[jira] [Created] (KYLIN-2634) kylin build stops while building dimension dictionary with file not found exception

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

[jira] [Created] (KYLIN-2634) kylin build stops while building dimension dictionary with file not found exception

JIRA jira@apache.org
flashput created KYLIN-2634:
-------------------------------

             Summary: kylin build stops while building dimension dictionary with file not found exception
                 Key: KYLIN-2634
                 URL: https://issues.apache.org/jira/browse/KYLIN-2634
             Project: Kylin
          Issue Type: Bug
          Components: Job Engine
    Affects Versions: v2.0.0
         Environment: CentOS release 6.8 (Final) x64

            Reporter: flashput
            Assignee: Dong Li
         Attachments: kylin_hive_conf.xml, kylin_job_conf.xml, kylin.log, kylin.properties

Model description:
{
  "uuid": "c39058c4-3e9d-4c0c-a908-c8efef41cc91",
  "last_modified": 1495117591531,
  "version": "2.0.0",
  "name": "LOG_PV",
  "owner": "ADMIN",
  "description": "",
  "fact_table": "DEFAULT.LOG_DATA_170416",
  "lookups": [],
  "dimensions": [
    {
      "table": "LOG_DATA_170416",
      "columns": [
        "U_DOMAIN",
        "U_PAGE",
        "R_DOMAIN",
        "R_PAGE",
        "AGENT",
        "IP"
      ]
    }
  ],
  "metrics": [
    "LOG_DATA_170416.LOAD_TIME",
    "LOG_DATA_170416.ARTICLE_CONTENT_HEIGHT"
  ],
  "filter_condition": "",
  "partition_desc": {
    "partition_date_column": null,
    "partition_time_column": null,
    "partition_date_start": 0,
    "partition_date_format": "yyyyMMdd",
    "partition_time_format": "HH:mm:ss",
    "partition_type": "APPEND",
    "partition_condition_builder": "org.apache.kylin.metadata.model.PartitionDesc$DefaultPartitionConditionBuilder"
  },
  "capacity": "MEDIUM"
}

Cube description json:
{
  "uuid": "b475f98a-1ec2-45ad-a2eb-90217aa83d9b",
  "last_modified": 1495117617084,
  "version": "2.0.0",
  "name": "cc",
  "model_name": "LOG_PV",
  "description": "",
  "null_string": null,
  "dimensions": [
    {
      "name": "IP",
      "table": "LOG_DATA_170416",
      "column": "IP",
      "derived": null
    },
    {
      "name": "U_DOMAIN",
      "table": "LOG_DATA_170416",
      "column": "U_DOMAIN",
      "derived": null
    },
    {
      "name": "U_PAGE",
      "table": "LOG_DATA_170416",
      "column": "U_PAGE",
      "derived": null
    },
    {
      "name": "R_DOMAIN",
      "table": "LOG_DATA_170416",
      "column": "R_DOMAIN",
      "derived": null
    },
    {
      "name": "R_PAGE",
      "table": "LOG_DATA_170416",
      "column": "R_PAGE",
      "derived": null
    },
    {
      "name": "AGENT",
      "table": "LOG_DATA_170416",
      "column": "AGENT",
      "derived": null
    }
  ],
  "measures": [
    {
      "name": "_COUNT_",
      "function": {
        "expression": "COUNT",
        "parameter": {
          "type": "constant",
          "value": "1"
        },
        "returntype": "bigint"
      }
    }
  ],
  "dictionaries": [],
  "rowkey": {
    "rowkey_columns": [
      {
        "column": "LOG_DATA_170416.IP",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "LOG_DATA_170416.U_DOMAIN",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "LOG_DATA_170416.U_PAGE",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "LOG_DATA_170416.R_DOMAIN",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "LOG_DATA_170416.R_PAGE",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "LOG_DATA_170416.AGENT",
        "encoding": "dict",
        "isShardBy": false
      }
    ]
  },
  "hbase_mapping": {
    "column_family": [
      {
        "name": "F1",
        "columns": [
          {
            "qualifier": "M",
            "measure_refs": [
              "_COUNT_"
            ]
          }
        ]
      }
    ]
  },
  "aggregation_groups": [
    {
      "includes": [
        "LOG_DATA_170416.IP",
        "LOG_DATA_170416.U_DOMAIN",
        "LOG_DATA_170416.U_PAGE",
        "LOG_DATA_170416.R_DOMAIN",
        "LOG_DATA_170416.R_PAGE",
        "LOG_DATA_170416.AGENT"
      ],
      "select_rule": {
        "hierarchy_dims": [],
        "mandatory_dims": [],
        "joint_dims": []
      }
    }
  ],
  "signature": "ALTH7M0wbIA5eA96sGbvCg==",
  "notify_list": [],
  "status_need_notify": [
    "ERROR",
    "DISCARDED",
    "SUCCEED"
  ],
  "partition_date_start": 0,
  "partition_date_end": 3153600000000,
  "auto_merge_time_ranges": [
    604800000,
    2419200000
  ],
  "retention_range": 0,
  "engine_type": 4,
  "storage_type": 2,
  "override_kylin_properties": {}
}


File not found Exception occured when doing Cube building .
build stops at #4 Step Name: Build Dimension Dictionary

Job error log:

java.io.FileNotFoundException: File does not exist: /kylin/kylin_metadata/resources/dict/DEFAULT.LOG_DATA_170416/IP/56abfe1f-1fdf-4bec-baec-43721e693c32.dict
        at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:66)
        at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:56)
        at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsUpdateTimes(FSNamesystem.java:1963)
        at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1904)
        at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1884)
        at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1856)
        at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:568)
        at org.apache.hadoop.hdfs.server.namenode.AuthorizationProviderProxyClientProtocol.getBlockLocations(AuthorizationProviderProxyClientProtocol.java:89)
        at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:363)
        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$1.run(Server.java:2086)
        at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2082)
        at java.security.AccessController.doPrivileged(Native Method)
        at javax.security.auth.Subject.doAs(Subject.java:422)
        at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1698)
        at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2080)

        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:106)
        at org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:73)
        at org.apache.hadoop.hdfs.DFSClient.callGetBlockLocations(DFSClient.java:1280)
        at org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1265)
        at org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1253)
        at org.apache.hadoop.hdfs.DFSInputStream.fetchLocatedBlocksAndGetLastBlockLength(DFSInputStream.java:305)
        at org.apache.hadoop.hdfs.DFSInputStream.openInfo(DFSInputStream.java:271)
        at org.apache.hadoop.hdfs.DFSInputStream.<init>(DFSInputStream.java:263)
        at org.apache.hadoop.hdfs.DFSClient.open(DFSClient.java:1584)
        at org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:309)
        at org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:305)
        at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
        at org.apache.hadoop.hdfs.DistributedFileSystem.open(DistributedFileSystem.java:305)
        at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:780)
        at org.apache.kylin.storage.hbase.HBaseResourceStore.getInputStream(HBaseResourceStore.java:207)
        at org.apache.kylin.storage.hbase.HBaseResourceStore.access$000(HBaseResourceStore.java:58)
        at org.apache.kylin.storage.hbase.HBaseResourceStore$2.visit(HBaseResourceStore.java:173)
        at org.apache.kylin.storage.hbase.HBaseResourceStore.visitFolder(HBaseResourceStore.java:143)
        at org.apache.kylin.storage.hbase.HBaseResourceStore.getAllResourcesImpl(HBaseResourceStore.java:168)
        at org.apache.kylin.common.persistence.ResourceStore.getAllResources(ResourceStore.java:182)
        at org.apache.kylin.common.persistence.ResourceStore.getAllResources(ResourceStore.java:175)
        at org.apache.kylin.dict.DictionaryManager.checkDupByInfo(DictionaryManager.java:374)
        at org.apache.kylin.dict.DictionaryManager.saveDictionary(DictionaryManager.java:318)
        at org.apache.kylin.cube.CubeManager.saveDictionary(CubeManager.java:234)
        at org.apache.kylin.cube.cli.DictionaryGeneratorCLI.processSegment(DictionaryGeneratorCLI.java:68)
        at org.apache.kylin.cube.cli.DictionaryGeneratorCLI.processSegment(DictionaryGeneratorCLI.java:54)
        at org.apache.kylin.engine.mr.steps.CreateDictionaryJob.run(CreateDictionaryJob.java:66)
        at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:70)
        at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:84)
        at org.apache.kylin.engine.mr.common.HadoopShellExecutable.doWork(HadoopShellExecutable.java:63)
        at org.apache.kylin.job.execution.AbstractExecutable.execute(AbstractExecutable.java:124)
        at org.apache.kylin.job.execution.DefaultChainedExecutable.doWork(DefaultChainedExecutable.java:64)
        at org.apache.kylin.job.execution.AbstractExecutable.execute(AbstractExecutable.java:124)
        at org.apache.kylin.job.impl.threadpool.DefaultScheduler$JobRunner.run(DefaultScheduler.java:142)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
        at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.hadoop.ipc.RemoteException(java.io.FileNotFoundException): File does not exist: /kylin/kylin_metadata/resources/dict/DEFAULT.LOG_DATA_170416/IP/56abfe1f-1fdf-4bec-baec-43721e693c32.dict
        at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:66)
        at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:56)
        at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsUpdateTimes(FSNamesystem.java:1963)
        at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1904)
        at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1884)
        at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1856)
        at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:568)
        at org.apache.hadoop.hdfs.server.namenode.AuthorizationProviderProxyClientProtocol.getBlockLocations(AuthorizationProviderProxyClientProtocol.java:89)
        at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:363)
        at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$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$1.run(Server.java:2086)
        at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2082)
        at java.security.AccessController.doPrivileged(Native Method)
        at javax.security.auth.Subject.doAs(Subject.java:422)
        at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1698)
        at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2080)

        at org.apache.hadoop.ipc.Client.call(Client.java:1471)
        at org.apache.hadoop.ipc.Client.call(Client.java:1408)
        at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:230)
        at com.sun.proxy.$Proxy30.getBlockLocations(Unknown Source)
        at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getBlockLocations(ClientNamenodeProtocolTranslatorPB.java:256)
        at sun.reflect.GeneratedMethodAccessor68.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:256)
        at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:104)
        at com.sun.proxy.$Proxy31.getBlockLocations(Unknown Source)
        at org.apache.hadoop.hdfs.DFSClient.callGetBlockLocations(DFSClient.java:1278)
        ... 34 more

result code:2

server configuration file added as attachment.



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)