24-Flink-高级特性-新特性-Streaming Flie Sink

Flink-高级特性-新特性-Streaming Flie Sink

介绍

https://ci.apache.org/projects/flink/flink-docs-release-1.12/dev/connectors/streamfile_sink.html

https://blog.csdn.net/u013220482/article/details/100901471

代码演示

package cn.itcast.feature;


import org.apache.commons.lang3.SystemUtils;
import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.serialization.SimpleStringEncoder;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.core.fs.Path;
import org.apache.flink.runtime.state.filesystem.FsStateBackend;
import org.apache.flink.streaming.api.CheckpointingMode;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.CheckpointConfig;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.sink.filesystem.OutputFileConfig;
import org.apache.flink.streaming.api.functions.sink.filesystem.StreamingFileSink;
import org.apache.flink.streaming.api.functions.sink.filesystem.rollingpolicies.DefaultRollingPolicy;
import org.apache.flink.util.Collector;

import java.util.concurrent.TimeUnit;

/**
 * Author itcast
 * Desc 演示Flink StreamingFileSink将流式数据写入到HDFS 数据一致性由Checkpoint + 两阶段提交保证
 */
public class StreamingFileSinkDemo {
    public static void main(String[] args) throws Exception {
        //TODO 0.env
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);

        //开启Checkpoint
        //===========类型1:必须参数=============
        //设置Checkpoint的时间间隔为1000ms做一次Checkpoint/其实就是每隔1000ms发一次Barrier!
        env.enableCheckpointing(1000);
        if (SystemUtils.IS_OS_WINDOWS) {
            env.setStateBackend(new FsStateBackend("file:///D:/ckp"));
        } else {
            env.setStateBackend(new FsStateBackend("hdfs://node1:8020/flink-checkpoint/checkpoint"));
        }
        //===========类型2:建议参数===========
        //设置两个Checkpoint 之间最少等待时间,如设置Checkpoint之间最少是要等 500ms(为了避免每隔1000ms做一次Checkpoint的时候,前一次太慢和后一次重叠到一起去了)
        //如:高速公路上,每隔1s关口放行一辆车,但是规定了两车之前的最小车距为500m
        env.getCheckpointConfig().setMinPauseBetweenCheckpoints(500);//默认是0
        //设置如果在做Checkpoint过程中出现错误，是否让整体任务失败：true是  false不是
        //env.getCheckpointConfig().setFailOnCheckpointingErrors(false);//默认是true
        env.getCheckpointConfig().setTolerableCheckpointFailureNumber(10);//默认值为0，表示不容忍任何检查点失败
        //设置是否清理检查点,表示 Cancel 时是否需要保留当前的 Checkpoint，默认 Checkpoint会在作业被Cancel时被删除
        //ExternalizedCheckpointCleanup.DELETE_ON_CANCELLATION：true,当作业被取消时，删除外部的checkpoint(默认值)
        //ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION：false,当作业被取消时，保留外部的checkpoint
        env.getCheckpointConfig().enableExternalizedCheckpoints(CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION);

        //===========类型3:直接使用默认的即可===============
        //设置checkpoint的执行模式为EXACTLY_ONCE(默认)
        env.getCheckpointConfig().setCheckpointingMode(CheckpointingMode.EXACTLY_ONCE);
        //设置checkpoint的超时时间,如果 Checkpoint在 60s内尚未完成说明该次Checkpoint失败,则丢弃。
        env.getCheckpointConfig().setCheckpointTimeout(60000);//默认10分钟
        //设置同一时间有多少个checkpoint可以同时执行
        env.getCheckpointConfig().setMaxConcurrentCheckpoints(1);//默认为1


        //TODO 1.source
        DataStream<String> lines = env.socketTextStream("node1", 9999);


        //TODO 2.transformation
        //注意:下面的操作将上面的2步合成了1步,直接切割单词并记为1返回
        SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndOne = lines.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
                String[] arr = value.split(" ");
                for (String word : arr) {
                    out.collect(Tuple2.of(word, 1));
                }
            }
        });

        SingleOutputStreamOperator<String> result = wordAndOne.keyBy(t -> t.f0).sum(1)
                .map(new MapFunction<Tuple2<String, Integer>, String>() {
                    @Override
                    public String map(Tuple2<String, Integer> value) throws Exception {
                        return value.f0 + ":" + value.f1;
                    }
                });

        //TODO 3.sink
        result.print();

        //使用StreamingFileSink将数据sink到HDFS
        OutputFileConfig config = OutputFileConfig
                .builder()
                .withPartPrefix("prefix")//设置文件前缀
                .withPartSuffix(".txt")//设置文件后缀
                .build();

        StreamingFileSink<String> streamingFileSink = StreamingFileSink.
                forRowFormat(new Path("hdfs://node1:8020/FlinkStreamFileSink/parquet"), new SimpleStringEncoder<String>("UTF-8"))
                .withRollingPolicy(
                        DefaultRollingPolicy.builder()
                                .withRolloverInterval(TimeUnit.MINUTES.toMillis(15))//每隔15分钟生成一个新文件
                                .withInactivityInterval(TimeUnit.MINUTES.toMillis(5))//每隔5分钟没有新数据到来,也把之前的生成一个新文件
                                .withMaxPartSize(1024 * 1024 * 1024)
                                .build())
                .withOutputFileConfig(config)
                .build();

        result.addSink(streamingFileSink);

        //TODO 4.execute
        env.execute();
    }
}