欢迎关注Hadoop、Spark、Flink、Hive、Hbase、Flume等大数据资料分享微信公共账号:iteblog_hadoop
  1. 文章总数:978
  2. 浏览总数:11,978,649
  3. 评论:3938
  4. 分类目录:106 个
  5. 注册用户数:6129
  6. 最后更新:2018年12月15日
过往记忆博客公众号iteblog_hadoop
欢迎关注微信公众号:
iteblog_hadoop
大数据技术博客公众号bigdata_ai
大数据猿:
bigdata_ai

Spark连接Hive的metastore异常

  在本博客的《使用Spark SQL读取Hive上的数据》文章中我介绍了如何通过Spark去读取Hive里面的数据,不过有时候我们在创建SQLContext实例的时候遇到类似下面的异常:

java.lang.RuntimeException: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient
	at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:522)
	at org.apache.spark.sql.hive.client.ClientWrapper.<init>(ClientWrapper.scala:171)
	at org.apache.spark.sql.hive.HiveContext.executionHive$lzycompute(HiveContext.scala:162)
	at org.apache.spark.sql.hive.HiveContext.executionHive(HiveContext.scala:160)
	at org.apache.spark.sql.hive.HiveContext.setConf(HiveContext.scala:391)
	at org.apache.spark.sql.SQLContext$$anonfun$5.apply(SQLContext.scala:235)
	at org.apache.spark.sql.SQLContext$$anonfun$5.apply(SQLContext.scala:234)
	at scala.collection.Iterator$class.foreach(Iterator.scala:727)
	at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
	at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
	at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
	at org.apache.spark.sql.SQLContext.<init>(SQLContext.scala:234)
	at org.apache.spark.sql.hive.HiveContext.<init>(HiveContext.scala:72)
	at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
	at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57)
	at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
	at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
	at org.apache.spark.repl.SparkILoop.createSQLContext(SparkILoop.scala:1028)
	at $iwC$$iwC.<init>(<console>:9)
	at $iwC.<init>(<console>:18)
	at <init>(<console>:20)
	at .<init>(<console>:24)
	at .<clinit>(<console>)
	at .<init>(<console>:7)
	at .<clinit>(<console>)
	at $print(<console>)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:606)
	at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
	at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1340)
	at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
	at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
	at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
	at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
	at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
	at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
	at org.apache.spark.repl.SparkILoopInit$$anonfun$initializeSpark$1.apply(SparkILoopInit.scala:132)
	at org.apache.spark.repl.SparkILoopInit$$anonfun$initializeSpark$1.apply(SparkILoopInit.scala:124)
	at org.apache.spark.repl.SparkIMain.beQuietDuring(SparkIMain.scala:324)
	at org.apache.spark.repl.SparkILoopInit$class.initializeSpark(SparkILoopInit.scala:124)
	at org.apache.spark.repl.SparkILoop.initializeSpark(SparkILoop.scala:64)
	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1$$anonfun$apply$mcZ$sp$5.apply$mcV$sp(SparkILoop.scala:974)
	at org.apache.spark.repl.SparkILoopInit$class.runThunks(SparkILoopInit.scala:159)
	at org.apache.spark.repl.SparkILoop.runThunks(SparkILoop.scala:64)
	at org.apache.spark.repl.SparkILoopInit$class.postInitialization(SparkILoopInit.scala:108)
	at org.apache.spark.repl.SparkILoop.postInitialization(SparkILoop.scala:64)
	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:991)
	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$$process(SparkILoop.scala:945)
	at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
	at org.apache.spark.repl.Main$.main(Main.scala:31)
	at org.apache.spark.repl.Main.main(Main.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:606)
	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:674)
	at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
	at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
	at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:120)
	at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient
	at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1523)
	at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.<init>(RetryingMetaStoreClient.java:86)
	at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:132)
	at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:104)
	at org.apache.hadoop.hive.ql.metadata.Hive.createMetaStoreClient(Hive.java:3005)
	at org.apache.hadoop.hive.ql.metadata.Hive.getMSC(Hive.java:3024)
	at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:503)
	... 64 more
Caused by: java.lang.reflect.InvocationTargetException
	at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
	at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57)
	at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
	at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
	at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1521)
	... 70 more
Caused by: MetaException(message:Version information not found in metastore. )
	at org.apache.hadoop.hive.metastore.ObjectStore.checkSchema(ObjectStore.java:6664)
	at org.apache.hadoop.hive.metastore.ObjectStore.verifySchema(ObjectStore.java:6645)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:606)
	at org.apache.hadoop.hive.metastore.RawStoreProxy.invoke(RawStoreProxy.java:114)
	at com.sun.proxy.$Proxy14.verifySchema(Unknown Source)
	at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.getMS(HiveMetaStore.java:572)
	at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.createDefaultDB(HiveMetaStore.java:620)
	at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.init(HiveMetaStore.java:461)
	at org.apache.hadoop.hive.metastore.RetryingHMSHandler.<init>(RetryingHMSHandler.java:66)
	at org.apache.hadoop.hive.metastore.RetryingHMSHandler.getProxy(RetryingHMSHandler.java:72)
	at org.apache.hadoop.hive.metastore.HiveMetaStore.newRetryingHMSHandler(HiveMetaStore.java:5762)
	at org.apache.hadoop.hive.metastore.HiveMetaStoreClient.<init>(HiveMetaStoreClient.java:199)
	at org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.<init>(SessionHiveMetaStoreClient.java:74)
	... 75 more

这是因为在创建SQLContext实例的时候,要求spark编译的Hive版本和HiveMetaStore里面记录的Hive版本一致,我们可以通过配置hive.metastore.schema.verification参数来取消这种验证,这个参数的默认值是true,我们可以取消验证,配置如下:

<property>  
   <name>hive.metastore.schema.verification</name>  
   <value>false</value>  
    <description>  
    Enforce metastore schema version consistency.  
    True: Verify that version information stored in metastore matches with one from Hive jars.  Also disable automatic  
          schema migration attempt. Users are required to manully migrate schema after Hive upgrade which ensures  
          proper metastore schema migration. (Default)  
    False: Warn if the version information stored in metastore doesn't match with one from in Hive jars.  
    </description>  
 </property> 

然后我们再启动Spark,这时候就可以创建SQLContext实例了。

本博客文章除特别声明,全部都是原创!
转载本文请加上:转载自过往记忆(https://www.iteblog.com/)
本文链接: 【Spark连接Hive的metastore异常】(https://www.iteblog.com/archives/1563.html)
喜欢 (10)
分享 (0)
发表我的评论
取消评论

表情
本博客评论系统带有自动识别垃圾评论功能,请写一些有意义的评论,谢谢!
(5)个小伙伴在吐槽
  1. 在哪个配置文件配置啊?
    七侯2017-08-14 09:14 回复
    • 在 $HIVE_HOME/conf/hive-site.xml 文件里面配置。
      w3970907702017-08-14 09:28 回复
      • 昂,谢谢啊,我试试
        七侯2017-08-14 09:29 回复
        • 试了不好使呢。。。
          戈雅Andy2018-01-10 16:52 回复
  2. 你好,请问下,我用sparksql连接hive时,出现找不到数据库,
    16/03/31 01:31:08 ERROR exec.DDLTask: org.apache.hadoop.hive.ql.metadata.HiveException: Database does not exist: hive at org.apache.hadoop.hive.ql.exec.DDLTask.switchDatabase(DDLTask.java:4011) at org.apache.hadoop.hive.ql.exec.DDLTask.execute(DDLTask.java:266) at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:153) at org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:85) at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:1503) at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1270) at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1088) at org.apache.hadoop.hive.ql.Driver.run(Driver.java:911) at org.apache.hadoop.hive.ql.Driver.run(Driver.java:901) at org.apache.spark.sql.hive.HiveContext.runHive(HiveContext.scala:305) at org.apache.spark.sql.hive.HiveContext.runSqlHive(HiveContext.scala:276) at org.apache.spark.sql.hive.execution.NativeCommand.sideEffectResult$lzycompute(NativeCommand.scala:35) at org.apache.spark.sql.hive.execution.NativeCommand.sideEffectResult(NativeCommand.scala:35) at org.apache.spark.sql.execution.Command$class.execute(commands.scala:46) at org.apache.spark.sql.hive.execution.NativeCommand.execute(NativeCommand.scala:30) at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:425) at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:425) at org.apache.spark.sql.SchemaRDDLike$class.$init$(SchemaRDDLike.scala:58) at org.apache.spark.sql.SchemaRDD.(SchemaRDD.scala:108) at org.apache.spark.sql.hive.HiveContext.sql(HiveContext.scala:94) at org.apache.spark.sql.hive.thriftserver.AbstractSparkSQLDriver.run(AbstractSparkSQLDriver.scala:56) at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:275) at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:423) at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:211) at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.deploy.SparkSubmit$.launch(SparkSubmit.scala:358) at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:75) at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.DDLTask. Database does not exist: hive
    流浪在伯纳乌2016-03-31 16:51 回复