Flink 双流 Join 的3种操作示例
Posted Flink 中文社区
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了Flink 双流 Join 的3种操作示例相关的知识,希望对你有一定的参考价值。
-
join() -
coGroup() -
intervalJoin()
准备数据
DataStream<String> clickSourceStream = env
.addSource(new FlinkKafkaConsumer011<>(
"ods_analytics_access_log",
new SimpleStringSchema(),
kafkaProps
).setStartFromLatest());
DataStream<String> orderSourceStream = env
.addSource(new FlinkKafkaConsumer011<>(
"ods_ms_order_done",
new SimpleStringSchema(),
kafkaProps
).setStartFromLatest());
DataStream<AnalyticsAccessLogRecord> clickRecordStream = clickSourceStream
.map(message -> JSON.parseObject(message, AnalyticsAccessLogRecord.class));
DataStream<OrderDoneLogRecord> orderRecordStream = orderSourceStream
.map(message -> JSON.parseObject(message, OrderDoneLogRecord.class));
join()
clickRecordStream
.join(orderRecordStream)
.where(record -> record.getMerchandiseId())
.equalTo(record -> record.getMerchandiseId())
.window(TumblingProcessingTimeWindows.of(Time.seconds(10)))
.apply(new JoinFunction<AnalyticsAccessLogRecord, OrderDoneLogRecord, String>() {
@Override
public String join(AnalyticsAccessLogRecord accessRecord, OrderDoneLogRecord orderRecord) throws Exception {
return StringUtils.join(Arrays.asList(
accessRecord.getMerchandiseId(),
orderRecord.getPrice(),
orderRecord.getCouponMoney(),
orderRecord.getRebateAmount()
), ' ');
}
})
.print().setParallelism(1);
coGroup()
clickRecordStream
.coGroup(orderRecordStream)
.where(record -> record.getMerchandiseId())
.equalTo(record -> record.getMerchandiseId())
.window(TumblingProcessingTimeWindows.of(Time.seconds(10)))
.apply(new CoGroupFunction<AnalyticsAccessLogRecord, OrderDoneLogRecord, Tuple2<String, Long>>() {
public void coGroup(Iterable<AnalyticsAccessLogRecord> accessRecords, Iterable<OrderDoneLogRecord> orderRecords, Collector<Tuple2<String, Long>> collector) throws Exception {
for (AnalyticsAccessLogRecord accessRecord : accessRecords) {
boolean isMatched = false;
for (OrderDoneLogRecord orderRecord : orderRecords) {
// 右流中有对应的记录
collector.collect(new Tuple2<>(accessRecord.getMerchandiseName(), orderRecord.getPrice()));
isMatched = true;
}
if (!isMatched) {
// 右流中没有对应的记录
collector.collect(new Tuple2<>(accessRecord.getMerchandiseName(), null));
}
}
}
})
.print().setParallelism(1);
intervalJoin()
right.timestamp ∈ [left.timestamp + lowerBound; left.timestamp + upperBound]
clickRecordStream
.keyBy(record -> record.getMerchandiseId())
.intervalJoin(orderRecordStream.keyBy(record -> record.getMerchandiseId()))
.between(Time.seconds(-30), Time.seconds(30))
.process(new ProcessJoinFunction<AnalyticsAccessLogRecord, OrderDoneLogRecord, String>() {
public void processElement(AnalyticsAccessLogRecord accessRecord, OrderDoneLogRecord orderRecord, Context context, Collector<String> collector) throws Exception {
collector.collect(StringUtils.join(Arrays.asList(
accessRecord.getMerchandiseId(),
orderRecord.getPrice(),
orderRecord.getCouponMoney(),
orderRecord.getRebateAmount()
), ' '));
}
})
.print().setParallelism(1);
interval join 的实现原理
public <OUT> SingleOutputStreamOperator<OUT> process(
ProcessJoinFunction<IN1, IN2, OUT> processJoinFunction,
TypeInformation<OUT> outputType) {
Preconditions.checkNotNull(processJoinFunction);
Preconditions.checkNotNull(outputType);
final ProcessJoinFunction<IN1, IN2, OUT> cleanedUdf = left.getExecutionEnvironment().clean(processJoinFunction);
final IntervalJoinOperator<KEY, IN1, IN2, OUT> operator =
new IntervalJoinOperator<>(
lowerBound,
upperBound,
lowerBoundInclusive,
upperBoundInclusive,
left.getType().createSerializer(left.getExecutionConfig()),
right.getType().createSerializer(right.getExecutionConfig()),
cleanedUdf
);
return left
.connect(right)
.keyBy(keySelector1, keySelector2)
.transform("Interval Join", outputType, operator);
}
private transient MapState<Long, List<BufferEntry<T1>>> leftBuffer;
private transient MapState<Long, List<BufferEntry<T2>>> rightBuffer;
public void initializeState(StateInitializationContext context) throws Exception {
super.initializeState(context);
this.leftBuffer = context.getKeyedStateStore().getMapState(new MapStateDescriptor<>(
LEFT_BUFFER,
LongSerializer.INSTANCE,
new ListSerializer<>(new BufferEntrySerializer<>(leftTypeSerializer))
));
this.rightBuffer = context.getKeyedStateStore().getMapState(new MapStateDescriptor<>(
RIGHT_BUFFER,
LongSerializer.INSTANCE,
new ListSerializer<>(new BufferEntrySerializer<>(rightTypeSerializer))
));
}
public void processElement1(StreamRecord<T1> record) throws Exception {
processElement(record, leftBuffer, rightBuffer, lowerBound, upperBound, true);
}
public void processElement2(StreamRecord<T2> record) throws Exception {
processElement(record, rightBuffer, leftBuffer, -upperBound, -lowerBound, false);
}
"unchecked") (
private <THIS, OTHER> void processElement(
final StreamRecord<THIS> record,
final MapState<Long, List<IntervalJoinOperator.BufferEntry<THIS>>> ourBuffer,
final MapState<Long, List<IntervalJoinOperator.BufferEntry<OTHER>>> otherBuffer,
final long relativeLowerBound,
final long relativeUpperBound,
final boolean isLeft) throws Exception {
final THIS ourValue = record.getValue();
final long ourTimestamp = record.getTimestamp();
if (ourTimestamp == Long.MIN_VALUE) {
throw new FlinkException("Long.MIN_VALUE timestamp: Elements used in " +
"interval stream joins need to have timestamps meaningful timestamps.");
}
if (isLate(ourTimestamp)) {
return;
}
addToBuffer(ourBuffer, ourValue, ourTimestamp);
for (Map.Entry<Long, List<BufferEntry<OTHER>>> bucket: otherBuffer.entries()) {
final long timestamp = bucket.getKey();
if (timestamp < ourTimestamp + relativeLowerBound ||
timestamp > ourTimestamp + relativeUpperBound) {
continue;
}
for (BufferEntry<OTHER> entry: bucket.getValue()) {
if (isLeft) {
collect((T1) ourValue, (T2) entry.element, ourTimestamp, timestamp);
} else {
collect((T1) entry.element, (T2) ourValue, timestamp, ourTimestamp);
}
}
}
long cleanupTime = (relativeUpperBound > 0L) ? ourTimestamp + relativeUpperBound : ourTimestamp;
if (isLeft) {
internalTimerService.registerEventTimeTimer(CLEANUP_NAMESPACE_LEFT, cleanupTime);
} else {
internalTimerService.registerEventTimeTimer(CLEANUP_NAMESPACE_RIGHT, cleanupTime);
}
}
-
取得当前流 StreamRecord 的时间戳,调用 isLate() 方法判断它是否是迟到数据(即时间戳小于当前水印值),如是则丢弃。 -
调用 addToBuffer() 方法,将时间戳和数据一起插入当前流对应的 MapState。 -
遍历另外一个流的 MapState,如果数据满足前述的时间区间条件,则调用 collect() 方法将该条数据投递给用户定义的 ProcessJoinFunction 进行处理。collect() 方法的代码如下,注意结果对应的时间戳是左右流时间戳里较大的那个。
private void collect(T1 left, T2 right, long leftTimestamp, long rightTimestamp) throws Exception {
final long resultTimestamp = Math.max(leftTimestamp, rightTimestamp);
collector.setAbsoluteTimestamp(resultTimestamp);
context.updateTimestamps(leftTimestamp, rightTimestamp, resultTimestamp);
userFunction.processElement(left, right, context, collector);
}
-
调用 TimerService.registerEventTimeTimer() 注册时间戳为 timestamp + relativeUpperBound 的定时器,该定时器负责在水印超过区间的上界时执行状态的清理逻辑,防止数据堆积。注意左右流的定时器所属的 namespace 是不同的,具体逻辑则位于 onEventTime() 方法中。
@Override
public void onEventTime(InternalTimer<K, String> timer) throws Exception {
long timerTimestamp = timer.getTimestamp();
String namespace = timer.getNamespace();
logger.trace("onEventTime @ {}", timerTimestamp);
switch (namespace) {
case CLEANUP_NAMESPACE_LEFT: {
long timestamp = (upperBound <= 0L) ? timerTimestamp : timerTimestamp - upperBound;
logger.trace("Removing from left buffer @ {}", timestamp);
leftBuffer.remove(timestamp);
break;
}
case CLEANUP_NAMESPACE_RIGHT: {
long timestamp = (lowerBound <= 0L) ? timerTimestamp + lowerBound : timerTimestamp;
logger.trace("Removing from right buffer @ {}", timestamp);
rightBuffer.remove(timestamp);
break;
}
default:
throw new RuntimeException("Invalid namespace " + namespace);
}
}
本文转载自简书,作者:LittleMagic
原文链接:https://www.jianshu.com/p/45ec888332df
以上是关于Flink 双流 Join 的3种操作示例的主要内容,如果未能解决你的问题,请参考以下文章
20.Flink高级特性--新特性--双流Joinjoin的分类API代码演示-WindowJoin代码演示-IntervalJoin
20.Flink高级特性--新特性--双流Joinjoin的分类API代码演示-WindowJoin代码演示-IntervalJoin