Examples with Duration org.apache.spark.streaming.Duration used on opensource projects

Example 1 with Duration

use of org.apache.spark.streaming.Duration in project learning-spark by databricks.

the class Flags method setFromCommandLineArgs.

public static void setFromCommandLineArgs(Options options, String[] args) {
    CommandLineParser parser = new PosixParser();
    try {
        CommandLine cl = parser.parse(options, args);
        THE_INSTANCE.windowLength = new Duration(Integer.parseInt(cl.getOptionValue(LogAnalyzerAppMain.WINDOW_LENGTH, "30")) * 1000);
        THE_INSTANCE.slideInterval = new Duration(Integer.parseInt(cl.getOptionValue(LogAnalyzerAppMain.SLIDE_INTERVAL, "5")) * 1000);
        THE_INSTANCE.logsDirectory = cl.getOptionValue(LogAnalyzerAppMain.LOGS_DIRECTORY, "/tmp/logs");
        THE_INSTANCE.outputHtmlFile = cl.getOptionValue(LogAnalyzerAppMain.OUTPUT_HTML_FILE, "/tmp/log_stats.html");
        THE_INSTANCE.checkpointDirectory = cl.getOptionValue(LogAnalyzerAppMain.CHECKPOINT_DIRECTORY, "/tmp/log-analyzer-streaming");
        THE_INSTANCE.indexHtmlTemplate = cl.getOptionValue(LogAnalyzerAppMain.INDEX_HTML_TEMPLATE, "./src/main/resources/index.html.template");
        THE_INSTANCE.outputDirectory = cl.getOptionValue(LogAnalyzerAppMain.OUTPUT_DIRECTORY, "/tmp/pandaout");
        THE_INSTANCE.initialized = true;
    } catch (ParseException e) {
        THE_INSTANCE.initialized = false;
        System.err.println("Parsing failed.  Reason: " + e.getMessage());
    }
}

Example 2 with Duration

use of org.apache.spark.streaming.Duration in project learning-spark by databricks.

the class KafkaInput method main.

public static void main(String[] args) throws Exception {
    String zkQuorum = args[0];
    String group = args[1];
    SparkConf conf = new SparkConf().setAppName("KafkaInput");
    // Create a StreamingContext with a 1 second batch size
    JavaStreamingContext jssc = new JavaStreamingContext(conf, new Duration(1000));
    Map<String, Integer> topics = new HashMap<String, Integer>();
    topics.put("pandas", 1);
    JavaPairDStream<String, String> input = KafkaUtils.createStream(jssc, zkQuorum, group, topics);
    input.print();
    // start our streaming context and wait for it to "finish"
    jssc.start();
    // Wait for 10 seconds then exit. To run forever call without a timeout
    jssc.awaitTermination(10000);
    // Stop the streaming context
    jssc.stop();
}

Example 3 with Duration

use of org.apache.spark.streaming.Duration in project beam by apache.

the class SparkGroupAlsoByWindowViaWindowSet method groupAlsoByWindow.

public static <K, InputT, W extends BoundedWindow> JavaDStream<WindowedValue<KV<K, Iterable<InputT>>>> groupAlsoByWindow(JavaDStream<WindowedValue<KV<K, Iterable<WindowedValue<InputT>>>>> inputDStream, final Coder<K> keyCoder, final Coder<WindowedValue<InputT>> wvCoder, final WindowingStrategy<?, W> windowingStrategy, final SparkRuntimeContext runtimeContext, final List<Integer> sourceIds) {
    final IterableCoder<WindowedValue<InputT>> itrWvCoder = IterableCoder.of(wvCoder);
    final Coder<InputT> iCoder = ((FullWindowedValueCoder<InputT>) wvCoder).getValueCoder();
    final Coder<? extends BoundedWindow> wCoder = ((FullWindowedValueCoder<InputT>) wvCoder).getWindowCoder();
    final Coder<WindowedValue<KV<K, Iterable<InputT>>>> wvKvIterCoder = FullWindowedValueCoder.of(KvCoder.of(keyCoder, IterableCoder.of(iCoder)), wCoder);
    final TimerInternals.TimerDataCoder timerDataCoder = TimerInternals.TimerDataCoder.of(windowingStrategy.getWindowFn().windowCoder());
    long checkpointDurationMillis = runtimeContext.getPipelineOptions().as(SparkPipelineOptions.class).getCheckpointDurationMillis();
    // we have to switch to Scala API to avoid Optional in the Java API, see: SPARK-4819.
    // we also have a broader API for Scala (access to the actual key and entire iterator).
    // we use coders to convert objects in the PCollection to byte arrays, so they
    // can be transferred over the network for the shuffle and be in serialized form
    // for checkpointing.
    // for readability, we add comments with actual type next to byte[].
    // to shorten line length, we use:
    //---- WV: WindowedValue
    //---- Iterable: Itr
    //---- AccumT: A
    //---- InputT: I
    DStream<Tuple2<ByteArray, byte[]>> /*Itr<WV<I>>*/
    pairDStream = inputDStream.transformToPair(new Function<JavaRDD<WindowedValue<KV<K, Iterable<WindowedValue<InputT>>>>>, JavaPairRDD<ByteArray, byte[]>>() {

        // we use mapPartitions with the RDD API because its the only available API
        // that allows to preserve partitioning.
        @Override
        public JavaPairRDD<ByteArray, byte[]> call(JavaRDD<WindowedValue<KV<K, Iterable<WindowedValue<InputT>>>>> rdd) throws Exception {
            return rdd.mapPartitions(TranslationUtils.functionToFlatMapFunction(WindowingHelpers.<KV<K, Iterable<WindowedValue<InputT>>>>unwindowFunction()), true).mapPartitionsToPair(TranslationUtils.<K, Iterable<WindowedValue<InputT>>>toPairFlatMapFunction(), true).mapPartitionsToPair(TranslationUtils.pairFunctionToPairFlatMapFunction(CoderHelpers.toByteFunction(keyCoder, itrWvCoder)), true);
        }
    }).dstream();
    PairDStreamFunctions<ByteArray, byte[]> pairDStreamFunctions = DStream.toPairDStreamFunctions(pairDStream, JavaSparkContext$.MODULE$.<ByteArray>fakeClassTag(), JavaSparkContext$.MODULE$.<byte[]>fakeClassTag(), null);
    int defaultNumPartitions = pairDStreamFunctions.defaultPartitioner$default$1();
    Partitioner partitioner = pairDStreamFunctions.defaultPartitioner(defaultNumPartitions);
    // use updateStateByKey to scan through the state and update elements and timers.
    DStream<Tuple2<ByteArray, Tuple2<StateAndTimers, List<byte[]>>>> /*WV<KV<K, Itr<I>>>*/
    firedStream = pairDStreamFunctions.updateStateByKey(new SerializableFunction1<scala.collection.Iterator<Tuple3</*K*/
    ByteArray, Seq<byte[]>, Option<Tuple2<StateAndTimers, /*WV<KV<K, Itr<I>>>*/
    List<byte[]>>>>>, scala.collection.Iterator<Tuple2</*K*/
    ByteArray, Tuple2<StateAndTimers, /*WV<KV<K, Itr<I>>>*/
    List<byte[]>>>>>() {

        @Override
        public scala.collection.Iterator<Tuple2</*K*/
        ByteArray, Tuple2<StateAndTimers, /*WV<KV<K, Itr<I>>>*/
        List<byte[]>>>> apply(final scala.collection.Iterator<Tuple3</*K*/
        ByteArray, Seq<byte[]>, Option<Tuple2<StateAndTimers, /*WV<KV<K, Itr<I>>>*/
        List<byte[]>>>>> iter) {
            //--- ACTUAL STATEFUL OPERATION:
            //
            // Input Iterator: the partition (~bundle) of a cogrouping of the input
            // and the previous state (if exists).
            //
            // Output Iterator: the output key, and the updated state.
            //
            // possible input scenarios for (K, Seq, Option<S>):
            // (1) Option<S>.isEmpty: new data with no previous state.
            // (2) Seq.isEmpty: no new data, but evaluating previous state (timer-like behaviour).
            // (3) Seq.nonEmpty && Option<S>.isDefined: new data with previous state.
            final SystemReduceFn<K, InputT, Iterable<InputT>, Iterable<InputT>, W> reduceFn = SystemReduceFn.buffering(((FullWindowedValueCoder<InputT>) wvCoder).getValueCoder());
            final OutputWindowedValueHolder<K, InputT> outputHolder = new OutputWindowedValueHolder<>();
            // use in memory Aggregators since Spark Accumulators are not resilient
            // in stateful operators, once done with this partition.
            final MetricsContainerImpl cellProvider = new MetricsContainerImpl("cellProvider");
            final CounterCell droppedDueToClosedWindow = cellProvider.getCounter(MetricName.named(SparkGroupAlsoByWindowViaWindowSet.class, GroupAlsoByWindowsAggregators.DROPPED_DUE_TO_CLOSED_WINDOW_COUNTER));
            final CounterCell droppedDueToLateness = cellProvider.getCounter(MetricName.named(SparkGroupAlsoByWindowViaWindowSet.class, GroupAlsoByWindowsAggregators.DROPPED_DUE_TO_LATENESS_COUNTER));
            AbstractIterator<Tuple2<ByteArray, Tuple2<StateAndTimers, List<byte[]>>>> /*WV<KV<K, Itr<I>>>*/
            outIter = new AbstractIterator<Tuple2</*K*/
            ByteArray, Tuple2<StateAndTimers, /*WV<KV<K, Itr<I>>>*/
            List<byte[]>>>>() {

                @Override
                protected Tuple2</*K*/
                ByteArray, Tuple2<StateAndTimers, /*WV<KV<K, Itr<I>>>*/
                List<byte[]>>> computeNext() {
                    // (possibly) previous-state and (possibly) new data.
                    while (iter.hasNext()) {
                        // for each element in the partition:
                        Tuple3<ByteArray, Seq<byte[]>, Option<Tuple2<StateAndTimers, List<byte[]>>>> next = iter.next();
                        ByteArray encodedKey = next._1();
                        K key = CoderHelpers.fromByteArray(encodedKey.getValue(), keyCoder);
                        Seq<byte[]> seq = next._2();
                        Option<Tuple2<StateAndTimers, List<byte[]>>> prevStateAndTimersOpt = next._3();
                        SparkStateInternals<K> stateInternals;
                        SparkTimerInternals timerInternals = SparkTimerInternals.forStreamFromSources(sourceIds, GlobalWatermarkHolder.get());
                        // get state(internals) per key.
                        if (prevStateAndTimersOpt.isEmpty()) {
                            // no previous state.
                            stateInternals = SparkStateInternals.forKey(key);
                        } else {
                            // with pre-existing state.
                            StateAndTimers prevStateAndTimers = prevStateAndTimersOpt.get()._1();
                            stateInternals = SparkStateInternals.forKeyAndState(key, prevStateAndTimers.getState());
                            Collection<byte[]> serTimers = prevStateAndTimers.getTimers();
                            timerInternals.addTimers(SparkTimerInternals.deserializeTimers(serTimers, timerDataCoder));
                        }
                        ReduceFnRunner<K, InputT, Iterable<InputT>, W> reduceFnRunner = new ReduceFnRunner<>(key, windowingStrategy, ExecutableTriggerStateMachine.create(TriggerStateMachines.stateMachineForTrigger(TriggerTranslation.toProto(windowingStrategy.getTrigger()))), stateInternals, timerInternals, outputHolder, new UnsupportedSideInputReader("GroupAlsoByWindow"), reduceFn, runtimeContext.getPipelineOptions());
                        // clear before potential use.
                        outputHolder.clear();
                        if (!seq.isEmpty()) {
                            // new input for key.
                            try {
                                Iterable<WindowedValue<InputT>> elementsIterable = CoderHelpers.fromByteArray(seq.head(), itrWvCoder);
                                Iterable<WindowedValue<InputT>> validElements = LateDataUtils.dropExpiredWindows(key, elementsIterable, timerInternals, windowingStrategy, droppedDueToLateness);
                                reduceFnRunner.processElements(validElements);
                            } catch (Exception e) {
                                throw new RuntimeException("Failed to process element with ReduceFnRunner", e);
                            }
                        } else if (stateInternals.getState().isEmpty()) {
                            // no input and no state -> GC evict now.
                            continue;
                        }
                        try {
                            // advance the watermark to HWM to fire by timers.
                            timerInternals.advanceWatermark();
                            // call on timers that are ready.
                            reduceFnRunner.onTimers(timerInternals.getTimersReadyToProcess());
                        } catch (Exception e) {
                            throw new RuntimeException("Failed to process ReduceFnRunner onTimer.", e);
                        }
                        // this is mostly symbolic since actual persist is done by emitting output.
                        reduceFnRunner.persist();
                        // obtain output, if fired.
                        List<WindowedValue<KV<K, Iterable<InputT>>>> outputs = outputHolder.get();
                        if (!outputs.isEmpty() || !stateInternals.getState().isEmpty()) {
                            StateAndTimers updated = new StateAndTimers(stateInternals.getState(), SparkTimerInternals.serializeTimers(timerInternals.getTimers(), timerDataCoder));
                            // persist Spark's state by outputting.
                            List<byte[]> serOutput = CoderHelpers.toByteArrays(outputs, wvKvIterCoder);
                            return new Tuple2<>(encodedKey, new Tuple2<>(updated, serOutput));
                        }
                    // an empty state with no output, can be evicted completely - do nothing.
                    }
                    return endOfData();
                }
            };
            // log if there's something to log.
            long lateDropped = droppedDueToLateness.getCumulative();
            if (lateDropped > 0) {
                LOG.info(String.format("Dropped %d elements due to lateness.", lateDropped));
                droppedDueToLateness.inc(-droppedDueToLateness.getCumulative());
            }
            long closedWindowDropped = droppedDueToClosedWindow.getCumulative();
            if (closedWindowDropped > 0) {
                LOG.info(String.format("Dropped %d elements due to closed window.", closedWindowDropped));
                droppedDueToClosedWindow.inc(-droppedDueToClosedWindow.getCumulative());
            }
            return scala.collection.JavaConversions.asScalaIterator(outIter);
        }
    }, partitioner, true, JavaSparkContext$.MODULE$.<Tuple2<StateAndTimers, List<byte[]>>>fakeClassTag());
    if (checkpointDurationMillis > 0) {
        firedStream.checkpoint(new Duration(checkpointDurationMillis));
    }
    // go back to Java now.
    JavaPairDStream<ByteArray, Tuple2<StateAndTimers, List<byte[]>>> /*WV<KV<K, Itr<I>>>*/
    javaFiredStream = JavaPairDStream.fromPairDStream(firedStream, JavaSparkContext$.MODULE$.<ByteArray>fakeClassTag(), JavaSparkContext$.MODULE$.<Tuple2<StateAndTimers, List<byte[]>>>fakeClassTag());
    // filter state-only output (nothing to fire) and remove the state from the output.
    return javaFiredStream.filter(new Function<Tuple2</*K*/
    ByteArray, Tuple2<StateAndTimers, /*WV<KV<K, Itr<I>>>*/
    List<byte[]>>>, Boolean>() {

        @Override
        public Boolean call(Tuple2</*K*/
        ByteArray, Tuple2<StateAndTimers, /*WV<KV<K, Itr<I>>>*/
        List<byte[]>>> t2) throws Exception {
            // filter output if defined.
            return !t2._2()._2().isEmpty();
        }
    }).flatMap(new FlatMapFunction<Tuple2</*K*/
    ByteArray, Tuple2<StateAndTimers, /*WV<KV<K, Itr<I>>>*/
    List<byte[]>>>, WindowedValue<KV<K, Iterable<InputT>>>>() {

        @Override
        public Iterable<WindowedValue<KV<K, Iterable<InputT>>>> call(Tuple2</*K*/
        ByteArray, Tuple2<StateAndTimers, /*WV<KV<K, Itr<I>>>*/
        List<byte[]>>> t2) throws Exception {
            // return in serialized form.
            return CoderHelpers.fromByteArrays(t2._2()._2(), wvKvIterCoder);
        }
    });
}

Example 4 with Duration

use of org.apache.spark.streaming.Duration 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);
    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 5 with Duration

use of org.apache.spark.streaming.Duration in project hbase by apache.

the class JavaHBaseStreamingBulkPutExample method main.

public static void main(String[] args) {
    if (args.length < 4) {
        System.out.println("JavaHBaseBulkPutExample  " + "{host} {port} {tableName}");
        return;
    }
    String host = args[0];
    String port = args[1];
    String tableName = args[2];
    SparkConf sparkConf = new SparkConf().setAppName("JavaHBaseStreamingBulkPutExample " + tableName + ":" + port + ":" + tableName);
    JavaSparkContext jsc = new JavaSparkContext(sparkConf);
    try {
        JavaStreamingContext jssc = new JavaStreamingContext(jsc, new Duration(1000));
        JavaReceiverInputDStream<String> javaDstream = jssc.socketTextStream(host, Integer.parseInt(port));
        Configuration conf = HBaseConfiguration.create();
        JavaHBaseContext hbaseContext = new JavaHBaseContext(jsc, conf);
        hbaseContext.streamBulkPut(javaDstream, TableName.valueOf(tableName), new PutFunction());
    } finally {
        jsc.stop();
    }
}