【十二】Spark Streaming整合Flume使用Push方式（使用Scala语言）

最新推荐文章于 2022-08-11 23:19:28 发布

jy02268879

最新推荐文章于 2022-08-11 23:19:28 发布

阅读量379

点赞数

本文链接：https://blog.csdn.net/jy02268879/article/details/81091317

版权

spark streaming 同时被 2 个专栏收录

24 篇文章 1 订阅

订阅专栏

flume

10 篇文章 0 订阅

订阅专栏

官网介绍

Spark Streaming整合Flume有两种方式

Approach 1: Flume-style Push-based Approach

Approach 2: Pull-based Approach using a Custom Sink

这里介绍第一种

Spark Streaming在Flume扮演一个avro agent。

由于是push模式，需要先启动Spark Streaming。

Flume发送数据到一个avro sink上。

在node1上进入flume目录

cd /app/flume/flume/conf

创建flume的agent配置文件

vi test-flume-push-streaming.conf

#flume-push-streaming

flume-push-streaming.sources = netcat-source
flume-push-streaming.sinks = avro-sink
flume-push-streaming.channels = memory-channel

flume-push-streaming.sources.netcat-source.type = netcat
flume-push-streaming.sources.netcat-source.bind = node1
flume-push-streaming.sources.netcat-source.port = 44444

#flume把数据写到什么机器的什么端口
#这里的192.168.2.100是用IDEA运行spark streaming程序的一台电脑
flume-push-streaming.sinks.avro-sink.type = avro
flume-push-streaming.sinks.avro-sink.hostname = 192.168.2.100
flume-push-streaming.sinks.avro-sink.port = 41414

flume-push-streaming.channels.memory-channel.type = memory

flume-push-streaming.sources.netcat-source.channels = memory-channel
flume-push-streaming.sinks.avro-sink.channel = memory-channel

项目目录

pom.xml

<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/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.sid.spark</groupId>
  <artifactId>spark-train</artifactId>
  <version>1.0</version>
  <inceptionYear>2008</inceptionYear>
  <properties>
    <scala.version>2.11.8</scala.version>
    <kafka.version>0.9.0.0</kafka.version>
    <spark.version>2.2.0</spark.version>
    <hadoop.version>2.9.0</hadoop.version>
    <hbase.version>1.4.4</hbase.version>
  </properties>

  <repositories>
    <repository>
      <id>scala-tools.org</id>
      <name>Scala-Tools Maven2 Repository</name>
      <url>http://scala-tools.org/repo-releases</url>
    </repository>
  </repositories>

  <pluginRepositories>
    <pluginRepository>
      <id>scala-tools.org</id>
      <name>Scala-Tools Maven2 Repository</name>
      <url>http://scala-tools.org/repo-releases</url>
    </pluginRepository>
  </pluginRepositories>

  <dependencies>
    <dependency>
      <groupId>org.scala-lang</groupId>
      <artifactId>scala-library</artifactId>
      <version>${scala.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.kafka</groupId>
      <artifactId>kafka_2.11</artifactId>
      <version>${kafka.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>${hadoop.version}</version>
      <exclusions>
        <exclusion>
          <artifactId>servlet-api</artifactId>
          <groupId>javax.servlet</groupId>
        </exclusion>
      </exclusions>
    </dependency>

    <!--<dependency>-->
      <!--<groupId>org.apache.hbase</groupId>-->
      <!--<artifactId>hbase-client</artifactId>-->
      <!--<version>${hbase.version}</version>-->
    <!--</dependency>-->

    <!--<dependency>-->
      <!--<groupId>org.apache.hbase</groupId>-->
      <!--<artifactId>hbase-server</artifactId>-->
      <!--<version>${hbase.version}</version>-->
    <!--</dependency>-->

    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-sql_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming-flume_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

    <dependency>
      <groupId>net.jpountz.lz4</groupId>
      <artifactId>lz4</artifactId>
      <version>1.3.0</version>
    </dependency>

    <dependency>
      <groupId>mysql</groupId>
      <artifactId>mysql-connector-java</artifactId>
      <version>5.1.31</version>
    </dependency>

  </dependencies>

  <build>
    <sourceDirectory>src/main/scala</sourceDirectory>
    <testSourceDirectory>src/test/scala</testSourceDirectory>
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <executions>
          <execution>
            <goals>
              <goal>compile</goal>
              <goal>testCompile</goal>
            </goals>
          </execution>
        </executions>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
          <args>
            <arg>-target:jvm-1.5</arg>
          </args>
        </configuration>
      </plugin>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-eclipse-plugin</artifactId>
        <configuration>
          <downloadSources>true</downloadSources>
          <buildcommands>
            <buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
          </buildcommands>
          <additionalProjectnatures>
            <projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
          </additionalProjectnatures>
          <classpathContainers>
            <classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
            <classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
          </classpathContainers>
        </configuration>
      </plugin>
    </plugins>
  </build>
  <reporting>
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
        </configuration>
      </plugin>
    </plugins>
  </reporting>
</project>

代码

package com.sid.spark

import org.apache.spark.SparkConf
import org.apache.spark.streaming.flume.FlumeUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}

/**
  * Created by jy02268879 on 2018/7/18.
  *
  * SparkStreaming整合Flume用Push方式 模拟词频统计 无状态
  */
object FlumePushSparkStreaming {
  def main(args: Array[String]): Unit = {

    //SparkStreaming从什么机器的端口接收数据
    if(args.length != 2){
      System.err.println("Usage: FlumePushStreaming <hostname> <port>")
      System.exit(1)
    }
    val Array(hostname,port) = args

    //本地运行
    val sparkConf = new SparkConf().setMaster("local[2]").setAppName("FlumePushSparkStreaming")
    //提交到服务器运行 不用把setMaster和setAppName写死
    //val sparkConf = new SparkConf()

    val ssc = new StreamingContext(sparkConf,Seconds(5))

    //该代码运行在192.168.2.100机器上，flume会把数据push到这台机器上来
    val flumeStream = FlumeUtils.createStream(ssc, hostname, port.toInt)
    //flume在传输的时候数据event是有head和body的，这里只拿body就好了
    flumeStream.map( x => new String(x.event.getBody.array()).trim)
        .flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).print()

    ssc.start()
    ssc.awaitTermination()
  }
}

启动IDEA项目传入参数hostname port

启动node1的agent

cd /app/flume/flume

bin/flume-ng agent --name flume-push-streaming -c conf -f conf/test-flume-push-streaming.conf -Dflume.root.logger=INFO,console

在node1中

telnet node1 44444

因为flume数据的来源配置的是从node1的44444端口接收数据

发送数据

IDEA控制台显示

本地运行通过以后打包传到服务器上运行

修改代码

打包

把target下面的jar包传到服务器,提交到spark上运行

cd /app/spark/spark-2.2.0-bin-2.9.0/bin

./spark-submit --class com.sid.spark.FlumePushSparkStreaming --master local[2] --name FlumePushSparkStreaming --packages org.apache.spark:spark-streaming-flume_2.11:2.2.0 /app/spark/test_data/spark-train-1.0-SNAPSHOT.jar node1 41414

修改flume的sink地址到node1，重启flume