我正在尝试实现reduce side join,并使用mapfile reader查找分布式缓存,但是在stderr中检查时它没有查找值,它显示以下错误,lookupfile文件已经存在于hdfs中,并且似乎正确加载进入缓存,如stdout中所示.
java.lang.IllegalArgumentException:Wrong FS:file:/ app/hadoop/tmp/mapred/local/taskTracker/distcache/-8118663285704962921_-1196516983_170706299/localhost/input/delivery_status/DeliveryStatusCodes/data,expected:hdfs:// localhost:9000 org.apache.hadoop.fs.FileSystem.checkPath(FileSystem.java:390)位于org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus的org.apache.hadoop.hdfs.DistributedFileSystem.getPathName(DistributedFileSystem.java:140) (DistributedFileSystem.java:554)atg.apache.hadoop.fs.FileSystem.getLength(FileSystem.java:816)org.apache.hadoop.io.SequenceFile $ Reader.(SequenceFile.java:1479)org.apache .hadoop.io.SequenceFile $ Reader.(SequenceFile.java:1474)org.apache.hadoop.io.MapFile $ Reader.createDataFileReader(MapFile.java:302)at org.apache.hadoop.io.MapFile $ Reader.打开(MapFile.java:284)org.apache.hadoop.io.MapFile $ Reader.(MapFile.java:273)org.apache.hadoop.io.MapFile $ Reader.(MapFile.java:260)at org .apache.hadoop.io.MapFile $读卡器(MapFile.java:253)在mr_poc.reducerrsj.initializeDepartmentsMap(reducerrsj.java:59)mr_poc.reducerrsj.setup(reducerrsj.java:42)atg.apache.hadoop.mapreduce.Reducer.run(Reducer.java:174)at org.位于org.apache.hadoop.mapred.Child $ 4.run的org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:418)中的apache.hadoop.mapred.ReduceTask.runNewReducer(ReduceTask.java:649) .java:255)at java.security.AccessController.doPrivileged(Native Method)at javax.security.auth.Subject.doAs(Subject.java:416)at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java) :1190)org.apache.hadoop.mapred.Child.main(Child.java:249)mr_poc.reducerrsj.reduce(reducerrsj.java)mr_poc.reducerrsj.buildOutputValue(reducerrsj.java:83)中的java.lang.NullPointerException :127)位于org.apache.hadoop.mapred.ReduceTask.runNewReducer(ReduceTask.)的org.apache.hadoop.mapreduce.Reducer.run(Reducer.java:177)中的mr_poc.reducerrsj.reduce(reducerrsj.java:1). java:649)at org.apache.hadoop.mapred.ReduceTask.run(Reduc)eTask.java:418)atg.apache.hadoop.mapred.Child $ 4.run(Child.java:255)at java.security.AccessController.doPrivileged(Native Method)at javax.security.auth.Subject.doAs(Subject .java:416)在org.apache.hadoop.security.
这是我的驱动程序代码,
package mr_poc;
import java.net.URI;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class driverrsj extends Configured implements Tool{
@Override …