解决kylin sync table报错：MetaException(message:java.lang.ClassNotFoundException Class org.apache.hive.hcatalog.data.JsonSerDe not found

在kylin-gui中sync表default.customer_visit时报错：

2017-04-26 18:55:16,045 ERROR [http-bio-7070-exec-5] controller.BasicController:44 : 
java.lang.RuntimeException: cannot get HiveTableMeta
        at org.apache.kylin.source.hive.HiveSourceTableLoader.extractHiveTables(HiveSourceTableLoader.java:95)
        at org.apache.kylin.source.hive.HiveSourceTableLoader.reloadHiveTables(HiveSourceTableLoader.java:73)
        at org.apache.kylin.rest.service.CubeService.reloadHiveTable(CubeService.java:538)
        at org.apache.kylin.rest.service.CubeService$$FastClassBySpringCGLIB$$17a07c0e.invoke(<generated>)
        at org.springframework.cglib.proxy.MethodProxy.invoke(MethodProxy.java:204)
        at org.springframework.aop.framework.CglibAopProxy$CglibMethodInvocation.invokeJoinpoint(CglibAopProxy.java:700)
        at org.springframework.aop.framework.ReflectiveMethodInvocation.proceed(ReflectiveMethodInvocation.java:150)
        at org.springframework.security.access.intercept.aopalliance.MethodSecurityInterceptor.invoke(MethodSecurityInterceptor.java:64)
        at org.springframework.aop.framework.ReflectiveMethodInvocation.proceed(ReflectiveMethodInvocation.java:172)
        at org.springframework.aop.framework.CglibAopProxy$DynamicAdvisedInterceptor.intercept(CglibAopProxy.java:633)
        at org.apache.kylin.rest.service.CubeService$$EnhancerBySpringCGLIB$$543fa169.reloadHiveTable(<generated>)
        at org.apache.kylin.rest.controller.TableController.loadHiveTable(TableController.java:149)
        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:497)
        at org.springframework.web.method.support.InvocableHandlerMethod.doInvoke(InvocableHandlerMethod.java:221)
        at org.springframework.web.method.support.InvocableHandlerMethod.invokeForRequest(InvocableHandlerMethod.java:136)
        at org.springframework.web.servlet.mvc.method.annotation.ServletInvocableHandlerMethod.invokeAndHandle(ServletInvocableHandlerMethod.java:104)
        at org.springframework.web.servlet.mvc.method.annotation.RequestMappingHandlerAdapter.invokeHandleMethod(RequestMappingHandlerAdapter.java:743)
        at org.springframework.web.servlet.mvc.method.annotation.RequestMappingHandlerAdapter.handleInternal(RequestMappingHandlerAdapter.java:672)
        at org.springframework.web.servlet.mvc.method.AbstractHandlerMethodAdapter.handle(AbstractHandlerMethodAdapter.java:82)
        at org.springframework.web.servlet.DispatcherServlet.doDispatch(DispatcherServlet.java:933)
        at org.springframework.web.servlet.DispatcherServlet.doService(DispatcherServlet.java:867)
        at org.springframework.web.servlet.FrameworkServlet.processRequest(FrameworkServlet.java:951)
        at org.springframework.web.servlet.FrameworkServlet.doPost(FrameworkServlet.java:853)
        at javax.servlet.http.HttpServlet.service(HttpServlet.java:650)
        at org.springframework.web.servlet.FrameworkServlet.service(FrameworkServlet.java:827)
        at javax.servlet.http.HttpServlet.service(HttpServlet.java:731)
        at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:303)
        at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:208)
        at org.apache.tomcat.websocket.server.WsFilter.doFilter(WsFilter.java:52)
        at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:241)
        at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:208)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:330)
        at org.springframework.security.web.access.intercept.FilterSecurityInterceptor.invoke(FilterSecurityInterceptor.java:118)
        at org.springframework.security.web.access.intercept.FilterSecurityInterceptor.doFilter(FilterSecurityInterceptor.java:84)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.access.ExceptionTranslationFilter.doFilter(ExceptionTranslationFilter.java:113)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.session.SessionManagementFilter.doFilter(SessionManagementFilter.java:103)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.authentication.AnonymousAuthenticationFilter.doFilter(AnonymousAuthenticationFilter.java:113)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.servletapi.SecurityContextHolderAwareRequestFilter.doFilter(SecurityContextHolderAwareRequestFilter.java:54)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.savedrequest.RequestCacheAwareFilter.doFilter(RequestCacheAwareFilter.java:45)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.authentication.www.BasicAuthenticationFilter.doFilter(BasicAuthenticationFilter.java:201)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.authentication.ui.DefaultLoginPageGeneratingFilter.doFilter(DefaultLoginPageGeneratingFilter.java:91)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.authentication.AbstractAuthenticationProcessingFilter.doFilter(AbstractAuthenticationProcessingFilter.java:183)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.authentication.logout.LogoutFilter.doFilter(LogoutFilter.java:105)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.context.SecurityContextPersistenceFilter.doFilter(SecurityContextPersistenceFilter.java:87)
        at org.springframework.security.web.FilterChainProxy$VirtualFilterChain.doFilter(FilterChainProxy.java:342)
        at org.springframework.security.web.FilterChainProxy.doFilterInternal(FilterChainProxy.java:192)
        at org.springframework.security.web.FilterChainProxy.doFilter(FilterChainProxy.java:160)
        at org.springframework.web.filter.DelegatingFilterProxy.invokeDelegate(DelegatingFilterProxy.java:343)
        at org.springframework.web.filter.DelegatingFilterProxy.doFilter(DelegatingFilterProxy.java:260)
        at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:241)
        at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:208)
        at com.thetransactioncompany.cors.CORSFilter.doFilter(CORSFilter.java:209)
        at com.thetransactioncompany.cors.CORSFilter.doFilter(CORSFilter.java:244)
        at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:241)
        at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:208)
        at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:220)
        at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:122)
        at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:505)
        at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:169)
        at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:103)
        at org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:956)
        at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:116)
        at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:436)
        at org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Processor.java:1078)
        at org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(AbstractProtocol.java:625)
        at org.apache.tomcat.util.net.JIoEndpoint$SocketProcessor.run(JIoEndpoint.java:316)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
        at org.apache.tomcat.util.threads.TaskThread$WrappingRunnable.run(TaskThread.java:61)
        at java.lang.Thread.run(Thread.java:745)
Caused by: MetaException(message:java.lang.ClassNotFoundException Class org.apache.hive.hcatalog.data.JsonSerDe not found)
        at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$get_fields_result$get_fields_resultStandardScheme.read(ThriftHiveMetastore.java:23967)
        at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$get_fields_result$get_fields_resultStandardScheme.read(ThriftHiveMetastore.java:23934)
        at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$get_fields_result.read(ThriftHiveMetastore.java:23860)
        at org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:86)
        at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.recv_get_fields(ThriftHiveMetastore.java:909)
        at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.get_fields(ThriftHiveMetastore.java:895)
        at org.apache.hadoop.hive.metastore.HiveMetaStoreClient.getFields(HiveMetaStoreClient.java:1333)
        at org.apache.kylin.source.hive.CLIHiveClient.getHiveTableMeta(CLIHiveClient.java:81)
        at org.apache.kylin.source.hive.HiveSourceTableLoader.extractHiveTables(HiveSourceTableLoader.java:93)

如果此表已被别的project引入，在另一个project中sync时报错为：

java.lang.RuntimeException: Failed to fetch metadata of 'DEFAULT.CUSTOMER_VISIT': java.lang.ClassNotFoundException Class org.apache.hive.hcatalog.data.JsonSerDe not fou
nd
        at org.apache.kylin.source.hive.SchemaChecker$CheckResult.raiseExceptionWhenInvalid(SchemaChecker.java:62)
        at org.apache.kylin.source.hive.HiveSourceTableLoader.reloadHiveTables(HiveSourceTableLoader.java:67)
        at org.apache.kylin.rest.service.CubeService.reloadHiveTable(CubeService.java:538)
        at org.apache.kylin.rest.service.CubeService$$FastClassBySpringCGLIB$$17a07c0e.invoke(<generated>)
        at org.springframework.cglib.proxy.MethodProxy.invoke(MethodProxy.java:204)
        at org.springframework.aop.framework.CglibAopProxy$CglibMethodInvocation.invokeJoinpoint(CglibAopProxy.java:700)

下面是此表的定义，ClassNotFoundException中的类就是此表用到的JsonSerDe:

CREATE EXTERNAL TABLE `customer_visit`(
  `age_m` int COMMENT 'from deserializer', 
  `discharge_date` date COMMENT 'from deserializer', 
  `address_code` string COMMENT 'from deserializer', 
  `admission_date` date COMMENT 'from deserializer', 
  `birth_date` date COMMENT 'from deserializer', 
  `outcome` string COMMENT 'from deserializer', 
  `age` int COMMENT 'from deserializer')
ROW FORMAT SERDE 
  'org.apache.hive.hcatalog.data.JsonSerDe' 
STORED AS INPUTFORMAT 
  'org.apache.hadoop.mapred.TextInputFormat' 
OUTPUTFORMAT 
  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
LOCATION
  'hdfs://xxx/user/data/abc.db/customer_visit'
TBLPROPERTIES (
  'COLUMN_STATS_ACCURATE'='false', 
  'numFiles'='0', 
  'numRows'='-1', 
  'rawDataSize'='-1', 
  'totalSize'='0', 
  'transient_lastDdlTime'='1493104733')

解决方案：

相关jar需要放到hive metastore服务的$HIVE_HOME/lib/。从第一个报错的Caused by部分可以看到报错是从org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore抛出来的，提示了是metastore的报错。

 

2. 另外kylin服务器上的$HIVE_HOME/lib/也需要放置此jar，否则执行第一步报错，这是hive cli需要用的：

FAILED: RuntimeException MetaException(message:java.lang.ClassNotFoundException Class org.apache.hive.hcatalog.data.JsonSerDe not found)
        at org.apache.kylin.common.util.CliCommandExecutor.execute(CliCommandExecutor.java:92)
        at org.apache.kylin.source.hive.CreateFlatHiveTableStep.createFlatHiveTable(CreateFlatHiveTableStep.java:90)
        at org.apache.kylin.source.hive.CreateFlatHiveTableStep.doWork(CreateFlatHiveTableStep.java:121)
        at org.apache.kylin.job.execution.AbstractExecutable.execute(AbstractExecutable.java:113)
        at org.apache.kylin.job.execution.DefaultChainedExecutable.doWork(DefaultChainedExecutable.java:57)
        at org.apache.kylin.job.execution.AbstractExecutable.execute(AbstractExecutable.java:113)
        at org.apache.kylin.job.impl.threadpool.DefaultScheduler$JobRunner.run(DefaultScheduler.java:136)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
        at java.lang.Thread.run(Thread.java:745)

执行build第一步时报如下错，需要配置hive-env.sh 中的HIVE_AUX_JARS_PATH，把用到的jar包路径配置到其中，这个是给MR用的，HIVE_AUX_JARS_PATH的说明是：Folder containing extra ibraries required for hive compilation/execution

2017-04-27 19:34:33,040 WARN [main] org.apache.hadoop.mapred.YarnChild: Exception running child : java.lang.RuntimeException: Error in configuring object
    at org.apache.hadoop.util.ReflectionUtils.setJobConf(ReflectionUtils.java:112)
    at org.apache.hadoop.util.ReflectionUtils.setConf(ReflectionUtils.java:78)
    at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:136)
    at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:449)
    at org.apache.hadoop.mapred.MapTask.run(MapTask.java:343)
    at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:164)
    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:1657)
    at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:158)
Caused by: java.lang.reflect.InvocationTargetException
    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:497)
    at org.apache.hadoop.util.ReflectionUtils.setJobConf(ReflectionUtils.java:109)
    ... 9 more
Caused by: java.lang.RuntimeException: Error in configuring object
    at org.apache.hadoop.util.ReflectionUtils.setJobConf(ReflectionUtils.java:112)
    at org.apache.hadoop.util.ReflectionUtils.setConf(ReflectionUtils.java:78)
    at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:136)
    at org.apache.hadoop.mapred.MapRunner.configure(MapRunner.java:38)
    ... 14 more
Caused by: java.lang.reflect.InvocationTargetException
    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:497)
    at org.apache.hadoop.util.ReflectionUtils.setJobConf(ReflectionUtils.java:109)
    ... 17 more
Caused by: java.lang.RuntimeException: Map operator initialization failed
    at org.apache.hadoop.hive.ql.exec.mr.ExecMapper.configure(ExecMapper.java:140)
    ... 22 more
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: java.lang.ClassNotFoundException: Class org.apache.hive.hcatalog.data.JsonSerDe not found
    at org.apache.hadoop.hive.ql.exec.MapOperator.getConvertedOI(MapOperator.java:328)
    at org.apache.hadoop.hive.ql.exec.MapOperator.setChildren(MapOperator.java:338)
    at org.apache.hadoop.hive.ql.exec.mr.ExecMapper.configure(ExecMapper.java:109)
    ... 22 more
Caused by: java.lang.ClassNotFoundException: Class org.apache.hive.hcatalog.data.JsonSerDe not found
    at org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:2101)
    at org.apache.hadoop.hive.ql.plan.PartitionDesc.getDeserializer(PartitionDesc.java:141)
    at org.apache.hadoop.hive.ql.exec.MapOperator.getConvertedOI(MapOperator.java:302)
    ... 24 more

一点收获：

1. kylin使用hive 依赖的是本地的hive客户端

2. 鉴于第一条，调试Kylin和hive相关的东西时，只需对本地hive客户端进行修改，不需要hive，这样可以节省不少时间

3. kylin sync table是通过hive metastore服务执行的，所以需要相关表在hive metastore服务上能正常访问，是否能正常访问可以在metastore服务的机器上执行相关hql（主要是元数据相关的hql）验证。