Flink--EventTime中WaterMark知识点扫盲

2019-08-03  本文已影响0人  李小李的路

概述

Flink WaterMark介绍

并行流中的watermark

生成 Timestamps / Watermarks

分配Timestamps

Source Functions with Timestamps and Watermarks

@Override
public void run(SourceContext<MyType> ctx) throws Exception {
    while (/* condition */) {
        MyType next = getNext();
        ctx.collectWithTimestamp(next, next.getEventTimestamp());

        if (next.hasWatermarkTime()) {
            ctx.emitWatermark(new Watermark(next.getWatermarkTime()));
        }
    }
}

scala

override def run(ctx: SourceContext[MyType]): Unit = {
    while (/* condition */) {
        val next: MyType = getNext()
        ctx.collectWithTimestamp(next, next.eventTimestamp)

        if (next.hasWatermarkTime) {
            ctx.emitWatermark(new Watermark(next.getWatermarkTime))
        }
    }
}

Timestamp Assigners / Watermark Generators

final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

DataStream<MyEvent> stream = env.readFile(
        myFormat, myFilePath, FileProcessingMode.PROCESS_CONTINUOUSLY, 100,
        FilePathFilter.createDefaultFilter(), typeInfo);

DataStream<MyEvent> withTimestampsAndWatermarks = stream
        .filter( event -> event.severity() == WARNING )
        .assignTimestampsAndWatermarks(new MyTimestampsAndWatermarks());

withTimestampsAndWatermarks
        .keyBy( (event) -> event.getGroup() )
        .timeWindow(Time.seconds(10))
        .reduce( (a, b) -> a.add(b) )
        .addSink(...);

val env = StreamExecutionEnvironment.getExecutionEnvironment
env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)

val stream: DataStream[MyEvent] = env.readFile(
         myFormat, myFilePath, FileProcessingMode.PROCESS_CONTINUOUSLY, 100,
         FilePathFilter.createDefaultFilter())

val withTimestampsAndWatermarks: DataStream[MyEvent] = stream
        .filter( _.severity == WARNING )
        .assignTimestampsAndWatermarks(new MyTimestampsAndWatermarks())

withTimestampsAndWatermarks
        .keyBy( _.getGroup )
        .timeWindow(Time.seconds(10))
        .reduce( (a, b) => a.add(b) )
        .addSink(...)

With Periodic Watermarks周期性watermark

定时提取watermark，这种方式会定时提取更新wartermark。

/**
 * This generator generates watermarks assuming that elements arrive out of order,
 * but only to a certain degree. The latest elements for a certain timestamp t will arrive
 * at most n milliseconds after the earliest elements for timestamp t.
 */
public class BoundedOutOfOrdernessGenerator implements AssignerWithPeriodicWatermarks<MyEvent> {

    private final long maxOutOfOrderness = 3500; // 3.5 seconds

    private long currentMaxTimestamp;

    @Override
    public long extractTimestamp(MyEvent element, long previousElementTimestamp) {
        long timestamp = element.getCreationTime();
        currentMaxTimestamp = Math.max(timestamp, currentMaxTimestamp);
        return timestamp;
    }

    @Override
    public Watermark getCurrentWatermark() {
        // return the watermark as current highest timestamp minus the out-of-orderness bound
        return new Watermark(currentMaxTimestamp - maxOutOfOrderness);
    }
}

/**
 * This generator generates watermarks that are lagging behind processing time by a fixed amount.
 * It assumes that elements arrive in Flink after a bounded delay.
 */
public class TimeLagWatermarkGenerator implements AssignerWithPeriodicWatermarks<MyEvent> {

    private final long maxTimeLag = 5000; // 5 seconds

    @Override
    public long extractTimestamp(MyEvent element, long previousElementTimestamp) {
        return element.getCreationTime();
    }

    @Override
    public Watermark getCurrentWatermark() {
        // return the watermark as current time minus the maximum time lag
        return new Watermark(System.currentTimeMillis() - maxTimeLag);
    }
}

/**
 * This generator generates watermarks assuming that elements arrive out of order,
 * but only to a certain degree. The latest elements for a certain timestamp t will arrive
 * at most n milliseconds after the earliest elements for timestamp t.
 */
class BoundedOutOfOrdernessGenerator extends AssignerWithPeriodicWatermarks[MyEvent] {

    val maxOutOfOrderness = 3500L // 3.5 seconds

    var currentMaxTimestamp: Long = _

    override def extractTimestamp(element: MyEvent, previousElementTimestamp: Long): Long = {
        val timestamp = element.getCreationTime()
        currentMaxTimestamp = max(timestamp, currentMaxTimestamp)
        timestamp
    }

    override def getCurrentWatermark(): Watermark = {
        // return the watermark as current highest timestamp minus the out-of-orderness bound
        new Watermark(currentMaxTimestamp - maxOutOfOrderness)
    }
}

/**
 * This generator generates watermarks that are lagging behind processing time by a fixed amount.
 * It assumes that elements arrive in Flink after a bounded delay.
 */
class TimeLagWatermarkGenerator extends AssignerWithPeriodicWatermarks[MyEvent] {

    val maxTimeLag = 5000L // 5 seconds

    override def extractTimestamp(element: MyEvent, previousElementTimestamp: Long): Long = {
        element.getCreationTime
    }

    override def getCurrentWatermark(): Watermark = {
        // return the watermark as current time minus the maximum time lag
        new Watermark(System.currentTimeMillis() - maxTimeLag)
    }
}

With Punctuated Watermarks

伴随event的到来就提取watermark，就是每一个event到来的时候，就会提取一次Watermark。这样的方式当然设置watermark更为精准，但是当数据量大的时候，频繁的更新wartermark会比较影响性能。通常情况下采用定时提取就足够了。

public class PunctuatedAssigner implements AssignerWithPunctuatedWatermarks<MyEvent> {

    @Override
    public long extractTimestamp(MyEvent element, long previousElementTimestamp) {
        return element.getCreationTime();
    }

    @Override
    public Watermark checkAndGetNextWatermark(MyEvent lastElement, long extractedTimestamp) {
        return lastElement.hasWatermarkMarker() ? new Watermark(extractedTimestamp) : null;
    }
}


class PunctuatedAssigner extends AssignerWithPunctuatedWatermarks[MyEvent] {

    override def extractTimestamp(element: MyEvent, previousElementTimestamp: Long): Long = {
        element.getCreationTime
    }

    override def checkAndGetNextWatermark(lastElement: MyEvent, extractedTimestamp: Long): Watermark = {
        if (lastElement.hasWatermarkMarker()) new Watermark(extractedTimestamp) else null
    }
}

Timestamps per Kafka Partition

FlinkKafkaConsumer09<MyType> kafkaSource = new FlinkKafkaConsumer09<>("myTopic", schema, props);
kafkaSource.assignTimestampsAndWatermarks(new AscendingTimestampExtractor<MyType>() {

    @Override
    public long extractAscendingTimestamp(MyType element) {
        return element.eventTimestamp();
    }
});

DataStream<MyType> stream = env.addSource(kafkaSource);

val kafkaSource = new FlinkKafkaConsumer09[MyType]("myTopic", schema, props)
kafkaSource.assignTimestampsAndWatermarks(new AscendingTimestampExtractor[MyType] {
    def extractAscendingTimestamp(element: MyType): Long = element.eventTimestamp
})

val stream: DataStream[MyType] = env.addSource(kafkaSource)
kafka.png

Pre-defined Timestamp Extractors / Watermark Emitters

上一篇 下一篇

猜你喜欢

热点阅读