我们正在为我们的数据仓库需求设置蜂巢，并使用spark进行处理，同时将hive作为存储。我们的文件非常小（<10KB）但数量巨大。要求是提供近乎实时的数据。所以我的方法每个都在hive上创建一个分区来指示它的CURRENT或PAST。继续发布当前数据，但在一定时间间隔后聚合它并移动到分区PAST。但是当移动操作正在进行时，我需要锁定表，因为它可能会提供不准确的数据。
对于hive CLI没有问题。
hive> LOCK TABLE t26013_75 exclusive;
OK
Time taken: 0.106 seconds
但是当我在火花上尝试相同时
scala> val hiveContext = new HiveContext(sc)
16/04/07 07:14:55 INFO hive.HiveContext: Initializing execution hive, version 0.13.1
hiveContext: org.apache.spark.sql.hive.HiveContext = org.apache.spark.sql.hive.HiveContext@723fadfe
scala> hiveContext.sql("LOCK TABLE ma.t26013_75 exclusive")
16/04/07 07:15:00 INFO parse.ParseDriver: Parsing command: LOCK TABLE ma.t26013_75 exclusive
16/04/07 07:15:00 INFO parse.ParseDriver: Parse Completed
16/04/07 07:15:00 INFO hive.HiveContext: Initializing HiveMetastoreConnection version 0.13.1 using Spark classes.
16/04/07 07:15:01 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
16/04/07 07:15:01 INFO hive.metastore: Trying to connect to metastore with URI thrift://localhost:9083
16/04/07 07:15:01 INFO hive.metastore: Connected to metastore.
16/04/07 07:15:02 INFO session.SessionState: No Tez session required at this point. hive.execution.engine=mr.
16/04/07 07:15:02 INFO log.PerfLogger: <PERFLOG method=Driver.run from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO log.PerfLogger: <PERFLOG method=TimeToSubmit from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO ql.Driver: Concurrency mode is disabled, not creating a lock manager
16/04/07 07:15:02 INFO log.PerfLogger: <PERFLOG method=compile from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO log.PerfLogger: <PERFLOG method=parse from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO parse.ParseDriver: Parsing command: LOCK TABLE ma.t26013_75 exclusive
16/04/07 07:15:02 INFO parse.ParseDriver: Parse Completed
16/04/07 07:15:02 INFO log.PerfLogger: </PERFLOG method=parse start=1460027702353 end=1460027702784 duration=431 from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO log.PerfLogger: <PERFLOG method=semanticAnalyze from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO ql.Driver: Semantic Analysis Completed
16/04/07 07:15:02 INFO log.PerfLogger: </PERFLOG method=semanticAnalyze start=1460027702785 end=1460027702832 duration=47 from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO ql.Driver: Returning Hive schema: Schema(fieldSchemas:null, properties:null)
16/04/07 07:15:02 INFO log.PerfLogger: </PERFLOG method=compile start=1460027702328 end=1460027702841 duration=513 from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO log.PerfLogger: <PERFLOG method=Driver.execute from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO ql.Driver: Starting command: LOCK TABLE ma.t26013_75 exclusive
16/04/07 07:15:02 INFO log.PerfLogger: </PERFLOG method=TimeToSubmit start=1460027702325 end=1460027702861 duration=536 from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO log.PerfLogger: <PERFLOG method=runTasks from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO log.PerfLogger: <PERFLOG method=task.DDL.Stage-0 from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO lockmgr.DummyTxnManager: Concurrency mode is disabled, not creating a lock manager
16/04/07 07:15:02 ERROR exec.DDLTask: org.apache.hadoop.hive.ql.metadata.HiveException: lock Table LockManager not specified
at org.apache.hadoop.hive.ql.exec.DDLTask.lockTable(DDLTask.java:2880)
at org.apache.hadoop.hive.ql.exec.DDLTask.execute(DDLTask.java:405)
at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:153)
at org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:85)
at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:1503)
at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1270)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1088)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:911)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:901)
at org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$runHive$1.apply(ClientWrapper.scala:345)
at org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$runHive$1.apply(ClientWrapper.scala:326)
at org.apache.spark.sql.hive.client.ClientWrapper.withHiveState(ClientWrapper.scala:155)
at org.apache.spark.sql.hive.client.ClientWrapper.runHive(ClientWrapper.scala:326)
at org.apache.spark.sql.hive.client.ClientWrapper.runSqlHive(ClientWrapper.scala:316)
at org.apache.spark.sql.hive.HiveContext.runSqlHive(HiveContext.scala:473)
at org.apache.spark.sql.hive.execution.HiveNativeCommand.run(HiveNativeCommand.scala:33)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:68)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:87)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:950)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:950)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:144)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:128)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:755)
at $line68.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:27)
at $line68.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:32)
at $line68.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:34)
at $line68.$read$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:36)
at $line68.$read$$iwC$$iwC$$iwC$$iwC.<init>(<console>:38)
at $line68.$read$$iwC$$iwC$$iwC.<init>(<console>:40)
at $line68.$read$$iwC$$iwC.<init>(<console>:42)
at $line68.$read$$iwC.<init>(<console>:44)
at $line68.$read.<init>(<console>:46)
at $line68.$read$.<init>(<console>:50)
at $line68.$read$.<clinit>(<console>)
at $line68.$eval$.<init>(<console>:7)
at $line68.$eval$.<clinit>(<console>)
at $line68.$eval.$print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1338)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:665)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:170)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:193)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:112)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
16/04/07 07:15:02 ERROR ql.Driver: FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.DDLTask. lock Table LockManager not specified
16/04/07 07:15:02 INFO log.PerfLogger: </PERFLOG method=Driver.execute start=1460027702841 end=1460027702880 duration=39 from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO log.PerfLogger: <PERFLOG method=releaseLocks from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 INFO log.PerfLogger: </PERFLOG method=releaseLocks start=1460027702880 end=1460027702880 duration=0 from=org.apache.hadoop.hive.ql.Driver>
16/04/07 07:15:02 ERROR client.ClientWrapper:
======================
HIVE FAILURE OUTPUT
======================
FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.DDLTask. lock Table LockManager not specified
======================
END HIVE FAILURE OUTPUT
======================
org.apache.spark.sql.execution.QueryExecutionException: FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.DDLTask. lock Table LockManager not specified
at org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$runHive$1.apply(ClientWrapper.scala:349)
at org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$runHive$1.apply(ClientWrapper.scala:326)
at org.apache.spark.sql.hive.client.ClientWrapper.withHiveState(ClientWrapper.scala:155)
at org.apache.spark.sql.hive.client.ClientWrapper.runHive(ClientWrapper.scala:326)
at org.apache.spark.sql.hive.client.ClientWrapper.runSqlHive(ClientWrapper.scala:316)
at org.apache.spark.sql.hive.HiveContext.runSqlHive(HiveContext.scala:473)
at org.apache.spark.sql.hive.execution.HiveNativeCommand.run(HiveNativeCommand.scala:33)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:68)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:87)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:950)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:950)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:144)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:128)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:755)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:27)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:32)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:34)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:36)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:38)
at $iwC$$iwC$$iwC.<init>(<console>:40)
at $iwC$$iwC.<init>(<console>:42)
at $iwC.<init>(<console>:44)
at <init>(<console>:46)
at .<init>(<console>:50)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1338)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:665)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:170)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:193)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:112)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
答案 0 :(得分：0)
我仔细观察了日志，并在添加以下内容后得到修复
scala> hiveContext.setConf("hive.support.concurrency","true")
我不知道为什么要问。我已经在hive / conf位置有hive-site.xml。
可能是因为我在spark / conf的hive-site.xml只有以下条目
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>thrift://localhost:9083</value>
</property>
将来可能会在spark / conf / hive-site.xml中添加此参数
感谢您的时间。