You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Tongqing Qiu (JIRA)" <ji...@apache.org> on 2019/05/07 16:47:00 UTC
[jira] [Created] (SPARK-27652) Caught Hive MetaException when query
by partition (partition col start with underscore)
Tongqing Qiu created SPARK-27652:
------------------------------------
Summary: Caught Hive MetaException when query by partition (partition col start with underscore)
Key: SPARK-27652
URL: https://issues.apache.org/jira/browse/SPARK-27652
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 2.4.3
Reporter: Tongqing Qiu
create a table, set location as parquet, do msck repair table to get the data.
But when query with partition column, got some errors.
select count(*) from some_table where `_partition_date` = '2015-01-01'
Error
{code:java}
com.databricks.backend.common.rpc.DatabricksExceptions$SQLExecutionException: java.lang.RuntimeException: Caught Hive MetaException attempting to get partition metadata by filter from Hive. You can set the Spark configuration setting spark.sql.hive.manageFilesourcePartitions to false to work around this problem, however this will result in degraded performance. Please report a bug: https://issues.apache.org/jira/browse/SPARK at org.apache.spark.sql.hive.client.Shim_v0_13.getPartitionsByFilter(HiveShim.scala:783) at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getPartitionsByFilter$1.apply(HiveClientImpl.scala:774) at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getPartitionsByFilter$1.apply(HiveClientImpl.scala:772) at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$withHiveState$1.apply(HiveClientImpl.scala:322) at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$retryLocked$1.apply(HiveClientImpl.scala:230) at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$retryLocked$1.apply(HiveClientImpl.scala:222) at org.apache.spark.sql.hive.client.HiveClientImpl.synchronizeOnObject(HiveClientImpl.scala:266) at org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:222) at org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:305) at org.apache.spark.sql.hive.client.HiveClientImpl.getPartitionsByFilter(HiveClientImpl.scala:772) at org.apache.spark.sql.hive.client.PoolingHiveClient$$anonfun$getPartitionsByFilter$1.apply(PoolingHiveClient.scala:373) at org.apache.spark.sql.hive.client.PoolingHiveClient$$anonfun$getPartitionsByFilter$1.apply(PoolingHiveClient.scala:372) at org.apache.spark.sql.hive.client.PoolingHiveClient.withHiveClient(PoolingHiveClient.scala:101) at org.apache.spark.sql.hive.client.PoolingHiveClient.getPartitionsByFilter(PoolingHiveClient.scala:372) at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$listPartitionsByFilter$1.apply(HiveExternalCatalog.scala:1295) at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$listPartitionsByFilter$1.apply(HiveExternalCatalog.scala:1288) at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$withClient$1$$anonfun$apply$1.apply(HiveExternalCatalog.scala:141) at org.apache.spark.sql.hive.HiveExternalCatalog.org$apache$spark$sql$hive$HiveExternalCatalog$$maybeSynchronized(HiveExternalCatalog.scala:104) at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$withClient$1.apply(HiveExternalCatalog.scala:139) at com.databricks.backend.daemon.driver.ProgressReporter$.withStatusCode(ProgressReporter.scala:345) at com.databricks.backend.daemon.driver.ProgressReporter$.withStatusCode(ProgressReporter.scala:331) at com.databricks.spark.util.SparkDatabricksProgressReporter$.withStatusCode(ProgressReporter.scala:23) at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:137) at org.apache.spark.sql.hive.HiveExternalCatalog.listPartitionsByFilter(HiveExternalCatalog.scala:1288) at org.apache.spark.sql.catalyst.catalog.ExternalCatalogWithListener.listPartitionsByFilter(ExternalCatalogWithListener.scala:261) at org.apache.spark.sql.catalyst.catalog.SessionCatalog.listPartitionsByFilter(SessionCatalog.scala:1045) at org.apache.spark.sql.execution.datasources.CatalogFileIndex.filterPartitions(CatalogFileIndex.scala:73) at org.apache.spark.sql.execution.datasources.PruneFileSourcePartitions$$anonfun$apply$1.applyOrElse(PruneFileSourcePartitions.scala:62) at org.apache.spark.sql.execution.datasources.PruneFileSourcePartitions$$anonfun$apply$1.applyOrElse(PruneFileSourcePartitions.scala:27) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:277) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:277) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:77) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:276) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.transformDown(AnalysisHelper.scala:149) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:282) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:282) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$8.apply(TreeNode.scala:351) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:208) at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:349) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:282) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.transformDown(AnalysisHelper.scala:149) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:282) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:282) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$8.apply(TreeNode.scala:351) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:208) at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:349) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:282) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.transformDown(AnalysisHelper.scala:149) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:282) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:282) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$8.apply(TreeNode.scala:351) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:208) at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:349) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:282) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.transformDown(AnalysisHelper.scala:149) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.execution.datasources.PruneFileSourcePartitions$.apply(PruneFileSourcePartitions.scala:27) at org.apache.spark.sql.execution.datasources.PruneFileSourcePartitions$.apply(PruneFileSourcePartitions.scala:26) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:112) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:109) at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:57) at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:66) at scala.collection.mutable.WrappedArray.foldLeft(WrappedArray.scala:35) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:109) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:101) at scala.collection.immutable.List.foreach(List.scala:392) at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:101) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$executeAndTrack$1.apply(RuleExecutor.scala:80) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$executeAndTrack$1.apply(RuleExecutor.scala:80) at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:88) at org.apache.spark.sql.catalyst.rules.RuleExecutor.executeAndTrack(RuleExecutor.scala:79) at org.apache.spark.sql.execution.QueryExecution$$anonfun$optimizedPlan$1.apply(QueryExecution.scala:92) at org.apache.spark.sql.execution.QueryExecution$$anonfun$optimizedPlan$1.apply(QueryExecution.scala:92) at org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111) at org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:91) at org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:91) at org.apache.spark.sql.execution.QueryExecution$$anonfun$sparkPlan$1.apply(QueryExecution.scala:99) at org.apache.spark.sql.execution.QueryExecution$$anonfun$sparkPlan$1.apply(QueryExecution.scala:95) at org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111) at org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:95) at org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:95) at org.apache.spark.sql.execution.QueryExecution$$anonfun$executedPlan$1.apply(QueryExecution.scala:106) at org.apache.spark.sql.execution.QueryExecution$$anonfun$executedPlan$1.apply(QueryExecution.scala:105) at org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111) at org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:105) at org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:105) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$withAction(Dataset.scala:3419) at org.apache.spark.sql.Dataset.collectResult(Dataset.scala:2818) at com.databricks.backend.daemon.driver.OutputAggregator$.withOutputAggregation0(OutputAggregator.scala:136) at com.databricks.backend.daemon.driver.OutputAggregator$.withOutputAggregation(OutputAggregator.scala:52) at com.databricks.backend.daemon.driver.SQLDriverLocal.executeSql(SQLDriverLocal.scala:105) at com.databricks.backend.daemon.driver.SQLDriverLocal.repl(SQLDriverLocal.scala:136) at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$8.apply(DriverLocal.scala:323) at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$8.apply(DriverLocal.scala:303) at com.databricks.logging.UsageLogging$$anonfun$withAttributionContext$1.apply(UsageLogging.scala:235) at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58) at com.databricks.logging.UsageLogging$class.withAttributionContext(UsageLogging.scala:230) at com.databricks.backend.daemon.driver.DriverLocal.withAttributionContext(DriverLocal.scala:47) at com.databricks.logging.UsageLogging$class.withAttributionTags(UsageLogging.scala:268) at com.databricks.backend.daemon.driver.DriverLocal.withAttributionTags(DriverLocal.scala:47) at com.databricks.backend.daemon.driver.DriverLocal.execute(DriverLocal.scala:303) at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:591) at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:591) at scala.util.Try$.apply(Try.scala:192) at com.databricks.backend.daemon.driver.DriverWrapper.tryExecutingCommand(DriverWrapper.scala:586) at com.databricks.backend.daemon.driver.DriverWrapper.getCommandOutputAndError(DriverWrapper.scala:477) at com.databricks.backend.daemon.driver.DriverWrapper.executeCommand(DriverWrapper.scala:544) at com.databricks.backend.daemon.driver.DriverWrapper.runInnerLoop(DriverWrapper.scala:383) at com.databricks.backend.daemon.driver.DriverWrapper.runInner(DriverWrapper.scala:330) at com.databricks.backend.daemon.driver.DriverWrapper.run(DriverWrapper.scala:216) at java.lang.Thread.run(Thread.java:748) 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:498) at org.apache.spark.sql.hive.client.Shim_v0_13.getPartitionsByFilter(HiveShim.scala:770) ... 120 more Caused by: MetaException(message:Error parsing partition filter : line 1:0 no viable alternative at character '_') at org.apache.hadoop.hive.metastore.ObjectStore.getFilterParser(ObjectStore.java:2371) at org.apache.hadoop.hive.metastore.ObjectStore.getPartitionsByFilterInternal(ObjectStore.java:2314) at org.apache.hadoop.hive.metastore.ObjectStore.getPartitionsByFilter(ObjectStore.java:2165) 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.hadoop.hive.metastore.RawStoreProxy.invoke(RawStoreProxy.java:108) at com.sun.proxy.$Proxy39.getPartitionsByFilter(Unknown Source) at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.get_partitions_by_filter(HiveMetaStore.java:3760) 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.hadoop.hive.metastore.RetryingHMSHandler.invoke(RetryingHMSHandler.java:105) at com.sun.proxy.$Proxy40.get_partitions_by_filter(Unknown Source) at org.apache.hadoop.hive.metastore.HiveMetaStoreClient.listPartitionsByFilter(HiveMetaStoreClient.java:903) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:89) at com.sun.proxy.$Proxy41.listPartitionsByFilter(Unknown Source) at org.apache.hadoop.hive.ql.metadata.Hive.getPartitionsByFilter(Hive.java:1944) ... 125 more at com.databricks.backend.daemon.driver.SQLDriverLocal.executeSql(SQLDriverLocal.scala:122) at com.databricks.backend.daemon.driver.SQLDriverLocal.repl(SQLDriverLocal.scala:136) at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$8.apply(DriverLocal.scala:323) at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$8.apply(DriverLocal.scala:303) at com.databricks.logging.UsageLogging$$anonfun$withAttributionContext$1.apply(UsageLogging.scala:235) at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58) at com.databricks.logging.UsageLogging$class.withAttributionContext(UsageLogging.scala:230) at com.databricks.backend.daemon.driver.DriverLocal.withAttributionContext(DriverLocal.scala:47) at com.databricks.logging.UsageLogging$class.withAttributionTags(UsageLogging.scala:268) at com.databricks.backend.daemon.driver.DriverLocal.withAttributionTags(DriverLocal.scala:47) at com.databricks.backend.daemon.driver.DriverLocal.execute(DriverLocal.scala:303) at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:591) at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:591) at scala.util.Try$.apply(Try.scala:192) at com.databricks.backend.daemon.driver.DriverWrapper.tryExecutingCommand(DriverWrapper.scala:586) at com.databricks.backend.daemon.driver.DriverWrapper.getCommandOutputAndError(DriverWrapper.scala:477) at com.databricks.backend.daemon.driver.DriverWrapper.executeCommand(DriverWrapper.scala:544) at com.databricks.backend.daemon.driver.DriverWrapper.runInnerLoop(DriverWrapper.scala:383) at com.databricks.backend.daemon.driver.DriverWrapper.runInner(DriverWrapper.scala:330) at com.databricks.backend.daemon.driver.DriverWrapper.run(DriverWrapper.scala:216) at java.lang.Thread.run(Thread.java:748){code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org