Override
public void publishAlerts(StageSpec stageSpec, StageStatisticsCollector collector) throws Exception {
    PluginFunctionContext pluginFunctionContext = new PluginFunctionContext(stageSpec, sec, collector);
    AlertPublisher alertPublisher = pluginFunctionContext.createPlugin();
    PipelineRuntime pipelineRuntime = new SparkPipelineRuntime(sec);
    AlertPublisherContext alertPublisherContext = new DefaultAlertPublisherContext(pipelineRuntime, stageSpec, sec.getMessagingContext(), sec.getAdmin());
    alertPublisher.initialize(alertPublisherContext);
    StageMetrics stageMetrics = new DefaultStageMetrics(sec.getMetrics(), stageSpec.getName());
    TrackedIterator<Alert> trackedAlerts = new TrackedIterator<>(((JavaRDD<Alert>) rdd).collect().iterator(), stageMetrics, Constants.Metrics.RECORDS_IN);
    alertPublisher.publish(trackedAlerts);
    alertPublisher.destroy();
}

Example 5 with SparkPipelineRuntime

use of co.cask.cdap.etl.spark.SparkPipelineRuntime in project cdap by caskdata.

the class RDDCollection method store.

@Override
public void store(StageSpec stageSpec, SparkSink<T> sink) throws Exception {
    String stageName = stageSpec.getName();
    PipelineRuntime pipelineRuntime = new SparkPipelineRuntime(sec);
    SparkExecutionPluginContext sparkPluginContext = new BasicSparkExecutionPluginContext(sec, jsc, datasetContext, pipelineRuntime, stageSpec);
    JavaRDD<T> countedRDD = rdd.map(new CountingFunction<T>(stageName, sec.getMetrics(), "records.in", null)).cache();
    sink.run(sparkPluginContext, countedRDD);
}