hadoop-23 Yarn tool接口

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 org.apache.hadoop.util.Tool;

import java.io.IOException;

public class WordCount implements Tool {
    private Configuration conf;

    // 核心驱动(conf 传入)
    @Override
    public int run(String[] args) throws Exception {
        Job job = Job.getInstance(conf);
        job.setJarByClass(WordCountDriver.class);
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        return job.waitForCompletion(true) ? 0 : 1;
    }

    @Override
    public void setConf(Configuration conf) {
        this.conf = conf;
    }

    @Override
    public Configuration getConf() {

        return null;
    }

    // mapper
    public static class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
        private Text outK = new Text();
        private IntWritable outV = new IntWritable(1);

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            String[] words = line.split("\t");
            for (String word : words) {
                outK.set(word);
                context.write(outK, outV);
            }
        }
    }

    // reducer
    public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable outV = new IntWritable();

        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable value : values) {
                sum += value.get();
            }
            outV.set(sum);
            context.write(key, outV);
        }
    }
}

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.util.Arrays;

public class WordCountDriver {

    private static Tool tool;

    public static void main(String[] args) throws Exception {
        // 创建配置
        Configuration conf = new Configuration();

        switch (args[0]) {
            case "wordcount":
                tool = new WordCount();
                break;
            default:
                throw new RuntimeException("no such tool " + args[0]);
        }
        // 执行程序
        int run = ToolRunner.run(conf, tool, Arrays.copyOfRange(args, 1, args.length));
        System.exit(run);
    }
}

yarn jar ~/HadoopLearn-1.0.0.jar com.learn.yarn.WordCountDriver wordcount /input /output

yarn jar ~/HadoopLearn-1.0.0.jar com.learn.yarn.WordCountDriver wordcount -Dmapreduce.job.queuename=hive /input /output1

jmap -heap 进程号