我这是因为一个Set类型的字段，add了一个null导致写入失败。/(ㄒoㄒ)/~~
Job aborted due to stage failure: Task 0 in stage 1.0 failed 4 times, most recent failure: Lost task 0.3 in stage 1.0 (TID 4, master, executor 7): org.apache.spark.SparkException: Task failed while writing rows at org.apache.spark.internal.io.SparkHadoopMapReduceWriter$.org$apache$spark$internal$io$SparkHadoopMapReduceWriter$$executeTask(SparkHadoopMapReduceWriter.scala:197) at org.apache.spark.internal.io.SparkHadoopMapReduceWriter$$anonfun$3.apply(SparkHadoopMapReduceWriter.scala:105) at org.apache.spark.internal.io.SparkHadoopMapReduceWriter$$anonfun$3.apply(SparkHadoopMapReduceWriter.scala:100) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:100) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:340) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) at java.lang.Thread.run(Thread.java:748) Caused by: java.lang.NullPointerException at org.apache.parquet.io.api.Binary$FromStringBinary.encodeUTF8(Binary.java:216) at org.apache.parquet.io.api.Binary$FromStringBinary.(Binary.java:206) at org.apache.parquet.io.api.Binary.fromString(Binary.java:519) at org.apache.parquet.thrift.ParquetWriteProtocol.writeStringToRecordConsumer(ParquetWriteProtocol.java:652) at org.apache.parquet.thrift.ParquetWriteProtocol.access$900(ParquetWriteProtocol.java:52) at org.apache.parquet.thrift.ParquetWriteProtocol$PrimitiveWriteProtocol.writeString(ParquetWriteProtocol.java:289) at org.apache.parquet.thrift.ParquetWriteProtocol.writeString(ParquetWriteProtocol.java:634) at com.test.data.InfoDf.write(InfoDf.java:1751) at org.apache.parquet.hadoop.thrift.TbaseWriteSupport.write(TbaseWriteSupport.java:57) at org.apache.parquet.hadoop.thrift.ThriftWriteSupport.write(ThriftWriteSupport.java:73) at org.apache.parquet.hadoop.thrift.ThriftWriteSupport.write(ThriftWriteSupport.java:31) at org.apache.parquet.hadoop.InternalParquetRecordWriter.write(InternalParquetRecordWriter.java:123) at org.apache.parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:180) at org.apache.parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:46) at org.apache.spark.internal.io.SparkHadoopMapReduceWriter$$anonfun$4.apply(SparkHadoopMapReduceWriter.scala:164) at org.apache.spark.internal.io.SparkHadoopMapReduceWriter$$anonfun$4.apply(SparkHadoopMapReduceWriter.scala:161) at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1361) at org.apache.spark.internal.io.SparkHadoopMapReduceWriter$.org$apache$spark$internal$io$SparkHadoopMapReduceWriter$$executeTask(SparkHadoopMapReduceWriter.scala:173) ... 8 more Suppressed: java.io.FileNotFoundException: File does not exist: /user/hive_table/dwm_info_df/date=20211201/_temporary/0/_temporary/attempt_*_0001_r_000000_3/part-r-00000.snappy.parquet (inode 31511531) Holder DFSClient_attempt_*_0000_m_000000_0_1847753967_93_application_*_* does not have any open files. at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkLease(FSNamesystem.java:3034) at org.apache.hadoop.hdfs.server.namenode.FSDirWriteFileOp.analyzeFileState(FSDirWriteFileOp.java:581) at org.apache.hadoop.hdfs.server.namenode.FSDirWriteFileOp.validateAddBlock(FSDirWriteFileOp.java:168) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getAdditionalBlock(FSNamesystem.java:2913) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.addBlock(NameNodeRpcServer.java:982) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.addBlock(ClientNamenodeProtocolServerSideTranslatorPB.java:612) at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:532) at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1070) at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1099) at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1027) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1805) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:3026) 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.ipc.RemoteException.instantiateException(RemoteException.java:121) at org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:88) at org.apache.hadoop.hdfs.DFSOutputStream.addBlock(DFSOutputStream.java:1125) at org.apache.hadoop.hdfs.DataStreamer.locateFollowingBlock(DataStreamer.java:1885) at org.apache.hadoop.hdfs.DataStreamer.nextBlockOutputStream(DataStreamer.java:1684) at org.apache.hadoop.hdfs.DataStreamer.run(DataStreamer.java:723) Caused by: org.apache.hadoop.ipc.RemoteException(java.io.FileNotFoundException): File does not exist: /user/hive_table/dwm_info_df/date=20211201/_temporary/0/_temporary/attempt_*_0001_r_000000_3/part-r-00000.snappy.parquet (inode 31511531) Holder DFSClient_attempt_*_0000_m_000000_0_1847753967_93_application_*_* does not have any open files. at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkLease(FSNamesystem.java:3034) at org.apache.hadoop.hdfs.server.namenode.FSDirWriteFileOp.analyzeFileState(FSDirWriteFileOp.java:581) at org.apache.hadoop.hdfs.server.namenode.FSDirWriteFileOp.validateAddBlock(FSDirWriteFileOp.java:168) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getAdditionalBlock(FSNamesystem.java:2913) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.addBlock(NameNodeRpcServer.java:982) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.addBlock(ClientNamenodeProtocolServerSideTranslatorPB.java:612) at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:532) at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1070) at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1099) at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1027) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1805) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:3026) at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1555) at org.apache.hadoop.ipc.Client.call(Client.java:1501) at org.apache.hadoop.ipc.Client.call(Client.java:1411) at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:228) at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:116) at com.sun.proxy.$Proxy14.addBlock(Unknown Source) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.addBlock(ClientNamenodeProtocolTranslatorPB.java:544) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:422) at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invokeMethod(RetryInvocationHandler.java:165) at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invoke(RetryInvocationHandler.java:157) at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invokeOnce(RetryInvocationHandler.java:95) at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:359) at com.sun.proxy.$Proxy15.addBlock(Unknown Source) at org.apache.hadoop.hdfs.DFSOutputStream.addBlock(DFSOutputStream.java:1122) ... 3 more Driver stacktrace:
