[
https://issues.apache.org/jira/browse/SPARK-12378?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15387889#comment-15387889
]
Chandana Sapparapu edited comment on SPARK-12378 at 7/24/16 3:46 PM:
---------------------------------------------------------------------
UPDATE - For temporary table, I don't have this issue.
For external table - the following syntax seems to work.
FROM (select a.* ,b.* from TBL_A a , TBL_B b where a.id=b.id) INPUT
insert overwrite TABLE MY_EXTERNAL_TABLE PARTITION (PARTITION_DT='2016-07-24' ,
SUB_PARTITION_DT='2016-07-24')
select *
where flg_1='N';
--------------------------------------------------------------------------
Environment:
Spark 1.6.2
AWS EMR 4.7.2
Hive execution 1.2.1
Metastore: 1.0.0
Query :
insert into table (managed)
select a.*, b.* from external_table1 a
LEFT OUTER JOIN external_table2 b
on a.id=b.id;
The statement succeeds and some data is written into this managed table, but it
throws the following exception which stops the subsequent statements from
getting executed.
java.lang.reflect.InvocationTargetException
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.sql.hive.client.Shim_v0_14.loadTable(HiveShim.scala:442)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply$mcV$sp(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$withHiveState$1.apply(ClientWrapper.scala:290)
at
org.apache.spark.sql.hive.client.ClientWrapper.liftedTree1$1(ClientWrapper.scala:237)
at
org.apache.spark.sql.hive.client.ClientWrapper.retryLocked(ClientWrapper.scala:236)
at
org.apache.spark.sql.hive.client.ClientWrapper.withHiveState(ClientWrapper.scala:279)
at
org.apache.spark.sql.hive.client.ClientWrapper.loadTable(ClientWrapper.scala:556)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult$lzycompute(InsertIntoHiveTable.scala:256)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult(InsertIntoHiveTable.scala:127)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.doExecute(InsertIntoHiveTable.scala:276)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:52)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:817)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:63)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:311)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:226)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Unable to alter
table. Invalid method name: 'alter_table_with_cascade'
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:500)
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:484)
at org.apache.hadoop.hive.ql.metadata.Hive.loadTable(Hive.java:1668)
... 40 more
Caused by: org.apache.thrift.TApplicationException: Invalid method name:
'alter_table_with_cascade'
at
org.apache.thrift.TApplicationException.read(TApplicationException.java:111)
at org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:71)
at
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.recv_alter_table_with_cascade(ThriftHiveMetastore.java:1374)
at
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.alter_table_with_cascade(ThriftHiveMetastore.java:1358)
at
org.apache.hadoop.hive.metastore.HiveMetaStoreClient.alter_table(HiveMetaStoreClient.java:340)
at
org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.alter_table(SessionHiveMetaStoreClient.java:251)
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.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:156)
at com.sun.proxy.$Proxy28.alter_table(Unknown Source)
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:496)
... 42 more
java.lang.reflect.InvocationTargetException
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.sql.hive.client.Shim_v0_14.loadTable(HiveShim.scala:442)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply$mcV$sp(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$withHiveState$1.apply(ClientWrapper.scala:290)
at
org.apache.spark.sql.hive.client.ClientWrapper.liftedTree1$1(ClientWrapper.scala:237)
at
org.apache.spark.sql.hive.client.ClientWrapper.retryLocked(ClientWrapper.scala:236)
at
org.apache.spark.sql.hive.client.ClientWrapper.withHiveState(ClientWrapper.scala:279)
at
org.apache.spark.sql.hive.client.ClientWrapper.loadTable(ClientWrapper.scala:556)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult$lzycompute(InsertIntoHiveTable.scala:256)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult(InsertIntoHiveTable.scala:127)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.doExecute(InsertIntoHiveTable.scala:276)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:52)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:817)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:63)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:311)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:226)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Unable to alter
table. Invalid method name: 'alter_table_with_cascade'
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:500)
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:484)
at org.apache.hadoop.hive.ql.metadata.Hive.loadTable(Hive.java:1668)
... 40 more
Caused by: org.apache.thrift.TApplicationException: Invalid method name:
'alter_table_with_cascade'
at
org.apache.thrift.TApplicationException.read(TApplicationException.java:111)
at org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:71)
at
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.recv_alter_table_with_cascade(ThriftHiveMetastore.java:1374)
at
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.alter_table_with_cascade(ThriftHiveMetastore.java:1358)
at
org.apache.hadoop.hive.metastore.HiveMetaStoreClient.alter_table(HiveMetaStoreClient.java:340)
at
org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.alter_table(SessionHiveMetaStoreClient.java:251)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:156)
at com.sun.proxy.$Proxy28.alter_table(Unknown Source)
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:496)
... 42 more
Spark 1.6.2
AWS EMR 4.7.2
Hive execution 1.2.1
Metastore: 1.0.0
I had a problem with hive 1.2.1 and default spark-sql on EMR 4.7.2
Since this could be a metastore, execution engine mismatch, I tried the
following version changes - but it didn't work.
Changes in spark - /usr/lib/spark/conf/spark-defaults.conf
spark.sql.hive.metastore.version 1.0.0
spark.sql.hive.metastore.jars maven
Got this exception -
Builtin jars can only be used when hive execution version == hive metastore
version. Execution: 1.2.1 != Metastore: 1.0.0. Specify a vaild path to the
correct hive jars using $HIVE_METASTORE_JARS or change
spark.sql.hive.metastore.version to 1.2.1.
was (Author: fullstack):
Environment:
Spark 1.6.2
AWS EMR 4.7.2
Hive execution 1.2.1
Metastore: 1.0.0
Query :
insert into table (managed)
select a.*, b.* from external_table1 a
LEFT OUTER JOIN external_table2 b
on a.id=b.id;
The statement succeeds and some data is written into this managed table, but it
throws the following exception which stops the subsequent statements from
getting executed.
java.lang.reflect.InvocationTargetException
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.sql.hive.client.Shim_v0_14.loadTable(HiveShim.scala:442)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply$mcV$sp(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$withHiveState$1.apply(ClientWrapper.scala:290)
at
org.apache.spark.sql.hive.client.ClientWrapper.liftedTree1$1(ClientWrapper.scala:237)
at
org.apache.spark.sql.hive.client.ClientWrapper.retryLocked(ClientWrapper.scala:236)
at
org.apache.spark.sql.hive.client.ClientWrapper.withHiveState(ClientWrapper.scala:279)
at
org.apache.spark.sql.hive.client.ClientWrapper.loadTable(ClientWrapper.scala:556)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult$lzycompute(InsertIntoHiveTable.scala:256)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult(InsertIntoHiveTable.scala:127)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.doExecute(InsertIntoHiveTable.scala:276)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:52)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:817)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:63)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:311)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:226)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Unable to alter
table. Invalid method name: 'alter_table_with_cascade'
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:500)
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:484)
at org.apache.hadoop.hive.ql.metadata.Hive.loadTable(Hive.java:1668)
... 40 more
Caused by: org.apache.thrift.TApplicationException: Invalid method name:
'alter_table_with_cascade'
at
org.apache.thrift.TApplicationException.read(TApplicationException.java:111)
at org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:71)
at
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.recv_alter_table_with_cascade(ThriftHiveMetastore.java:1374)
at
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.alter_table_with_cascade(ThriftHiveMetastore.java:1358)
at
org.apache.hadoop.hive.metastore.HiveMetaStoreClient.alter_table(HiveMetaStoreClient.java:340)
at
org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.alter_table(SessionHiveMetaStoreClient.java:251)
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.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:156)
at com.sun.proxy.$Proxy28.alter_table(Unknown Source)
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:496)
... 42 more
java.lang.reflect.InvocationTargetException
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.sql.hive.client.Shim_v0_14.loadTable(HiveShim.scala:442)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply$mcV$sp(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:557)
at
org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$withHiveState$1.apply(ClientWrapper.scala:290)
at
org.apache.spark.sql.hive.client.ClientWrapper.liftedTree1$1(ClientWrapper.scala:237)
at
org.apache.spark.sql.hive.client.ClientWrapper.retryLocked(ClientWrapper.scala:236)
at
org.apache.spark.sql.hive.client.ClientWrapper.withHiveState(ClientWrapper.scala:279)
at
org.apache.spark.sql.hive.client.ClientWrapper.loadTable(ClientWrapper.scala:556)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult$lzycompute(InsertIntoHiveTable.scala:256)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult(InsertIntoHiveTable.scala:127)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.doExecute(InsertIntoHiveTable.scala:276)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:52)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:817)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:63)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:311)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:226)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Unable to alter
table. Invalid method name: 'alter_table_with_cascade'
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:500)
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:484)
at org.apache.hadoop.hive.ql.metadata.Hive.loadTable(Hive.java:1668)
... 40 more
Caused by: org.apache.thrift.TApplicationException: Invalid method name:
'alter_table_with_cascade'
at
org.apache.thrift.TApplicationException.read(TApplicationException.java:111)
at org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:71)
at
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.recv_alter_table_with_cascade(ThriftHiveMetastore.java:1374)
at
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.alter_table_with_cascade(ThriftHiveMetastore.java:1358)
at
org.apache.hadoop.hive.metastore.HiveMetaStoreClient.alter_table(HiveMetaStoreClient.java:340)
at
org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.alter_table(SessionHiveMetaStoreClient.java:251)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:156)
at com.sun.proxy.$Proxy28.alter_table(Unknown Source)
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:496)
... 42 more
Spark 1.6.2
AWS EMR 4.7.2
Hive execution 1.2.1
Metastore: 1.0.0
I had a problem with hive 1.2.1 and default spark-sql on EMR 4.7.2
Since this could be a metastore, execution engine mismatch, I tried the
following version changes - but it didn't work.
Changes in spark - /usr/lib/spark/conf/spark-defaults.conf
spark.sql.hive.metastore.version 1.0.0
spark.sql.hive.metastore.jars maven
Got this exception -
Builtin jars can only be used when hive execution version == hive metastore
version. Execution: 1.2.1 != Metastore: 1.0.0. Specify a vaild path to the
correct hive jars using $HIVE_METASTORE_JARS or change
spark.sql.hive.metastore.version to 1.2.1.
> CREATE EXTERNAL TABLE AS SELECT EXPORT AWS S3 ERROR
> ---------------------------------------------------
>
> Key: SPARK-12378
> URL: https://issues.apache.org/jira/browse/SPARK-12378
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.5.2
> Environment: AWS EMR 4.2.0
> Just Master Running m3.xlarge
> Applications:
> Hive 1.0.0
> Spark 1.5.2
> Reporter: CESAR MICHELETTI
>
> I am receive the bellow error during try exporting data to AWS S3, in
> spark-sql.
> Command:
> CREATE external TABLE export
> ROW FORMAT DELIMITED FIELDS TERMINATED BY '\054'
> -- lines terminated by '\n'
> STORED AS TEXTFILE
> LOCATION 's3://xxx/yyy'
> AS
> SELECT
> xxx
> ....
> (complete query)
> ;
> Error:
> -chgrp: '' does not match expected pattern for group
> Usage: hadoop fs [generic options] -chgrp [-R] GROUP PATH...
> -chgrp: '' does not match expected pattern for group
> Usage: hadoop fs [generic options] -chgrp [-R] GROUP PATH...
> 15/12/16 21:09:25 ERROR SparkSQLDriver: Failed in [CREATE external TABLE
> csvexport
> ...
> (create table + query)
> ...
> java.lang.reflect.InvocationTargetException
> 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.sql.hive.client.Shim_v0_14.loadTable(HiveShim.scala:441)
> at
> org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply$mcV$sp(ClientWrapper.scala:489)
> at
> org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:489)
> at
> org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:489)
> at
> org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$withHiveState$1.apply(ClientWrapper.scala:256)
> at
> org.apache.spark.sql.hive.client.ClientWrapper.retryLocked(ClientWrapper.scala:211)
> at
> org.apache.spark.sql.hive.client.ClientWrapper.withHiveState(ClientWrapper.scala:248)
> at
> org.apache.spark.sql.hive.client.ClientWrapper.loadTable(ClientWrapper.scala:488)
> at
> org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult$lzycompute(InsertIntoHiveTable.scala:243)
> at
> org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult(InsertIntoHiveTable.scala:127)
> at
> org.apache.spark.sql.hive.execution.InsertIntoHiveTable.doExecute(InsertIntoHiveTable.scala:263)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
> at
> org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:933)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:933)
> at
> org.apache.spark.sql.hive.execution.CreateTableAsSelect.run(CreateTableAsSelect.scala:89)
> at
> org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$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:69)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
> at
> org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:933)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:933)
> at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:144)
> at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:129)
> at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
> at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:725)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:308)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:226)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> org.apache.spark.deploy.SparkSubmit$.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: org.apache.hadoop.hive.ql.metadata.HiveException: Unable to alter
> table. Invalid method name: 'alter_table_with_cascade'
> at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:500)
> at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:484)
> at org.apache.hadoop.hive.ql.metadata.Hive.loadTable(Hive.java:1668)
> ... 49 more
> Caused by: org.apache.thrift.TApplicationException: Invalid method name:
> 'alter_table_with_cascade'
> at
> org.apache.thrift.TApplicationException.read(TApplicationException.java:111)
> at
> org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:71)
> at
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.recv_alter_table_with_cascade(ThriftHiveMetastore.java:1374)
> at
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.alter_table_with_cascade(ThriftHiveMetastore.java:1358)
> at
> org.apache.hadoop.hive.metastore.HiveMetaStoreClient.alter_table(HiveMetaStoreClient.java:340)
> at
> org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.alter_table(SessionHiveMetaStoreClient.java:251)
> 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.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:156)
> at com.sun.proxy.$Proxy29.alter_table(Unknown Source)
> at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:496)
> ... 51 more
> java.lang.reflect.InvocationTargetException
> 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.sql.hive.client.Shim_v0_14.loadTable(HiveShim.scala:441)
> at
> org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply$mcV$sp(ClientWrapper.scala:489)
> at
> org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:489)
> at
> org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$loadTable$1.apply(ClientWrapper.scala:489)
> at
> org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$withHiveState$1.apply(ClientWrapper.scala:256)
> at
> org.apache.spark.sql.hive.client.ClientWrapper.retryLocked(ClientWrapper.scala:211)
> at
> org.apache.spark.sql.hive.client.ClientWrapper.withHiveState(ClientWrapper.scala:248)
> at
> org.apache.spark.sql.hive.client.ClientWrapper.loadTable(ClientWrapper.scala:488)
> at
> org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult$lzycompute(InsertIntoHiveTable.scala:243)
> at
> org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult(InsertIntoHiveTable.scala:127)
> at
> org.apache.spark.sql.hive.execution.InsertIntoHiveTable.doExecute(InsertIntoHiveTable.scala:263)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
> at
> org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:933)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:933)
> at
> org.apache.spark.sql.hive.execution.CreateTableAsSelect.run(CreateTableAsSelect.scala:89)
> at
> org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
> at
> org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
> at
> org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:69)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
> at
> org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:933)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:933)
> at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:144)
> at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:129)
> at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
> at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:725)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:308)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:226)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$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$.main(SparkSubmit.scala:120)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Unable to alter
> table. Invalid method name: 'alter_table_with_cascade'
> at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:500)
> at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:484)
> at org.apache.hadoop.hive.ql.metadata.Hive.loadTable(Hive.java:1668)
> ... 49 more
> Caused by: org.apache.thrift.TApplicationException: Invalid method name:
> 'alter_table_with_cascade'
> at
> org.apache.thrift.TApplicationException.read(TApplicationException.java:111)
> at
> org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:71)
> at
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.recv_alter_table_with_cascade(ThriftHiveMetastore.java:1374)
> at
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.alter_table_with_cascade(ThriftHiveMetastore.java:1358)
> at
> org.apache.hadoop.hive.metastore.HiveMetaStoreClient.alter_table(HiveMetaStoreClient.java:340)
> at
> org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.alter_table(SessionHiveMetaStoreClient.java:251)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:156)
> at com.sun.proxy.$Proxy29.alter_table(Unknown Source)
> at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:496)
> ... 51 more
> Detail:
> The file exported is generated in S3 bucket, but the process terminate with
> error...
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
