Hadoop Yarn运行模式 WordCount例子(JAVA)

失业的中年程序员

已于 2024-04-24 13:52:02 修改

阅读量224

点赞数 2

分类专栏：大数据文章标签： java hadoop eclipse

于 2024-04-24 02:12:19 首次发布

本文链接：https://blog.csdn.net/hhujjj2005/article/details/138143145

版权

大数据专栏收录该内容

8 篇文章 0 订阅

订阅专栏

本文介绍了如何在Hadoop3.3.5的YARN模式下，通过WordCount程序实现文本处理，并详细说明了在LinuxCentOS8环境中进行Hadoop配置，包括YARN-site.xml和mapred-site.xml的设置。

摘要由CSDN通过智能技术生成

Hadoop版本：3.3.5

运行环境：Linux Centos8

Hadoop运行模式：yarn模式

yarn架构，参考YARN 详解 --- ResourceManager, NodeManager以及ApplicationMaster_yarn resourcemanager-CSDN博客

1 JAVA

WordCount.java

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCount {

    public static class TokenizerMapper
            extends Mapper<Object, Text, Text, IntWritable>{

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Context context
        ) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer
            extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values,
                           Context context
        ) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

pom.xml

<properties>
	<maven.compiler.source>8</maven.compiler.source>
	<maven.compiler.target>8</maven.compiler.target>
	<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
	<hadoop.version>3.3.5</hadoop.version>
</properties>

<dependencies>
	<!-- 导入hadoop依赖环境 -->
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-common</artifactId>
		<version>${hadoop.version}</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-hdfs</artifactId>
		<version>${hadoop.version}</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-mapreduce-client-core</artifactId>
		<version>${hadoop.version}</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-client</artifactId>
		<version>${hadoop.version}</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-yarn-api</artifactId>
		<version>${hadoop.version}</version>
	</dependency>
</dependencies>

打包成Wordcount-1.0-SNAPSHOT.jar，上传到/home/hadoop

2 Hadoop配置

Hadoop安装：腾讯云服务器Linux centos hadoop安装配置-CSDN博客

配置

# cd hadoop-3.3.5/etc/hadoop

# vi yarn-site.xml
<property>
	<name>yarn.nodemanager.aux-services</name>
	<value>mapreduce_shuffle</value>
</property>
<property>
	<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
	<value>org.apache.hahoop.mapred.ShuffleHandler</value>
</property>

# hadoop classpath
hadoop classpath路径

# vi mapred-site.xml
<property>
   <name>mapreduce.framework.name</name>
   <value>yarn</value>
</property>
<property>
   <name>mapred.job.tracker</name>
   <value>hdfs://localhost:9000</value>
</property>
<property>
  <name>yarn.app.mapreduce.am.env</name>
  <value>HADOOP_MAPRED_HOME=hadoop classpath路径</value>
</property>
<property>
  <name>mapreduce.map.env</name>
  <value>HADOOP_MAPRED_HOME=hadoop classpath路径</value>
</property>
<property>
  <name>mapreduce.reduce.env</name>
  <value>HADOOP_MAPRED_HOME=hadoop classpath路径</value>
</property>

3 运行WordCount

# start-dfs.sh
# start-yarn.sh

# cat 1.txt
hello hadoop
hello spark
hello world

# hdfs dfs -put ./1.txt /    # 1.txt上传到HDFS

# hadoop jar /home/hadoop/Wordcount-1.0-SNAPSHOT.jar WordCount /1.txt /tmp/output    # 提交mapreduce任务

hadoop问题汇总：https://blog.csdn.net/hhujjj2005/article/details/138143204