![](/img/trans.png)
[英]Hadoop: File Copy with Cascading 2.5.1 and Hadoop 2.2.0
[英]hadoop2.2.0 append file occur AlreadyBeingCreatedException
我遇到了關於hadoop2.2.0追加操作的問題。 我通過HDFS java API將一些字節附加到hdfs文件。首先,如果在附加操作之前文件不存在,我將創建目標文件,代碼如下:
String fileUri = "hdfs://hadoopmaster:9000/in/append_test.txt";
// create the hdfs file, if not exists
HdfsClient.createPathIfNotExist(fileUri);
// do 5 times append operation
for (int i=0; i<5; i++){
HdfsClient.appendTo(fileUri, ("append content"+i).getBytes("UTF-8"));
}
createPathIfNotExist
函數:
Path p = null;
FileSystem fs = null;
try {
fs = FileSystem.get(URI.create(uri), conf);
p = new Path(uri);
if (!fs.exists(p)) {
if (uri.charAt(uri.length() - 1) == '/'){ //create a directory
if(fs.mkdirs(p)){
// create successfully
}
}else{ //create a file
FSDataOutputStream fos = fs.create(p);
fos.close();
}
} else{
System.out.println(uri + "existing");
}
} catch (IOException e) {
e.printStackTrace();
} finally{
if (fs != null)
try {
fs.close();
fs = null;
} catch (IOException e) {
e.printStackTrace();
}
}
appendTo
函數:
ByteArrayInputStream in = null;
OutputStream out = null;
FileSystem fs = null;
try {
in = new ByteArrayInputStream(bytes);
fs = FileSystem.get(URI.create(uri), conf);
out = fs.append(new Path(uri)); //get append outputstream
IOUtils.copyBytes(in, out, bufferSize, false);
} catch(Exception e){
e.printStackTrace();
} finally{
if (in != null) IOUtils.closeStream(in);
if (out != null) IOUtils.closeStream(out);
if (fs != null){
try {
fs.close();
fs = null;
} catch (IOException e) {
e.printStackTrace();
}
}
}
結果是創建了append_test.txt,但內容只有:
append content0
並發生異常:
org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.hdfs.protocol.AlreadyBeingCreatedException): Failed to create file [/in/append_test.txt] for [DFSClient_NONMAPREDUCE_-1148656837_1] on client [192.168.141.1], because this file is already being created by [DFSClient_NONMAPREDUCE_2099912242_1] on [192.168.141.1]
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.recoverLeaseInternal(FSNamesystem.java:2320)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.appendFileInternal(FSNamesystem.java:2153)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.appendFileInt(FSNamesystem.java:2386)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.appendFile(FSNamesystem.java:2347)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.append(NameNodeRpcServer.java:508)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.append(ClientNamenodeProtocolServerSideTranslatorPB.java:320)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java:59572)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:585)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:928)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2048)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2044)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1491)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2042)
at org.apache.hadoop.ipc.Client.call(Client.java:1347)
at org.apache.hadoop.ipc.Client.call(Client.java:1300)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:206)
at com.sun.proxy.$Proxy10.append(Unknown Source)
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:186)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
at com.sun.proxy.$Proxy10.append(Unknown Source)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.append(ClientNamenodeProtocolTranslatorPB.java:245)
at org.apache.hadoop.hdfs.DFSClient.callAppend(DFSClient.java:1480)
at org.apache.hadoop.hdfs.DFSClient.append(DFSClient.java:1520)
at org.apache.hadoop.hdfs.DFSClient.append(DFSClient.java:1508)
at org.apache.hadoop.hdfs.DistributedFileSystem$4.doCall(DistributedFileSystem.java:310)
at org.apache.hadoop.hdfs.DistributedFileSystem$4.doCall(DistributedFileSystem.java:306)
at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at org.apache.hadoop.hdfs.DistributedFileSystem.append(DistributedFileSystem.java:306)
at org.apache.hadoop.fs.FileSystem.append(FileSystem.java:1160)
at org.lh.blog.message.hadoop.HdfsClient$2.run(HdfsClient.java:130)
at org.lh.blog.message.hadoop.HdfsClient$2.run(HdfsClient.java:1)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:356)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1471)
at org.lh.blog.message.hadoop.HdfsClient.appendTo(HdfsClient.java:121)
at org.lh.blog.message.hadoop.HdfsClient.appendTo(HdfsClient.java:110)
at org.lh.blog.message.test.HdfsClientTests.testCreateFileBeforeAppend(HdfsClientTests.java:26)
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.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:45)
at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:15)
at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:42)
at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:20)
at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:263)
at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:68)
at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:47)
at org.junit.runners.ParentRunner$3.run(ParentRunner.java:231)
at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:60)
at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:229)
at org.junit.runners.ParentRunner.access$000(ParentRunner.java:50)
at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:222)
at org.junit.runners.ParentRunner.run(ParentRunner.java:300)
at org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:50)
at org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38)
at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:467)
at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:683)
at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:390)
at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:197)
也就是說,在創建非xx文件后,它只執行了一次追加操作,其他4個追加操作失敗,發生在錯誤之上。 我在追加之前創建了文件,但是它說AlreadyBeingCreatedException
,我AlreadyBeingCreatedException
困惑。
我也有一些嘗試。 我發現java API創建的hdfs文件,都不能做追加操作。 但是hdfs命令(etc,“hdfs dfs -put”)創建的hdfs文件可以執行追加操作。
你能幫我一下,給我一些建議嗎?
感謝和問候。
這個問題是由hadoop“追加代碼”中的一些錯誤引起的。 您可以在本文中閱讀更多相關內容: 將內容附加到HDFS中的文件
還為此問題提供了解決方案。 您也可以在創建文件后在fs上調用close()方法,並在追加操作之前再次獲取FileSystem。 對我來說很好,但這取決於你。
您可以將推測操作設置為false
job.setSpeculativeExecution(false);
或者可以使用時間戳或路徑中的任何其他變量事件創建文件到某個臨時位置,並稍后將結果合並到基本路徑
要解決這個問題,
這個過程對我來說很好,並解決了這個問題。
APPEND操作很昂貴,如果你試圖並行嘗試,那么我就會出現這個問題。 因此,重新創建文件並將內容重寫到它而不是附加。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.