docker体验hadoop

1. 拉取镜像

docker pull sequenceiq/hadoop-docker

2. 运行镜像

docker run -it -p 50070:50070 sequenceiq/hadoop-docker:2.7.0 /etc/bootstrap.sh -bash

在镜像中运行如下命令。
开放50070是为了从web端查看hadoop运行状况。

3. build项目 （WordCount）

新建工作目录取名为 test, 进入test目录后运行如下命令：

3.1 编写程序

vim WordCount.java
hadoop中的HelloWorld程序。

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;import org.apache.hadoop.util.GenericOptionsParser;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();        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();        if (otherArgs.length < 2) {            System.err.println("Usage: wordcount <in> [<in>...] <out>");            System.exit(2);        }        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);        for (int i = 0; i < otherArgs.length - 1; ++i) {            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));        }        FileOutputFormat.setOutputPath(job,                new Path(otherArgs[otherArgs.length - 1]));        System.exit(job.waitForCompletion(true) ? 0 : 1);    }}

3.2 打成jar包

进入到 $HADOOP_PREFIX目录下 cd $HADOOP_PREFIX
以下4个jar包是编译WordCount.java的依赖包

/usr/local/hadoop/share/hadoop/common/hadoop-common-2.7.0.jar/usr/local/hadoop/share/hadoop/common/lib/hadoop-annotations-2.7.0.jar/usr/local/hadoop/share/hadoop/common/lib/commons-cli-1.2.jar/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.7.0.jar

将它们放入工作目录test中， 然后运行如下命令进行编译：

javac -classpath hadoop-common-2.7.0.jar:hadoop-annotations-2.7.0.jar:commons-cli-1.2.jar:hadoop-mapreduce-client-core-2.7.0.jar WordCount.java

编译后test目录出现如下几个class文件, 之后打包class文件:

jar -cvf wordcount.jar *.class
test目录下出现 wordcount.jar文件。

4. 运行任务

编辑一个输入的文件

vim input_files/hellohello worldhello worldhello hi

将这个输入文件传入hadoop fs里面

cd $HADOOP_PREFIX bin/hadoop fs -put input_files/* input

运行jar包：

bin/hadoop jar wordcount.jar WordCount input output

查看输出结果

bin/hadoop fs -cat output/*

结果如下：
hello 3
hi 1
world 2

5.访问web界面

在浏览器输入
localhost:50070