从hadoop网址

时间:2016-04-22 02:29:17

标签: hadoop hdfs

我正在尝试关注Tom White的Hadoop诽谤指南,并坚持从Hadoop Url阅读数据。我已经尝试了各种调整,但我一直在不断发现'找不到文件错误'我的文件在hdfs上的路径。

这是Java类:

    package JavaInterfacePractice;
    import java.io.InputStream;
    import java.net.URI;
    import java.net.URL;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.FsUrlStreamHandlerFactory;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;

public class UrlCat {

    static{
        URL.setURLStreamHandlerFactory(new FsUrlStreamHandlerFactory());
    }

    public static void main(String[] args) throws Exception {
        String uri = args[0];
        InputStream in=null;
        Configuration conf = new Configuration();
        conf.addResource(new Path("/usr/local/hadoop/etc/hadoop/core-site.xml"));
        conf.addResource(new Path("/usr/local/hadoop/etc/hadoop/hdfs-site.xml"));

        FileSystem fs = FileSystem.get(URI.create(uri),conf);
        try{
            in=fs.open(new Path(uri));
            IOUtils.copyBytes(in, System.out, 4096,false);

        }finally{
            IOUtils.closeStream(in);
        }
    }

}

以下是我用来运行此代码的命令:

hadoop jar /home/hduser/workspace/MaxTemperature/target/MaxTemperature-0.0.1-SNAPSHOT.jar JavaInterfacePractice.UrlCat /input/1901

这是我得到的错误:

    Exception in thread "main" java.io.FileNotFoundException: File does not exist: /input/1901
    at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:71)
    at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:61)
    at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1828)
    at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1799)
    at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1712)
    at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:587)
    at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:365)
    at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
    at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:616)
    at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:969)
    at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2049)
    at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2045)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:415)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
    at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2043)

    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.ipc.RemoteException.instantiateException(RemoteException.java:106)
    at org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:73)
    at org.apache.hadoop.hdfs.DFSClient.callGetBlockLocations(DFSClient.java:1228)
    at org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1213)
    at org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1201)
    at org.apache.hadoop.hdfs.DFSInputStream.fetchLocatedBlocksAndGetLastBlockLength(DFSInputStream.java:306)
    at org.apache.hadoop.hdfs.DFSInputStream.openInfo(DFSInputStream.java:272)
    at org.apache.hadoop.hdfs.DFSInputStream.<init>(DFSInputStream.java:264)
    at org.apache.hadoop.hdfs.DFSClient.open(DFSClient.java:1526)
    at org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:303)
    at org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:299)
    at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
    at org.apache.hadoop.hdfs.DistributedFileSystem.open(DistributedFileSystem.java:299)
    at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:767)
    at JavaInterfacePractice.UrlCat.main(UrlCat.java:28)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.apache.hadoop.util.RunJar.run(RunJar.java:221)
    at org.apache.hadoop.util.RunJar.main(RunJar.java:136)
Caused by: org.apache.hadoop.ipc.RemoteException(java.io.FileNotFoundException): File does not exist: /input/1901
    at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:71)
    at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:61)
    at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1828)
    at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1799)
    at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1712)
    at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:587)
    at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:365)
    at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
    at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:616)
    at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:969)
    at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2049)
    at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2045)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:415)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
    at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2043)

    at org.apache.hadoop.ipc.Client.call(Client.java:1475)
    at org.apache.hadoop.ipc.Client.call(Client.java:1412)
    at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229)
    at com.sun.proxy.$Proxy9.getBlockLocations(Unknown Source)
    at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getBlockLocations(ClientNamenodeProtocolTranslatorPB.java:255)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:191)
    at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
    at com.sun.proxy.$Proxy10.getBlockLocations(Unknown Source)
    at org.apache.hadoop.hdfs.DFSClient.callGetBlockLocations(DFSClient.java:1226)
    ... 18 more

这是我的HDFS结构:

    drwxr-xr-x   - hduser supergroup          0 2016-04-20 06:50 input
-rw-r--r--   1 hduser supergroup     888190 2016-04-17 12:53 input/1901
-rw-r--r--   1 hduser supergroup     888978 2016-04-20 06:50 input/1902
drwxr-xr-x   - hduser supergroup          0 2016-04-19 22:20 output
-rw-r--r--   1 hduser supergroup          0 2016-04-19 22:20 output/_SUCCESS
-rw-r--r--   1 hduser supergroup          9 2016-04-19 22:20 output/part-r-00000
drwxr-xr-x   - hduser supergroup          0 2016-04-20 06:52 output2
-rw-r--r--   1 hduser supergroup          0 2016-04-20 06:52 output2/_SUCCESS
-rw-r--r--   1 hduser supergroup         18 2016-04-20 06:52 output2/part-r-00000
drwxr-xr-x   - hduser supergroup          0 2016-04-20 07:20 output3
-rw-r--r--   1 hduser supergroup          0 2016-04-20 07:20 output3/_SUCCESS
-rw-r--r--   1 hduser supergroup         18 2016-04-20 07:20 output3/part-r-00000

如果HDFS中存在该文件,为什么我无法运行此文件?任何帮助将不胜感激。

1 个答案:

答案 0 :(得分:0)

假设您已经修复过10个月前提交的内容,但请尝试完整的hdfs输入:

HDFS://服务器:端口/输入/ 1901