[ https://issues.apache.org/jira/browse/CARBONDATA-3925?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] yutao updated CARBONDATA-3925: ------------------------------ Description: in CarbonWriter.java code ,you can find this; public abstract class *{color:#FF0000}CarbonWriter{color}* extends ProxyFileWriter<Object[]> { private static final Logger LOGGER = LogServiceFactory.getLogService({color:#FF0000}CarbonS3Writer{color}.class.getName());} always wo can find logfile print like ; 2020-07-27 14:19:25,107 DEBUG org.apache.carbon.flink.CarbonS3Writer this is puzzled; 2020-08-19 13:14:13,329 INFO org.apache.carbondata.hadoop.api.CarbonTableOutputFormat - Closed writer task attempt_f229b922-1f77-426f-a4bc-42e49aa53df7_0000_m_1968253873_-1049302646 2020-08-19 13:14:13,329 DEBUG org.apache.carbon.flink.CarbonLocalWriter - Commit write. org.apache.carbon.flink.CarbonLocalWriter@41f5c4a9 2020-08-19 13:14:13,329 DEBUG org.apache.carbon.flink.CarbonS3Writer - Upload file[/home/hadoop/yutest/d963e9836ccb4318aa8fc953af983d07/part-0-a132f98547584dcabae6c43090626baf_batchno0-0-null-1597814047953.snappy.carbondata] to [hdfs://beh/user/dc_cbss/warehouse/yutest/tf_b_trade/stage_data] start. 2020-08-19 13:14:13,329 INFO org.apache.carbondata.core.util.CarbonUtil - Copying /home/hadoop/yutest/d963e9836ccb4318aa8fc953af983d07/part-0-a132f98547584dcabae6c43090626baf_batchno0-0-null-1597814047953.snappy.carbondata to hdfs://beh/user/dc_cbss/warehouse/yutest/tf_b_trade/stage_data, operation id 1597814053329 2020-08-19 13:14:13,331 DEBUG org.apache.carbondata.core.util.CarbonUtil -{color:#FF0000} The configured block size is 1 KB, the actual carbon file size is 277 KB, choose the max value 277 KB as the block size on HDFS{color} 2020-08-19 13:14:13,331 DEBUG org.apache.carbondata.core.util.CarbonUtil - HDFS file block size for file: hdfs://beh/user/dc_cbss/warehouse/yutest/tf_b_trade/stage_data/part-0-a132f98547584dcabae6c43090626baf_batchno0-0-null-1597814047953.snappy.carbondata is 284160 (bytes 2020-08-19 13:14:13,332 INFO org.apache.carbondata.processing.util.CarbonLoaderUtil - Deleted the local store location: /tmp/f97548ae6efc43d2ba269c9d35295bb9_attempt_f229b922-1f77-426f-a4bc-42e49aa53df7_0000_m_1968253873_-1049302646 : Time taken: 2 2020-08-19 13:14:13,358 ERROR org.apache.carbon.flink.CarbonS3Writer - Problem while copying file from local store to carbon store org.apache.carbondata.core.datastore.exception.CarbonDataWriterException: Problem while copying file from local store to carbon store at org.apache.carbondata.core.util.CarbonUtil.copyCarbonDataFileToCarbonStorePath(CarbonUtil.java:2694) at org.apache.carbon.flink.CarbonWriter.uploadSegmentDataFiles(CarbonWriter.java:90) at org.apache.carbon.flink.CarbonLocalWriter.commit(CarbonLocalWriter.java:155) at org.apache.carbon.flink.CarbonLocalWriter.flush(CarbonLocalWriter.java:129) at org.apache.flink.streaming.api.functions.sink.filesystem.BulkPartWriter.closeForCommit(BulkPartWriter.java:61) at org.apache.flink.streaming.api.functions.sink.filesystem.Bucket.closePartFile(Bucket.java:239) at org.apache.flink.streaming.api.functions.sink.filesystem.Bucket.prepareBucketForCheckpointing(Bucket.java:280) at org.apache.flink.streaming.api.functions.sink.filesystem.Bucket.onReceptionOfCheckpoint(Bucket.java:253) at org.apache.flink.streaming.api.functions.sink.filesystem.Buckets.snapshotActiveBuckets(Buckets.java:250) at org.apache.flink.streaming.api.functions.sink.filesystem.Buckets.snapshotState(Buckets.java:241) at org.apache.flink.streaming.api.functions.sink.filesystem.StreamingFileSink.snapshotState(StreamingFileSink.java:447) at org.apache.flink.streaming.util.functions.StreamingFunctionUtils.trySnapshotFunctionState(StreamingFunctionUtils.java:118) at org.apache.flink.streaming.util.functions.StreamingFunctionUtils.snapshotFunctionState(StreamingFunctionUtils.java:99) at org.apache.flink.streaming.api.operators.AbstractUdfStreamOperator.snapshotState(AbstractUdfStreamOperator.java:90) at org.apache.flink.streaming.api.operators.AbstractStreamOperator.snapshotState(AbstractStreamOperator.java:402) at org.apache.flink.streaming.runtime.tasks.StreamTask$CheckpointingOperation.checkpointStreamOperator(StreamTask.java:1403) at org.apache.flink.streaming.runtime.tasks.StreamTask$CheckpointingOperation.executeCheckpointing(StreamTask.java:1337) at org.apache.flink.streaming.runtime.tasks.StreamTask.checkpointState(StreamTask.java:974) at org.apache.flink.streaming.runtime.tasks.StreamTask.lambda$performCheckpoint$5(StreamTask.java:870) at org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$SynchronizedStreamTaskActionExecutor.runThrowing(StreamTaskActionExecutor.java:94) at org.apache.flink.streaming.runtime.tasks.StreamTask.performCheckpoint(StreamTask.java:843) at org.apache.flink.streaming.runtime.tasks.StreamTask.triggerCheckpointOnBarrier(StreamTask.java:803) at org.apache.flink.streaming.runtime.io.CheckpointBarrierHandler.notifyCheckpoint(CheckpointBarrierHandler.java:86) at org.apache.flink.streaming.runtime.io.CheckpointBarrierAligner.processBarrier(CheckpointBarrierAligner.java:177) at org.apache.flink.streaming.runtime.io.CheckpointedInputGate.pollNext(CheckpointedInputGate.java:155) at org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.emitNext(StreamTaskNetworkInput.java:133) at org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:69) at org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:310) at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:187) at org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:485) at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:469) at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:708) at org.apache.flink.runtime.taskmanager.Task.run(Task.java:533) at java.lang.Thread.run(Thread.java:748) {color:#FF0000}Caused by: org.apache.hadoop.ipc.RemoteException(java.io.IOException): Specified block size is less than configured minimum value (dfs.namenode.fs-limits.min-block-size): 284160 < 1048576{color} at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInt(FSNamesystem.java:2821) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:2774) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.create(NameNodeRpcServer.java:610) at org.apache.hadoop.hdfs.server.namenode.AuthorizationProviderProxyClientProtocol.create(AuthorizationProviderProxyClientProtocol.java:117) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.create(ClientNamenodeProtocolServerSideTranslatorPB.java:413) at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java) at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:617) at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1073) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2278) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2274) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1924) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2272) at org.apache.hadoop.ipc.Client.call(Client.java:1476) at org.apache.hadoop.ipc.Client.call(Client.java:1413) at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229) at com.sun.proxy.$Proxy23.create(Unknown Source) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.create(ClientNamenodeProtocolTranslatorPB.java:296) 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:191) at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102) at com.sun.proxy.$Proxy24.create(Unknown Source) at org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1652) at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1689) at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1624) at org.apache.hadoop.hdfs.DistributedFileSystem$7.doCall(DistributedFileSystem.java:448) at org.apache.hadoop.hdfs.DistributedFileSystem$7.doCall(DistributedFileSystem.java:444) at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:459) at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:387) at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:910) at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:891) at org.apache.carbondata.core.datastore.filesystem.AbstractDFSCarbonFile.getDataOutputStream(AbstractDFSCarbonFile.java:363) at org.apache.carbondata.core.datastore.filesystem.AbstractDFSCarbonFile.getDataOutputStream(AbstractDFSCarbonFile.java:357) at org.apache.carbondata.core.datastore.impl.FileFactory.getDataOutputStream(FileFactory.java:252) at org.apache.carbondata.core.util.CarbonUtil.copyLocalFileToCarbonStore(CarbonUtil.java:2721) at org.apache.carbondata.core.util.CarbonUtil.copyCarbonDataFileToCarbonStorePath(CarbonUtil.java:2678) ... 33 more was: in CarbonWriter.java code ,you can find this; public abstract class *{color:red}CarbonWriter{color}* extends ProxyFileWriter<Object[]> { private static final Logger LOGGER = LogServiceFactory.getLogService({color:red}CarbonS3Writer{color}.class.getName());} always wo can find logfile print like ; 2020-07-27 14:19:25,107 DEBUG org.apache.carbon.flink.CarbonS3Writer this is puzzled > flink-integration write carbon file to hdfs error > ------------------------------------------------- > > Key: CARBONDATA-3925 > URL: https://issues.apache.org/jira/browse/CARBONDATA-3925 > Project: CarbonData > Issue Type: Bug > Components: flink-integration > Affects Versions: 2.0.0 > Reporter: yutao > Priority: Major > Fix For: 2.1.0, 2.0.1 > > > in CarbonWriter.java code ,you can find this; > public abstract class *{color:#FF0000}CarbonWriter{color}* extends ProxyFileWriter<Object[]> { > private static final Logger LOGGER = > LogServiceFactory.getLogService({color:#FF0000}CarbonS3Writer{color}.class.getName());} > always wo can find logfile print like ; > 2020-07-27 14:19:25,107 DEBUG org.apache.carbon.flink.CarbonS3Writer > this is puzzled; > 2020-08-19 13:14:13,329 INFO org.apache.carbondata.hadoop.api.CarbonTableOutputFormat - Closed writer task attempt_f229b922-1f77-426f-a4bc-42e49aa53df7_0000_m_1968253873_-1049302646 > 2020-08-19 13:14:13,329 DEBUG org.apache.carbon.flink.CarbonLocalWriter - Commit write. org.apache.carbon.flink.CarbonLocalWriter@41f5c4a9 > 2020-08-19 13:14:13,329 DEBUG org.apache.carbon.flink.CarbonS3Writer - Upload file[/home/hadoop/yutest/d963e9836ccb4318aa8fc953af983d07/part-0-a132f98547584dcabae6c43090626baf_batchno0-0-null-1597814047953.snappy.carbondata] to [hdfs://beh/user/dc_cbss/warehouse/yutest/tf_b_trade/stage_data] start. > 2020-08-19 13:14:13,329 INFO org.apache.carbondata.core.util.CarbonUtil - Copying /home/hadoop/yutest/d963e9836ccb4318aa8fc953af983d07/part-0-a132f98547584dcabae6c43090626baf_batchno0-0-null-1597814047953.snappy.carbondata to hdfs://beh/user/dc_cbss/warehouse/yutest/tf_b_trade/stage_data, operation id 1597814053329 > 2020-08-19 13:14:13,331 DEBUG org.apache.carbondata.core.util.CarbonUtil -{color:#FF0000} The configured block size is 1 KB, the actual carbon file size is 277 KB, choose the max value 277 KB as the block size on HDFS{color} > 2020-08-19 13:14:13,331 DEBUG org.apache.carbondata.core.util.CarbonUtil - HDFS file block size for file: hdfs://beh/user/dc_cbss/warehouse/yutest/tf_b_trade/stage_data/part-0-a132f98547584dcabae6c43090626baf_batchno0-0-null-1597814047953.snappy.carbondata is 284160 (bytes > 2020-08-19 13:14:13,332 INFO org.apache.carbondata.processing.util.CarbonLoaderUtil - Deleted the local store location: /tmp/f97548ae6efc43d2ba269c9d35295bb9_attempt_f229b922-1f77-426f-a4bc-42e49aa53df7_0000_m_1968253873_-1049302646 : Time taken: 2 > 2020-08-19 13:14:13,358 ERROR org.apache.carbon.flink.CarbonS3Writer - Problem while copying file from local store to carbon store > org.apache.carbondata.core.datastore.exception.CarbonDataWriterException: Problem while copying file from local store to carbon store > at org.apache.carbondata.core.util.CarbonUtil.copyCarbonDataFileToCarbonStorePath(CarbonUtil.java:2694) > at org.apache.carbon.flink.CarbonWriter.uploadSegmentDataFiles(CarbonWriter.java:90) > at org.apache.carbon.flink.CarbonLocalWriter.commit(CarbonLocalWriter.java:155) > at org.apache.carbon.flink.CarbonLocalWriter.flush(CarbonLocalWriter.java:129) > at org.apache.flink.streaming.api.functions.sink.filesystem.BulkPartWriter.closeForCommit(BulkPartWriter.java:61) > at org.apache.flink.streaming.api.functions.sink.filesystem.Bucket.closePartFile(Bucket.java:239) > at org.apache.flink.streaming.api.functions.sink.filesystem.Bucket.prepareBucketForCheckpointing(Bucket.java:280) > at org.apache.flink.streaming.api.functions.sink.filesystem.Bucket.onReceptionOfCheckpoint(Bucket.java:253) > at org.apache.flink.streaming.api.functions.sink.filesystem.Buckets.snapshotActiveBuckets(Buckets.java:250) > at org.apache.flink.streaming.api.functions.sink.filesystem.Buckets.snapshotState(Buckets.java:241) > at org.apache.flink.streaming.api.functions.sink.filesystem.StreamingFileSink.snapshotState(StreamingFileSink.java:447) > at org.apache.flink.streaming.util.functions.StreamingFunctionUtils.trySnapshotFunctionState(StreamingFunctionUtils.java:118) > at org.apache.flink.streaming.util.functions.StreamingFunctionUtils.snapshotFunctionState(StreamingFunctionUtils.java:99) > at org.apache.flink.streaming.api.operators.AbstractUdfStreamOperator.snapshotState(AbstractUdfStreamOperator.java:90) > at org.apache.flink.streaming.api.operators.AbstractStreamOperator.snapshotState(AbstractStreamOperator.java:402) > at org.apache.flink.streaming.runtime.tasks.StreamTask$CheckpointingOperation.checkpointStreamOperator(StreamTask.java:1403) > at org.apache.flink.streaming.runtime.tasks.StreamTask$CheckpointingOperation.executeCheckpointing(StreamTask.java:1337) > at org.apache.flink.streaming.runtime.tasks.StreamTask.checkpointState(StreamTask.java:974) > at org.apache.flink.streaming.runtime.tasks.StreamTask.lambda$performCheckpoint$5(StreamTask.java:870) > at org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$SynchronizedStreamTaskActionExecutor.runThrowing(StreamTaskActionExecutor.java:94) > at org.apache.flink.streaming.runtime.tasks.StreamTask.performCheckpoint(StreamTask.java:843) > at org.apache.flink.streaming.runtime.tasks.StreamTask.triggerCheckpointOnBarrier(StreamTask.java:803) > at org.apache.flink.streaming.runtime.io.CheckpointBarrierHandler.notifyCheckpoint(CheckpointBarrierHandler.java:86) > at org.apache.flink.streaming.runtime.io.CheckpointBarrierAligner.processBarrier(CheckpointBarrierAligner.java:177) > at org.apache.flink.streaming.runtime.io.CheckpointedInputGate.pollNext(CheckpointedInputGate.java:155) > at org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.emitNext(StreamTaskNetworkInput.java:133) > at org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:69) > at org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:310) > at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:187) > at org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:485) > at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:469) > at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:708) > at org.apache.flink.runtime.taskmanager.Task.run(Task.java:533) > at java.lang.Thread.run(Thread.java:748) > {color:#FF0000}Caused by: org.apache.hadoop.ipc.RemoteException(java.io.IOException): Specified block size is less than configured minimum value (dfs.namenode.fs-limits.min-block-size): 284160 < 1048576{color} > at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInt(FSNamesystem.java:2821) > at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:2774) > at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.create(NameNodeRpcServer.java:610) > at org.apache.hadoop.hdfs.server.namenode.AuthorizationProviderProxyClientProtocol.create(AuthorizationProviderProxyClientProtocol.java:117) > at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.create(ClientNamenodeProtocolServerSideTranslatorPB.java:413) > at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java) > at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:617) > at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1073) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2278) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2274) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:422) > at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1924) > at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2272) > at org.apache.hadoop.ipc.Client.call(Client.java:1476) > at org.apache.hadoop.ipc.Client.call(Client.java:1413) > at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229) > at com.sun.proxy.$Proxy23.create(Unknown Source) > at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.create(ClientNamenodeProtocolTranslatorPB.java:296) > 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:191) > at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102) > at com.sun.proxy.$Proxy24.create(Unknown Source) > at org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1652) > at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1689) > at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1624) > at org.apache.hadoop.hdfs.DistributedFileSystem$7.doCall(DistributedFileSystem.java:448) > at org.apache.hadoop.hdfs.DistributedFileSystem$7.doCall(DistributedFileSystem.java:444) > at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) > at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:459) > at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:387) > at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:910) > at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:891) > at org.apache.carbondata.core.datastore.filesystem.AbstractDFSCarbonFile.getDataOutputStream(AbstractDFSCarbonFile.java:363) > at org.apache.carbondata.core.datastore.filesystem.AbstractDFSCarbonFile.getDataOutputStream(AbstractDFSCarbonFile.java:357) > at org.apache.carbondata.core.datastore.impl.FileFactory.getDataOutputStream(FileFactory.java:252) > at org.apache.carbondata.core.util.CarbonUtil.copyLocalFileToCarbonStore(CarbonUtil.java:2721) > at org.apache.carbondata.core.util.CarbonUtil.copyCarbonDataFileToCarbonStorePath(CarbonUtil.java:2678) > ... 33 more -- This message was sent by Atlassian Jira (v8.3.4#803005) |
Free forum by Nabble | Edit this page |