Flink WordCount Job Submit

原创转载请注明出处：https://www.cnblogs.com/agilestyle/p/15127770.html

Project Directory

Maven Dependency

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>org.fool</groupId>
    <artifactId>flink</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.12.5</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.12</artifactId>
            <version>1.12.5</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.12</artifactId>
            <version>1.12.5</version>
        </dependency>
    </dependencies>

</project>

words.txt

hello world
hello spark
hello fink
hello hadoop
hello es
hello java

批处理

BatchWordCount.java

package org.fool.flink;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;

import java.util.Objects;

public class BatchWordCount {
    public static void main(String[] args) throws Exception {
        ExecutionEnvironment environment = ExecutionEnvironment.getExecutionEnvironment();

        String inputPath = Objects.requireNonNull(ClassLoader.getSystemClassLoader().getResource("words.txt")).getPath();

        DataSet<String> inputDataSet = environment.readTextFile(inputPath);

        DataSet<Tuple2<String, Integer>> resultSet = inputDataSet.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String value, Collector<Tuple2<String, Integer>> collector) throws Exception {
                String[] words = value.split(" ");
                for (String word : words) {
                    collector.collect(new Tuple2<>(word, 1));
                }
            }
        }).groupBy(0).sum(1);

        resultSet.print();
    }
}

Run

流处理

使用有界数据来进行流处理

StreamWordCount.java

package org.fool.flink;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

import java.util.Objects;

public class StreamWordCount {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment environment = StreamExecutionEnvironment.getExecutionEnvironment();
        environment.setParallelism(4);

        String inputPath = Objects.requireNonNull(ClassLoader.getSystemClassLoader().getResource("words.txt")).getPath();

        DataStream<String> inputDataStream = environment.readTextFile(inputPath);

        DataStream<Tuple2<String, Integer>> resultStream = inputDataStream.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String value, Collector<Tuple2<String, Integer>> collector) throws Exception {
                String[] words = value.split(" ");
                for (String word : words) {
                    collector.collect(new Tuple2<>(word, 1));
                }
            }
        }).keyBy(new KeySelector<Tuple2<String, Integer>, Object>() {
            @Override
            public Object getKey(Tuple2<String, Integer> stringIntegerTuple2) throws Exception {
                return stringIntegerTuple2.getField(0);
            }
        }).sum(1);

        resultStream.print();

        environment.execute();
    }
}

Note: 程序中设置了并行度为4，Flink 的每个算子都是可以设置并行度的。

Run

Note：> 左边的 数字 是计算处理的线程号

使用无界数据来进行流处理

StreamSocketWordCount.java

package org.fool.flink;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class StreamSocketWordCount {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment environment = StreamExecutionEnvironment.getExecutionEnvironment();
        environment.setParallelism(4);

        ParameterTool parameterTool = ParameterTool.fromArgs(args);
        String host = parameterTool.get("host");
        int port = parameterTool.getInt("port");
        DataStream<String> inputDataStream = environment.socketTextStream(host, port);

        DataStream<Tuple2<String, Integer>> resultStream = inputDataStream.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String value, Collector<Tuple2<String, Integer>> collector) throws Exception {
                String[] words = value.split(" ");
                for (String word : words) {
                    collector.collect(new Tuple2<>(word, 1));
                }
            }
        }).keyBy(new KeySelector<Tuple2<String, Integer>, Object>() {
            @Override
            public Object getKey(Tuple2<String, Integer> stringIntegerTuple2) throws Exception {
                return stringIntegerTuple2.getField(0);
            }
        }).sum(1);

        resultStream.print();

        environment.execute();
    }
}

Run

使用 nc 开启一个 socket

nc -lk 7878

查看控制台输出

Job 提交运行

使用 UI 提交

停止 IDEA 中的 StreamSocketWordCount 程序，注释掉

// environment.setParallelism(4);

项目根目录下打包

mvn clean package

启动 Flink Cluster

./start-cluster.sh

使用 nc 开启一个 socket

nc -lk 7878

将打包好的 flink-1.0-SNAPSHOT.jar 提交到 Flink Cluster 中

设置 并行度为 3，点击 Show Plan

关闭后，点击 Submit

查看 Stdout

使用 命令行 提交

cd 到 flink 的 bin 目录

cd ~/app/flink-1.12.5/bin

flink run job

flink run -c org.fool.flink.StreamSocketWordCount -p 3 ~/IdeaProjects/helloflink/target/flink-1.0-SNAPSHOT.jar --host 127.0.0.1 -port 7878

flink list job

flink list

flink cancel job

flink cancel 8ba760464860d28fe4e30109a721be93

flink list

flink list -a

Note: 可以看到 使用 命令行提交 job 比操作 UI 提交更高效和方便。

---

欢迎点赞关注和收藏