官方网址:Apache Hadoop
1、hadoop是什么?
hadoop是Apache顶级项目
hadoop是一个可靠的、可扩展的、开源的、分布式软件
2、初识hadoop理解图
将hadoop按照官方文档部署好后,你只需要编写简单的代码就可以在多台机器上实现分布式计算
hdfs(Hadoop Distributed File System):
是hadoop分布式文件系统,意思就是可以将你要放的文件分散到多个节点上
yarn:
资源管理和作业调度/监视,可以将你写的程序移动到需要计算的数据节点进行计算,并进行状态的监控
MapReduce:
分布式计算框架,按照框架继承Mapper、Reducer,并在main方法中进行提交即可实现分布式计算了
3、示例程序WordCount
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); } }