hadoop如何通过cachefile来避免数据倾斜

这篇文章主要介绍了hadoop如何通过cachefile来避免数据倾斜，具有一定借鉴价值，感兴趣的朋友可以参考下，希望大家阅读完这篇文章之后大有收获，下面让小编带着大家一起了解一下。

package hello_hadoop;import java.io.BufferedReader;import java.io.BufferedWriter;import java.io.File;import java.io.FileInputStream;import java.io.FileReader;import java.io.FileWriter;import java.io.IOException;import java.io.InputStream;import java.io.InputStreamReader;import java.net.URI;import java.net.URISyntaxException;import org.apache.commons.logging.Log;import org.apache.commons.logging.LogFactory;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.filecache.DistributedCache;import org.apache.hadoop.fs.Path;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.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.input.FileSplit;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;public class GetFileName {        //得到处理的文件名，以及将需要的文件缓存到相应的节点        private final static  Log LOG = LogFactory.getLog(GetFileName.class);        public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException, URISyntaxException {                LOG.info("Go into the main method ......");                Configuration conf = new Configuration();                Job job = Job.getInstance(conf);                                job.setJarByClass(GetFileName.class);                job.setMapOutputKeyClass(Text.class);                job.setMapOutputValueClass(Text.class);                job.setMapperClass(GetFileNameMapper.class);                job.setNumReduceTasks(0);                //集群上添加DistributedCache data134:9000namenode的描述   #thelinkofthefile改文件的链接，下面读取的时候需要使用                job.addCacheFile(new URI("hdfs://data134:9000/home/tmp.txt#thelinkofthefile"));                FileInputFormat.addInputPath(job, new Path(args[0]));                FileOutputFormat.setOutputPath(job, new Path(args[1]));                boolean test = job.waitForCompletion(true);                LOG.info("End  the main method ......");                System.exit(test?0:1);                  }}class GetFileNameMapper extends Mapper{        private final Log LOG = LogFactory.getLog(GetFileNameMapper.class);                @Override        protected void setup(Mapper.Context context)                        throws IOException, InterruptedException {                if(context.getCacheFiles().length>0);                URI u = context.getCacheFiles()[0];                //这里使用链接来访问文件                BufferedReader br = new BufferedReader( new FileReader(new File("./thelinkofthefile")));                String line = br.readLine();                context.write(new Text(line), new Text());                System.out.println("Here I read Line :"+line);        }        @Override        protected void map(LongWritable key, Text value, Mapper.Context context)                        throws IOException, InterruptedException {        }}

感谢你能够认真阅读完这篇文章，希望小编分享的"hadoop如何通过cachefile来避免数据倾斜"这篇文章对大家有帮助，同时也希望大家多多支持，关注行业资讯频道，更多相关知识等着你来学习!