1. 用途
Flink定时器存在于窗口的触发,TTL等诸多用途,因此搞清楚其原理对于理解这些知识点至关重要。
2. 示例
在flink实时处理中,涉及到延时处理可使用KeyedProcessFunction来完成,KeyedProcessFunction是flink提供面向用户的low level api,可以访问状态、当前的watermark或者当前的processingtime, 更重要的是提供了注册定时器的功能,分为:
- 注册处理时间定时器,直到系统的processingTime超过了注册的时间就会触发定时任务
- 注册事件时间定时器,直到watermark值超过了注册的时间就会触发定时任务另外也可以删除已经注册的定时器。
示例代码如下:
// 创建bean类CountWithTimestamp,里面有三个字段
package com.bolingcavalry.keyedprocessfunction;
public class CountWithTimestamp {
public String key;
public long count;
public long lastModified;
}
// 创建FlatMapFunction的实现类Splitter,作用是将字符串分割后生成多个Tuple2实例,f0是分隔后的单词,f1等于1:
package com.bolingcavalry;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;
import org.apache.flink.util.StringUtils;
public class Splitter implements FlatMapFunction<String, Tuple2<String, Integer>> {
@Override
public void flatMap(String s, Collector<Tuple2<String, Integer>> collector) throws Exception {
if(StringUtils.isNullOrWhitespaceOnly(s)) {
System.out.println("invalid line");
return;
}
for(String word : s.split(" ")) {
collector.collect(new Tuple2<String, Integer>(word, 1));
}
}
}
// 最后是整个逻辑功能的主体:ProcessTime.java,这里面有自定义的KeyedProcessFunction子类,还有程序入口的main方法
package com.bolingcavalry.keyedprocessfunction;
import com.bolingcavalry.Splitter;
import org.apache.flink.api.common.state.ValueState;
import org.apache.flink.api.common.state.ValueStateDescriptor;
import org.apache.flink.api.java.tuple.Tuple;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.TimeCharacteristic;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.AssignerWithPeriodicWatermarks;
import org.apache.flink.streaming.api.functions.KeyedProcessFunction;
import org.apache.flink.streaming.api.watermark.Watermark;
import org.apache.flink.util.Collector;
import java.text.SimpleDateFormat;
import java.util.Date;
/**
* @author will
* @email zq2599@gmail.com
* @date 2020-05-17 13:43
* @description 体验KeyedProcessFunction类(时间类型是处理时间)
*/
public class ProcessTime {
/**
* KeyedProcessFunction的子类,作用是将每个单词最新出现时间记录到backend,并创建定时器,
* 定时器触发的时候,检查这个单词距离上次出现是否已经达到10秒,如果是,就发射给下游算子
*/
static class CountWithTimeoutFunction extends KeyedProcessFunction<Tuple, Tuple2<String, Integer>, Tuple2<String, Long>> {
// 自定义状态
private ValueState<CountWithTimestamp> state;
@Override
public void open(Configuration parameters) throws Exception {
// 初始化状态,name是myState
state = getRuntimeContext().getState(new ValueStateDescriptor<>("myState", CountWithTimestamp