1

我想在 EMR 上使用 hive 将数据从一个数据库表复制到另一个数据库表。下面是我用来复制数据和日期分区的 HQL。

insert into Target.exttbl_user_identification_details PARTITION(load_date="2018-04-23") select * from Source.exttbl_user_identification_details;

错误日志：（状态，以前的作者可能没有写……所以我也不太可能写）

INFO  : Compiling command(queryId=hive_20180424083045_4bf96c97-dbab-4578-8e1b-a1c2b02e1559): insert into  Target.exttbl_user_identification_details PARTITION(load_date="2018-04-23") select * from Source.exttbl_user_identification_details
INFO  : Semantic Analysis Completed
INFO  : Returning Hive schema: Schema(fieldSchemas:[FieldSchema(name:exttbl_user_identification_details.user_id, type:varchar(70), comment:null), FieldSchema(name:exttbl_user_identification_details.signed_up_flag, type:varchar(20), comment:null), FieldSchema(name:exttbl_user_identification_details.identifier, type:varchar(70), comment:null)], properties:null)
INFO  : Completed compiling command(queryId=hive_20180424083045_4bf96c97-dbab-4578-8e1b-a1c2b02e1559); Time taken: 0.838 seconds
INFO  : Concurrency mode is disabled, not creating a lock manager
INFO  : Executing command(queryId=hive_20180424083045_4bf96c97-dbab-4578-8e1b-a1c2b02e1559): insert into  Target.exttbl_user_identification_details PARTITION(load_date="2018-04-23") select * from Source.exttbl_user_identification_details
INFO  : Query ID = hive_20180424083045_4bf96c97-dbab-4578-8e1b-a1c2b02e1559
INFO  : Total jobs = 1
INFO  : Launching Job 1 out of 1
INFO  : Starting task [Stage-1:MAPRED] in serial mode
INFO  : Tez session hasn't been created yet. Opening session
ERROR : Failed to execute tez graph.
java.io.IOException: Previous writer likely failed to write hdfs://ip-*-*-*-*.ec2.internal:8020/tmp/hive/ganesh/_tez_session_dir/ea5b020d-deb8-4846-947f-db52c5b9b884/hive-hcatalog-core-2.1.1-amzn-0.jar. Failing because I am unlikely to write too.
    at org.apache.hadoop.hive.ql.exec.tez.DagUtils.localizeResource(DagUtils.java:1022) ~[hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.exec.tez.DagUtils.addTempResources(DagUtils.java:902) ~[hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.exec.tez.DagUtils.localizeTempFilesFromConf(DagUtils.java:845) ~[hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.exec.tez.TezSessionState.refreshLocalResourcesFromConf(TezSessionState.java:466) ~[hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.exec.tez.TezSessionState.openInternal(TezSessionState.java:252) ~[hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.exec.tez.TezSessionPoolManager$TezSessionPoolSession.openInternal(TezSessionPoolManager.java:622) ~[hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.exec.tez.TezSessionState.open(TezSessionState.java:206) ~[hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.exec.tez.TezTask.updateSession(TezTask.java:283) ~[hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.exec.tez.TezTask.execute(TezTask.java:155) [hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:197) [hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:100) [hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:2073) [hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1744) [hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1453) [hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1171) [hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1166) [hive-exec-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hive.service.cli.operation.SQLOperation.runQuery(SQLOperation.java:242) [hive-service-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hive.service.cli.operation.SQLOperation.access$800(SQLOperation.java:91) [hive-service-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at org.apache.hive.service.cli.operation.SQLOperation$BackgroundWork$1.run(SQLOperation.java:334) [hive-service-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at java.security.AccessController.doPrivileged(Native Method) ~[?:1.8.0_141]
    at javax.security.auth.Subject.doAs(Subject.java:422) [?:1.8.0_141]
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1698) [hadoop-common-2.7.3-amzn-2.jar:?]
    at org.apache.hive.service.cli.operation.SQLOperation$BackgroundWork.run(SQLOperation.java:347) [hive-service-2.1.1-amzn-0.jar:2.1.1-amzn-0]
    at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511) [?:1.8.0_141]
    at java.util.concurrent.FutureTask.run(FutureTask.java:266) [?:1.8.0_141]
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) [?:1.8.0_141]
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) [?:1.8.0_141]
    at java.lang.Thread.run(Thread.java:748) [?:1.8.0_141]
ERROR : FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.tez.TezTask
INFO  : Completed executing command(queryId=hive_20180424083045_4bf96c97-dbab-4578-8e1b-a1c2b02e1559); Time taken: 25.045 seconds+

如果我在这里缺少任何配置或任何东西，请提出建议。

4

0 回答 0