I created a table using java client: CREATE TABLE csvdemo (id Int, name String, email String) STORED AS PARQUET I use the java hadoop file system to copy the csv file from local into hdfs When I run this load command it looks successful (running from ambari): load data inpath '/user/admin/MOCK_DATA.csv' into table csvdemo; But when I try to read from it using: select * from csvdemo limit 1; I get this error: org.apache.hive.service.cli.HiveSQLException: java.io.IOException: java.lang.RuntimeException: hdfs://my-host:8020/apps/hive/warehouse/csvdemo/MOCK_DATA.csv is not a Parquet file. expected magic number at tail [80, 65, 82, 49] but found [103, 111, 118, 10]
org.apache.hive.service.cli.HiveSQLException: java.io.IOException: java.lang.RuntimeException: hdfs://my-host:8020/apps/hive/warehouse/csvdemo/MOCK_DATA.csv is not a Parquet file. expected magic number at tail [80, 65, 82, 49] but found [103, 111, 118, 10]
at org.apache.hive.jdbc.Utils.verifySuccess(Utils.java:264)
at org.apache.hive.jdbc.Utils.verifySuccessWithInfo(Utils.java:250)
at org.apache.hive.jdbc.HiveQueryResultSet.next(HiveQueryResultSet.java:373)
at org.apache.ambari.view.hive20.actor.ResultSetIterator.getNext(ResultSetIterator.java:119)
at org.apache.ambari.view.hive20.actor.ResultSetIterator.handleMessage(ResultSetIterator.java:78)
at org.apache.ambari.view.hive20.actor.HiveActor.onReceive(HiveActor.java:38)
at akka.actor.UntypedActor$$anonfun$receive$1.applyOrElse(UntypedActor.scala:167)
at akka.actor.Actor$class.aroundReceive(Actor.scala:467)
at akka.actor.UntypedActor.aroundReceive(UntypedActor.scala:97)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
at akka.actor.ActorCell.invoke(ActorCell.scala:487)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
at akka.dispatch.Mailbox.run(Mailbox.scala:220)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:397)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
Caused by: org.apache.hive.service.cli.HiveSQLException: java.io.IOException: java.lang.RuntimeException: hdfs://my-host:8020/apps/hive/warehouse/csvdemo/MOCK_DATA.csv is not a Parquet file. expected magic number at tail [80, 65, 82, 49] but found [103, 111, 118, 10]
at org.apache.hive.service.cli.operation.SQLOperation.getNextRowSet(SQLOperation.java:414)
at org.apache.hive.service.cli.operation.OperationManager.getOperationNextRowSet(OperationManager.java:233)
at org.apache.hive.service.cli.session.HiveSessionImpl.fetchResults(HiveSessionImpl.java:784)
at sun.reflect.GeneratedMethodAccessor37.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.hive.service.cli.session.HiveSessionProxy.invoke(HiveSessionProxy.java:78)
at org.apache.hive.service.cli.session.HiveSessionProxy.access$000(HiveSessionProxy.java:36)
at org.apache.hive.service.cli.session.HiveSessionProxy$1.run(HiveSessionProxy.java:63)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1866)
at org.apache.hive.service.cli.session.HiveSessionProxy.invoke(HiveSessionProxy.java:59)
at com.sun.proxy.$Proxy29.fetchResults(Unknown Source)
at org.apache.hive.service.cli.CLIService.fetchResults(CLIService.java:520)
at org.apache.hive.service.cli.thrift.ThriftCLIService.FetchResults(ThriftCLIService.java:709)
at org.apache.hive.service.cli.thrift.TCLIService$Processor$FetchResults.getResult(TCLIService.java:1557)
at org.apache.hive.service.cli.thrift.TCLIService$Processor$FetchResults.getResult(TCLIService.java:1542)
at org.apache.thrift.ProcessFunction.process(ProcessFunction.java:39)
at org.apache.thrift.TBaseProcessor.process(TBaseProcessor.java:39)
at org.apache.hive.service.auth.TSetIpAddressProcessor.process(TSetIpAddressProcessor.java:56)
at org.apache.thrift.server.TThreadPoolServer$WorkerProcess.run(TThreadPoolServer.java:286)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException: java.lang.RuntimeException: hdfs://my-host:8020/apps/hive/warehouse/csvdemo/MOCK_DATA.csv is not a Parquet file. expected magic number at tail [80, 65, 82, 49] but found [103, 111, 118, 10]
at org.apache.hadoop.hive.ql.exec.FetchOperator.getNextRow(FetchOperator.java:520)
at org.apache.hadoop.hive.ql.exec.FetchOperator.pushRow(FetchOperator.java:427)
at org.apache.hadoop.hive.ql.exec.FetchTask.fetch(FetchTask.java:146)
at org.apache.hadoop.hive.ql.Driver.getResults(Driver.java:1765)
at org.apache.hive.service.cli.operation.SQLOperation.getNextRowSet(SQLOperation.java:409)
... 24 more
Caused by: java.lang.RuntimeException: hdfs://my-host:8020/apps/hive/warehouse/csvdemo/MOCK_DATA.csv is not a Parquet file. expected magic number at tail [80, 65, 82, 49] but found [103, 111, 118, 10]
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:423)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:386)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:372)
at org.apache.hadoop.hive.ql.io.parquet.read.ParquetRecordReaderWrapper.getSplit(ParquetRecordReaderWrapper.java:255)
at org.apache.hadoop.hive.ql.io.parquet.read.ParquetRecordReaderWrapper.<init>(ParquetRecordReaderWrapper.java:97)
at org.apache.hadoop.hive.ql.io.parquet.read.ParquetRecordReaderWrapper.<init>(ParquetRecordReaderWrapper.java:83)
at org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat.getRecordReader(MapredParquetInputFormat.java:71)
at org.apache.hadoop.hive.ql.exec.FetchOperator$FetchInputFormatSplit.getRecordReader(FetchOperator.java:694)
at org.apache.hadoop.hive.ql.exec.FetchOperator.getRecordReader(FetchOperator.java:332)
at org.apache.hadoop.hive.ql.exec.FetchOperator.getNextRow(FetchOperator.java:458)
... 28 more
... View more
