Я установил Hadoop на Windows в соответствии с этой статьей и теперь могу запустить тестовое приложение hadoop-mapreduce-examples-X.Y.Z.jar.
К сожалению, когда я запускаю полномасштабное приложение, оно начинает получать доступ к какому-то странному адресу 0.0.0.0:10020. Изменили мою конфигурацию DFS на <value>hdfs://0.0.0.0</value>, но это не помогло.
Исключение составляют следующие:
[Thread-14] INFO org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchControlledJob - Job status available at: http://lagrangian:8088/proxy/application_1525212500911_0002/
[Thread-14] ERROR org.apache.crunch.impl.mr.exec.MRExecutor - Pipeline failed due to exception
java.io.IOException: java.io.IOException: java.net.ConnectException: Call From lagrangian/169.254.105.43 to 0.0.0.0:10020 failed on connection exception: java.net.ConnectException: Connection refused: no further information; For more details see:
http://wiki.apache.org/hadoop/ConnectionRefused
at org.apache.crunch.impl.mr.exec.CrunchJobHooks$CompletionHook.handleMultiPaths(CrunchJobHooks.java:92)
at org.apache.crunch.impl.mr.exec.CrunchJobHooks$CompletionHook.run(CrunchJobHooks.java:79)
at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchControlledJob.checkRunningState(CrunchControlledJob.java:288)
at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchControlledJob.checkState(CrunchControlledJob.java:299)
at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchJobControl.checkRunningJobs(CrunchJobControl.java:193)
at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchJobControl.pollJobStatusAndStartNewOnes(CrunchJobControl.java:313)
at org.apache.crunch.impl.mr.exec.MRExecutor.monitorLoop(MRExecutor.java:131)
at org.apache.crunch.impl.mr.exec.MRExecutor.access$000(MRExecutor.java:58)
at org.apache.crunch.impl.mr.exec.MRExecutor$1.run(MRExecutor.java:90)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException: java.net.ConnectException: Call From lagrangian/169.254.105.43 to 0.0.0.0:10020 failed on connection exception: java.net.ConnectException: Connection refused: no further information; For more details see: http://wiki.apache.org/hadoop/ConnectionRefused
at org.apache.hadoop.mapred.ClientServiceDelegate.invoke(ClientServiceDelegate.java:344)
at org.apache.hadoop.mapred.ClientServiceDelegate.getJobStatus(ClientServiceDelegate.java:429)
at org.apache.hadoop.mapred.YARNRunner.getJobStatus(YARNRunner.java:617)
at org.apache.hadoop.mapreduce.Job$1.run(Job.java:323)
at org.apache.hadoop.mapreduce.Job$1.run(Job.java:320)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1836)
at org.apache.hadoop.mapreduce.Job.updateStatus(Job.java:320)
at org.apache.hadoop.mapreduce.Job.isSuccessful(Job.java:616)
at org.apache.crunch.impl.mr.exec.CrunchJobHooks$CompletionHook.handleMultiPaths(CrunchJobHooks.java:84)
... 9 more
Caused by: java.net.ConnectException: Call From lagrangian/169.254.105.43 to 0.0.0.0:10020 failed on connection exception: java.net.ConnectException: Connection refused: no further information; For more details see: http://wiki.apache.org/hadoop/ConnectionRefused
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at org.apache.hadoop.net.NetUtils.wrapWithMessage(NetUtils.java:801)
at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:732)
at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1493)
at org.apache.hadoop.ipc.Client.call(Client.java:1435)
at org.apache.hadoop.ipc.Client.call(Client.java:1345)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:227)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:116)
at com.sun.proxy.$Proxy20.getJobReport(Unknown Source)
at org.apache.hadoop.mapreduce.v2.api.impl.pb.client.MRClientProtocolPBClientImpl.getJobReport(MRClientProtocolPBClientImpl.java:133)
at sun.reflect.GeneratedMethodAccessor15.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.hadoop.mapred.ClientServiceDelegate.invoke(ClientServiceDelegate.java:325)
... 19 more
Caused by: java.net.ConnectException: Connection refused: no further information
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)
at org.apache.hadoop.net.SocketIOWithTimeout.connect(SocketIOWithTimeout.java:206)
at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:531)
at org.apache.hadoop.ipc.Client$Connection.setupConnection(Client.java:685)
at org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:788)
at org.apache.hadoop.ipc.Client$Connection.access$3500(Client.java:410)
at org.apache.hadoop.ipc.Client.getConnection(Client.java:1550)
at org.apache.hadoop.ipc.Client.call(Client.java:1381)
... 28 more
Я читал, что это, вероятно, связано с Job History Server, но я не уверен, как запустить его на Windows.