Hi
I can't reproduce it with "spark2.1+ carbondata1.1.1"
Maybe not completely finish compaction , then you do the query.
Have you tried:
Execute the query in the same shell after " compaction and clean"?
Regards
Liang
yixu2001 wrote
> dev
>
>
> spark2.1+ carbondata1.1.1
>
> "Select" query failed when executing "COMPACT" and "CLEAN".
>
> After my cluster running for a period of time, there are so many fragments
> generated in it. Then I input the following 2 command.
> "ALTER table e_carbon.offer COMPACT 'MAJOR';"
> "CLEAN FILES FOR TABLE e_carbon.offer;"
>
> When the above 2 command are being executed, I execute a query statement
> in another shell such as:
> "select offer_id,count(*) from e_carbon.offer group by offer_id having
> count(*)>1"
>
> It failed with the following infomation:
> "scala> cc.sql("select offer_id,count(*) from e_carbon.offer group by
> offer_id having count(*)>1").show;
>
>
> [Stage 163:==================> (60 + 9)
> / 173]18/01/16 16:38:17 WARN scheduler.TaskSetManager: Lost task 149.0 in
> stage 163.0 (TID 6854, HDD012, executor 106):
> org.apache.spark.util.TaskCompletionListenerException:
> java.util.concurrent.ExecutionException:
> java.util.concurrent.ExecutionException: java.io.FileNotFoundException:
> File does not exist:
> /user/e_carbon/public/carbon.store/e_carbon/offer_inst_c/Fact/Part0/Segment_22.15/part-0-7_batchno0-0-1516091074114.carbondata
> 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:652)
> 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$1.run(Server.java:2151)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2147)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2145)
>
> at
> org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:105)
> at org.apache.spark.scheduler.Task.run(Task.scala:112)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
>
> 18/01/16 16:38:17 WARN scheduler.TaskSetManager: Lost task 150.0 in stage
> 163.0 (TID 6855, HDD013, executor 95):
> org.apache.carbondata.core.datastore.exception.IndexBuilderException:
> Block B-tree loading failed
> at
> org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:286)
> at
> org.apache.carbondata.core.datastore.BlockIndexStore.getAll(BlockIndexStore.java:194)
> at
> org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.initQuery(AbstractQueryExecutor.java:132)
> at
> org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.getBlockExecutionInfos(AbstractQueryExecutor.java:187)
> at
> org.apache.carbondata.core.scan.executor.impl.VectorDetailQueryExecutor.execute(VectorDetailQueryExecutor.java:36)
> at
> org.apache.carbondata.spark.vectorreader.VectorizedCarbonRecordReader.initialize(VectorizedCarbonRecordReader.java:112)
> at
> org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:213)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.scheduler.Task.run(Task.scala:99)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.util.concurrent.ExecutionException:
> java.io.FileNotFoundException: File does not exist:
> /user/e_carbon/public/carbon.store/e_carbon/offer_inst_c/Fact/Part0/Segment_22.15/part-0-8_batchno0-0-1516091074114.carbondata
> 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:652)
> 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$1.run(Server.java:2151)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2147)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2145)
>
> at java.util.concurrent.FutureTask.report(FutureTask.java:122)
> at java.util.concurrent.FutureTask.get(FutureTask.java:192)
> at
> org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:271)
> ... 21 more
> Caused by: java.io.FileNotFoundException: File does not exist:
> /user/e_carbon/public/carbon.store/e_carbon/offer_inst_c/Fact/Part0/Segment_22.15/part-0-8_batchno0-0-1516091074114.carbondata
> 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:652)
> 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$1.run(Server.java:2151)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2147)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2145)
>
> at sun.reflect.GeneratedConstructorAccessor29.newInstance(Unknown Source)
> 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: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:304)
> at
> org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:299)
> at
> org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
> at
> org.apache.hadoop.hdfs.DistributedFileSystem.open(DistributedFileSystem.java:312)
> at
> org.apache.carbondata.core.datastore.impl.FileFactory.getDataInputStream_(FileFactory.java:208)
> at
> org.apache.carbondata.core.datastore.impl.FileFactory.getDataInputStream(FileFactory.java:180)
> at
> org.apache.carbondata.core.reader.ThriftReader.open(ThriftReader.java:77)
> at
> org.apache.carbondata.core.reader.CarbonHeaderReader.readHeader(CarbonHeaderReader.java:46)
> at
> org.apache.carbondata.core.util.DataFileFooterConverterV3.readDataFileFooter(DataFileFooterConverterV3.java:53)
> at
> org.apache.carbondata.core.util.CarbonUtil.readMetadatFile(CarbonUtil.java:1021)
> at
> org.apache.carbondata.core.datastore.AbstractBlockIndexStoreCache.checkAndLoadTableBlocks(AbstractBlockIndexStoreCache.java:98)
> at
> org.apache.carbondata.core.datastore.BlockIndexStore.loadBlock(BlockIndexStore.java:326)
> at
> org.apache.carbondata.core.datastore.BlockIndexStore.get(BlockIndexStore.java:110)
> at
> org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:316)
> at
> org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:306)
> at java.util.concurrent.FutureTask.run(FutureTask.java:266)
> ... 3 more
> Caused by:
> org.apache.hadoop.ipc.RemoteException(java.io.FileNotFoundException): File
> does not exist:
> /user/e_carbon/public/carbon.store/e_carbon/offer_inst_c/Fact/Part0/Segment_22.15/part-0-8_batchno0-0-1516091074114.carbondata
> at
> org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:71)
> at
> org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:61)
> at
> org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1828)
> at
> org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1799)
> at
> org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1712)
> at
> org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:652)
> at
> org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:365)
> at
> org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$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$1.run(Server.java:2151)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2147)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2145)
>
> 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$Invoker.invoke(ProtobufRpcEngine.java:229)
> at com.sun.proxy.$Proxy17.getBlockLocations(Unknown Source)
> at
> org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getBlockLocations(ClientNamenodeProtocolTranslatorPB.java:255)
> at sun.reflect.GeneratedMethodAccessor11.invoke(Unknown Source)
> 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:191)
> at
> org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
> at com.sun.proxy.$Proxy18.getBlockLocations(Unknown Source)
> at
> org.apache.hadoop.hdfs.DFSClient.callGetBlockLocations(DFSClient.java:1226)
> ... 25 more
>
>
>
> yixu2001
--
Sent from:
http://apache-carbondata-dev-mailing-list-archive.1130556.n5.nabble.com/
