MapReduce二次排序中遇到的问题，及解决方法

遇到的问题

解决方法

mapreduce_shuffle does not exist

Container launch failed for container_1446452318872_0002_01_000002 : org.apache.hadoop.yarn.exceptions.InvalidAuxServiceException: The auxService:mapreduce_shuffle does not exist
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.instantiateException(SerializedExceptionPBImpl.java:152)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.deSerialize(SerializedExceptionPBImpl.java:106)
at org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl$Container.launch(ContainerLauncherImpl.java:155)
at org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl$EventProcessor.run(ContainerLauncherImpl.java:369)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)

<configuration>
<!-- Site specific YARN configuration properties -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.aux-services.mapreduce_shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
</configuration>

EOF Exception

Error: java.lang.RuntimeException: java.io.EOFException
at org.apache.hadoop.io.WritableComparator.compare(WritableComparator.java:135)
at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.compare(MapTask.java:1245)
at org.apache.hadoop.util.QuickSort.fix(QuickSort.java:35)
at org.apache.hadoop.util.QuickSort.sortInternal(QuickSort.java:87)
at org.apache.hadoop.util.QuickSort.sort(QuickSort.java:63)
at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.sortAndSpill(MapTask.java:1575)
at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.flush(MapTask.java:1462)
at org.apache.hadoop.mapred.MapTask$NewOutputCollector.close(MapTask.java:700)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:770)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:340)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:167)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1556)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:162)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(DataInputStream.java:392)
at com.wowSpark.secondarySort.NewKey.readFields(NewKey.java:29)
at org.apache.hadoop.io.WritableComparator.compare(WritableComparator.java:129)
... 14 more

public class NewKey implements WritableComparable<NewKey> {

...

@Override
public void readFields(DataInput in) throws IOException {
first = in.readInt();
second = in.readInt();
}

@Override
public void write(DataOutput out) throws IOException {
/**原来是这样写的
out.write(first);
out.write(second);
因为上面的readFields方法中用的是
in.readInt() 读取四个输入字节并返回一个 int 值。简单的说它要读取4个字节的数据。
如果这里使用 out.write() 将指定字节（参数 b 的八个低位）写入基础输出流。它只写1个字节的数据，因此会导致上面异常
*/
out.writeInt(first);
out.writeInt(second);
}