mapreduce输出多文件出错

待我称王封你为后i 2022-06-14 11:42 219阅读 0赞

运行mapreduce多文件输出试报错。

17/06/19 17:25:45 INFO mapreduce.Job: Task Id : attempt_1497864070486_0001_r_000000_2, Status : FAILED
    Error: org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.hdfs.protocol.AlreadyBeingCreatedException): failed to create file /test/output/_temporary/1/_temporary/attempt_1497864070486_0001_r_000000_2/b-r-00000 for DFSClient_attempt_1497864070486_0001_r_000000_2_473674087_1 for client 192.168.10.250 because current leaseholder is trying to recreate file.
    	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.recoverLeaseInternal(FSNamesystem.java:3034)
    	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInternal(FSNamesystem.java:2737)
    	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInt(FSNamesystem.java:2632)
    	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:2520)
    	at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.create(NameNodeRpcServer.java:579)
    	at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.create(ClientNamenodeProtocolServerSideTranslatorPB.java:394)
    	at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
    	at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:619)
    	at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:962)
    	at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2040)
    	at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2036)
    	at java.security.AccessController.doPrivileged(Native Method)
    	at javax.security.auth.Subject.doAs(Subject.java:422)
    	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1656)
    	at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2034)
    
    	at org.apache.hadoop.ipc.Client.call(Client.java:1469)
    	at org.apache.hadoop.ipc.Client.call(Client.java:1400)
    	at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:232)
    	at com.sun.proxy.$Proxy13.create(Unknown Source)
    	at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.create(ClientNamenodeProtocolTranslatorPB.java:295)
    	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    	at java.lang.reflect.Method.invoke(Method.java:498)
    	at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:187)
    	at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
    	at com.sun.proxy.$Proxy14.create(Unknown Source)
    	at org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1725)
    	at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1657)
    	at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1582)
    	at org.apache.hadoop.hdfs.DistributedFileSystem$6.doCall(DistributedFileSystem.java:397)
    	at org.apache.hadoop.hdfs.DistributedFileSystem$6.doCall(DistributedFileSystem.java:393)
    	at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
    	at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:393)
    	at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:337)
    	at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:908)
    	at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:889)
    	at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:786)
    	at org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.getRecordWriter(TextOutputFormat.java:132)
    	at org.apache.hadoop.mapreduce.lib.output.MultipleOutputs.getRecordWriter(MultipleOutputs.java:475)
    	at org.apache.hadoop.mapreduce.lib.output.MultipleOutputs.write(MultipleOutputs.java:433)
    	at org.apache.hadoop.mapreduce.lib.output.MultipleOutputs.write(MultipleOutputs.java:411)
    	at hadoop.WordCount$WordCountReduce.reduce(WordCount.java:51)
    	at hadoop.WordCount$WordCountReduce.reduce(WordCount.java:1)
    	at org.apache.hadoop.mapreduce.Reducer.run(Reducer.java:171)
    	at org.apache.hadoop.mapred.ReduceTask.runNewReducer(ReduceTask.java:627)
    	at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:389)
    	at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:163)
    	at java.security.AccessController.doPrivileged(Native Method)
    	at javax.security.auth.Subject.doAs(Subject.java:422)
    	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1656)
    	at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:158)

后来发现我的reduce里面MultipleOutputs忘记close了。下面是运行正常的程序

package hadoop;
    
    import java.io.IOException;
    import java.util.StringTokenizer;
    import org.apache.hadoop.conf.Configuration;
    import org.apache.hadoop.fs.FileSystem;
    import org.apache.hadoop.fs.Path;
    import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapred.lib.MultipleTextOutputFormat;
    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.mapreduce.lib.output.MultipleOutputs;
    import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
    import org.apache.hadoop.util.GenericOptionsParser;
    
    import scala.reflect.generic.Trees.New;
    
    public class WordCount {
    
    	public static class WordCountMapper extends Mapper<Object, Text, Text, IntWritable>{
    		private static final IntWritable Number = new IntWritable(1);
    		private Text word = new Text();
    		@Override
    		protected void map(Object key, Text value, Context context)
    				throws IOException, InterruptedException {
    			StringTokenizer stringTokenizer = new StringTokenizer(value.toString());
    			while(stringTokenizer.hasMoreTokens()){
    				String string = stringTokenizer.nextToken();
    				word.set(string);
    				context.write(word, Number);
    			}
    		}
    		
    	}
    	
    	public static class WordCountReduce extends Reducer<Text, IntWritable, Text, IntWritable>{
    
    		MultipleOutputs multipleOutputs=null;
    		@Override
    		protected void setup(Reducer<Text, IntWritable, Text, IntWritable>.Context context)
    				throws IOException, InterruptedException {
    			// TODO Auto-generated method stub
    			 multipleOutputs = new MultipleOutputs(context);
    		}
    
    		@Override
    		protected void reduce(Text key, Iterable<IntWritable> vlaues,
    				Context context) throws IOException, InterruptedException {
    			int num=0;
    			for(IntWritable intWritable:vlaues){
    				num+=intWritable.get();
    				
    			}
    			if("hello".equals(key.toString())){
    				multipleOutputs.write("a", key, new IntWritable(num));
    			}else{
    				multipleOutputs.write("b", key, new IntWritable(num));
    			}
    		}
    
    		@Override
    		protected void cleanup(Reducer<Text, IntWritable, Text, IntWritable>.Context context)
    				throws IOException, InterruptedException {
    			// TODO Auto-generated method stub
    			multipleOutputs.close();
    		}
    		
    		
    	}
    	
    	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    		Configuration conf = new Configuration();
    		String[] argsValues = new GenericOptionsParser(conf, args).getRemainingArgs();
    		if(args.length<2){
    			System.exit(2);
    		}
    		Job job = new Job(conf, "word count");  
    		job.setJarByClass(WordCount.class);
    		job.setMapperClass(WordCountMapper.class);
    		job.setReducerClass(WordCountReduce.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(IntWritable.class);
    		FileInputFormat.addInputPaths(job, argsValues[0]);
    		FileOutputFormat.setOutputPath(job, new Path(argsValues[1]));
    		MultipleOutputs.addNamedOutput(job, "a", TextOutputFormat.class, Text.class, IntWritable.class);
    		MultipleOutputs.addNamedOutput(job, "b", TextOutputFormat.class, Text.class, IntWritable.class);
    		System.exit(job.waitForCompletion(true)?0:1);
    	}
    	
    }