windows IDEA直接提交MapReduce到集群上执行

云主机

1. 开放云主机所有端口（可以限制源IP，避免被挖矿）
   
2. 编写WordCount程序,并配置相应的参数

package www.immoc.hadoop.mapreduce.yarn;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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 java.io.IOException;

public class WordCountOnYarnApp {
    public static void main(String[] args) throws Exception{
        System.setProperty("HADOOP_USER_NAME", "hadoop");
        Configuration conf = new Configuration();
        conf.set("yarn.resourcemanager.address", "bigdata:8032");
        conf.set("dfs.client.use.datanode.hostname", "true");
        conf.set("mapreduce.framework.name", "yarn");
        conf.set("fs.defaultFS", "hdfs://bigdata:9000/");
        conf.set("mapreduce.app-submission.cross-platform", "true");
        Job job = Job.getInstance(conf, "wc");

        String inputPath = "hdfs://bigdata:9000/ruozedata/wc/input/wc.data";
//        String inputPath = args[0];
        String outputPath = "hdfs://bigdata:9000/ruozedata/wc/outputyarn1";
//        String outputPath = args[1];

        job.setJar("target/hdfs-train-1.0.jar");
        job.setJarByClass(WordCountOnYarnApp.class);

        job.setMapperClass(myMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setReducerClass(myReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job, new Path(inputPath));
        FileOutputFormat.setOutputPath(job, new Path(outputPath));


        boolean result = job.waitForCompletion(true);
        System.out.println(result ? 0 : 1);
    }

    public static class myMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] datas = value.toString().split(",");

            for (String data : datas) {
                context.write(new Text(data), new IntWritable(1));
            }
        }
    }
    
    public static class myReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int count = 0;

            for (IntWritable value : values) {
                count += value.get();
            }

            context.write(key, new IntWritable(count));
        }
    }
}

如果实现不了，先配置本地远行的环境（由于本人是先本地之后才要提交到远程集群中，所以不知道本地运行的环境是有影响）
本地运行环境配置

虚拟机思路同上