Examples with SparkPipelineTranslator org.apache.beam.runners.spark.translation.SparkPipelineTranslator used on opensource projects

Example 1 with SparkPipelineTranslator

use of org.apache.beam.runners.spark.translation.SparkPipelineTranslator in project beam by apache.

the class SparkRunnerStreamingContextFactory method call.

@Override
public JavaStreamingContext call() throws Exception {
    LOG.info("Creating a new Spark Streaming Context");
    // validate unbounded read properties.
    checkArgument(options.getMinReadTimeMillis() < options.getBatchIntervalMillis(), "Minimum read time has to be less than batch time.");
    checkArgument(options.getReadTimePercentage() > 0 && options.getReadTimePercentage() < 1, "Read time percentage is bound to (0, 1).");
    SparkPipelineTranslator translator = new StreamingTransformTranslator.Translator(new TransformTranslator.Translator());
    Duration batchDuration = new Duration(options.getBatchIntervalMillis());
    LOG.info("Setting Spark streaming batchDuration to {} msec", batchDuration.milliseconds());
    JavaSparkContext jsc = SparkContextFactory.getSparkContext(options);
    JavaStreamingContext jssc = new JavaStreamingContext(jsc, batchDuration);
    // We must first init accumulators since translators expect them to be instantiated.
    SparkRunner.initAccumulators(options, jsc);
    // do not need to create a MetricsPusher instance here because if is called in SparkRunner.run()
    EvaluationContext ctxt = new EvaluationContext(jsc, pipeline, options, jssc);
    // update cache candidates
    SparkRunner.updateCacheCandidates(pipeline, translator, ctxt);
    pipeline.traverseTopologically(new SparkRunner.Evaluator(translator, ctxt));
    ctxt.computeOutputs();
    checkpoint(jssc, checkpointDir);
    return jssc;
}

Example 2 with SparkPipelineTranslator

use of org.apache.beam.runners.spark.translation.SparkPipelineTranslator in project beam by apache.

the class SparkRunner method run.

@Override
public SparkPipelineResult run(final Pipeline pipeline) {
    LOG.info("Executing pipeline using the SparkRunner.");
    final SparkPipelineResult result;
    final Future<?> startPipeline;
    final SparkPipelineTranslator translator;
    final ExecutorService executorService = Executors.newSingleThreadExecutor();
    MetricsEnvironment.setMetricsSupported(true);
    // visit the pipeline to determine the translation mode
    detectTranslationMode(pipeline);
    // TODO(BEAM-10670): Use SDF read as default when we address performance issue.
    if (!ExperimentalOptions.hasExperiment(pipeline.getOptions(), "beam_fn_api")) {
        SplittableParDo.convertReadBasedSplittableDoFnsToPrimitiveReadsIfNecessary(pipeline);
    }
    pipeline.replaceAll(SparkTransformOverrides.getDefaultOverrides(pipelineOptions.isStreaming()));
    prepareFilesToStage(pipelineOptions);
    final long startTime = Instant.now().getMillis();
    EventLoggingListener eventLoggingListener = null;
    JavaSparkContext jsc = null;
    if (pipelineOptions.isStreaming()) {
        CheckpointDir checkpointDir = new CheckpointDir(pipelineOptions.getCheckpointDir());
        SparkRunnerStreamingContextFactory streamingContextFactory = new SparkRunnerStreamingContextFactory(pipeline, pipelineOptions, checkpointDir);
        final JavaStreamingContext jssc = JavaStreamingContext.getOrCreate(checkpointDir.getSparkCheckpointDir().toString(), streamingContextFactory);
        jsc = jssc.sparkContext();
        eventLoggingListener = startEventLoggingListener(jsc, pipelineOptions, startTime);
        // Checkpoint aggregator/metrics values
        jssc.addStreamingListener(new JavaStreamingListenerWrapper(new AggregatorsAccumulator.AccumulatorCheckpointingSparkListener()));
        jssc.addStreamingListener(new JavaStreamingListenerWrapper(new MetricsAccumulator.AccumulatorCheckpointingSparkListener()));
        // register user-defined listeners.
        for (JavaStreamingListener listener : pipelineOptions.as(SparkContextOptions.class).getListeners()) {
            LOG.info("Registered listener {}." + listener.getClass().getSimpleName());
            jssc.addStreamingListener(new JavaStreamingListenerWrapper(listener));
        }
        // register Watermarks listener to broadcast the advanced WMs.
        jssc.addStreamingListener(new JavaStreamingListenerWrapper(new WatermarkAdvancingStreamingListener()));
        // The reason we call initAccumulators here even though it is called in
        // SparkRunnerStreamingContextFactory is because the factory is not called when resuming
        // from checkpoint (When not resuming from checkpoint initAccumulators will be called twice
        // but this is fine since it is idempotent).
        initAccumulators(pipelineOptions, jssc.sparkContext());
        startPipeline = executorService.submit(() -> {
            LOG.info("Starting streaming pipeline execution.");
            jssc.start();
        });
        executorService.shutdown();
        result = new SparkPipelineResult.StreamingMode(startPipeline, jssc);
    } else {
        jsc = SparkContextFactory.getSparkContext(pipelineOptions);
        eventLoggingListener = startEventLoggingListener(jsc, pipelineOptions, startTime);
        final EvaluationContext evaluationContext = new EvaluationContext(jsc, pipeline, pipelineOptions);
        translator = new TransformTranslator.Translator();
        // update the cache candidates
        updateCacheCandidates(pipeline, translator, evaluationContext);
        initAccumulators(pipelineOptions, jsc);
        startPipeline = executorService.submit(() -> {
            pipeline.traverseTopologically(new Evaluator(translator, evaluationContext));
            evaluationContext.computeOutputs();
            LOG.info("Batch pipeline execution complete.");
        });
        executorService.shutdown();
        result = new SparkPipelineResult.BatchMode(startPipeline, jsc);
    }
    if (pipelineOptions.getEnableSparkMetricSinks()) {
        registerMetricsSource(pipelineOptions.getAppName());
    }
    // it would have been better to create MetricsPusher from runner-core but we need
    // runner-specific
    // MetricsContainerStepMap
    MetricsPusher metricsPusher = new MetricsPusher(MetricsAccumulator.getInstance().value(), pipelineOptions.as(MetricsOptions.class), result);
    metricsPusher.start();
    if (eventLoggingListener != null && jsc != null) {
        eventLoggingListener.onApplicationStart(SparkCompat.buildSparkListenerApplicationStart(jsc, pipelineOptions, startTime, result));
        eventLoggingListener.onApplicationEnd(new SparkListenerApplicationEnd(Instant.now().getMillis()));
        eventLoggingListener.stop();
    }
    return result;
}

Example 3 with SparkPipelineTranslator

use of org.apache.beam.runners.spark.translation.SparkPipelineTranslator in project beam by apache.

the class SparkRunnerDebugger method run.

@Override
public SparkPipelineResult run(Pipeline pipeline) {
    boolean isStreaming = options.isStreaming() || options.as(TestSparkPipelineOptions.class).isForceStreaming();
    // TODO(BEAM-10670): Use SDF read as default when we address performance issue.
    if (!ExperimentalOptions.hasExperiment(pipeline.getOptions(), "beam_fn_api")) {
        SplittableParDo.convertReadBasedSplittableDoFnsToPrimitiveReadsIfNecessary(pipeline);
    }
    JavaSparkContext jsc = new JavaSparkContext("local[1]", "Debug_Pipeline");
    JavaStreamingContext jssc = new JavaStreamingContext(jsc, new org.apache.spark.streaming.Duration(1000));
    SparkRunner.initAccumulators(options, jsc);
    TransformTranslator.Translator translator = new TransformTranslator.Translator();
    SparkNativePipelineVisitor visitor;
    if (isStreaming) {
        SparkPipelineTranslator streamingTranslator = new StreamingTransformTranslator.Translator(translator);
        EvaluationContext ctxt = new EvaluationContext(jsc, pipeline, options, jssc);
        visitor = new SparkNativePipelineVisitor(streamingTranslator, ctxt);
    } else {
        EvaluationContext ctxt = new EvaluationContext(jsc, pipeline, options, jssc);
        visitor = new SparkNativePipelineVisitor(translator, ctxt);
    }
    pipeline.traverseTopologically(visitor);
    jsc.stop();
    String debugString = visitor.getDebugString();
    LOG.info("Translated Native Spark pipeline:\n" + debugString);
    return new DebugSparkPipelineResult(debugString);
}