引入YARN作为通用资源调度平台后,Hadoop得以支持多种计算框架,如MapReduce、Spark、Storm等。MRv1是Hadoop1中的MapReduce,MRv2是Hadoop2中的MapReduce。下面是MRv1和MRv2之间的一些基本变化:
MRv2上的参数可以参考官方文档进行配置,但是在mapred-site.xml中有一个参数需要注意:mapreduce.job.user.classpath.first
,本文推荐将其配置成true。如果不配置该参数的话,在执行jar程序的时候,系统会优先选择Hadoop框架中已经存在的java类而不是用户指定包中自己编写的java类
org.apache.hadoop.mapred
包(旧包)和org.apache.hadoop.mapreduce
包(新包)。MapReduce包wordcount事例
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 {
//context.nextKeyValue()
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> <out>");
System.exit(2);
}
Job job = new Job(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(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}