You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Hyukjin Kwon (JIRA)" <ji...@apache.org> on 2019/08/06 06:44:00 UTC
[jira] [Resolved] (SPARK-28632) Cannot read from a partitioned
table by Int
[ https://issues.apache.org/jira/browse/SPARK-28632?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Hyukjin Kwon resolved SPARK-28632.
----------------------------------
Resolution: Incomplete
> Cannot read from a partitioned table by Int
> -------------------------------------------
>
> Key: SPARK-28632
> URL: https://issues.apache.org/jira/browse/SPARK-28632
> Project: Spark
> Issue Type: Bug
> Components: Spark Shell, SQL, YARN
> Affects Versions: 2.1.1
> Environment: Dev env
> Reporter: Juan
> Priority: Major
> Original Estimate: 672h
> Remaining Estimate: 672h
>
> Getting the following error when reading count from the DataFrame:
> {code}
> scala> task189DF.select("ID_NBR").count()
> {code}
> {code}
> 19/08/05 17:16:20 WARN Utils: Truncated the string representation of a plan since it was too large. This behavior can be adjusted by setting 'spark.debug.maxToStringFields' in SparkEnv.conf.
> org.apache.spark.sql.catalyst.errors.package$TreeNodeException: execute, tree:
> Exchange SinglePartition
> +- *HashAggregate(keys=[], functions=[partial_count(1)], output=[count#78L])
> +- HiveTableScan MetastoreRelation schema, table_name, [isnotnull(day_nbr#12), isnotnull(mth_nbr#11), isnotnull(yr_nbr#10), (yr_nbr#10 = 2019), (mth_nbr#11 = 7), (day_nbr#12 = 24)]
> at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
> at org.apache.spark.sql.execution.exchange.ShuffleExchange.doExecute(ShuffleExchange.scala:112)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
> at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:235)
> at org.apache.spark.sql.execution.aggregate.HashAggregateExec.inputRDDs(HashAggregateExec.scala:141)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:368)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
> at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:228)
> at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:275)
> at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2386)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
> at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$withNewExecutionId(Dataset.scala:2788)
> at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2385)
> at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2392)
> at org.apache.spark.sql.Dataset$$anonfun$count$1.apply(Dataset.scala:2420)
> at org.apache.spark.sql.Dataset$$anonfun$count$1.apply(Dataset.scala:2419)
> at org.apache.spark.sql.Dataset.withCallback(Dataset.scala:2801)
> at org.apache.spark.sql.Dataset.count(Dataset.scala:2419)
> ... 48 elided
> Caused by: java.lang.RuntimeException: Caught Hive MetaException attempting to get partition metadata by filter from Hive. You can set the Spark configuration setting spark.sql.hive.manageFilesourcePartitions to false to work around this problem, however this will result in degraded performance. Please report a bug: https://issues.apache.org/jira/browse/SPARK
> at org.apache.spark.sql.hive.client.Shim_v0_13.getPartitionsByFilter(HiveShim.scala:627)
> at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getPartitionsByFilter$1.apply(HiveClientImpl.scala:574)
> at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getPartitionsByFilter$1.apply(HiveClientImpl.scala:572)
> at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$withHiveState$1.apply(HiveClientImpl.scala:279)
> at org.apache.spark.sql.hive.client.HiveClientImpl.liftedTree1$1(HiveClientImpl.scala:226)
> at org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:225)
> at org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:268)
> at org.apache.spark.sql.hive.client.HiveClientImpl.getPartitionsByFilter(HiveClientImpl.scala:572)
> at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$listPartitionsByFilter$1.apply(HiveExternalCatalog.scala:1020)
> at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$listPartitionsByFilter$1.apply(HiveExternalCatalog.scala:1003)
> at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97)
> at org.apache.spark.sql.hive.HiveExternalCatalog.listPartitionsByFilter(HiveExternalCatalog.scala:1003)
> at org.apache.spark.sql.hive.MetastoreRelation.getHiveQlPartitions(MetastoreRelation.scala:160)
> at org.apache.spark.sql.hive.execution.HiveTableScanExec$$anonfun$10.apply(HiveTableScanExec.scala:151)
> at org.apache.spark.sql.hive.execution.HiveTableScanExec$$anonfun$10.apply(HiveTableScanExec.scala:150)
> at org.apache.spark.util.Utils$.withDummyCallSite(Utils.scala:2458)
> at org.apache.spark.sql.hive.execution.HiveTableScanExec.doExecute(HiveTableScanExec.scala:149)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
> at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:235)
> at org.apache.spark.sql.execution.aggregate.HashAggregateExec.inputRDDs(HashAggregateExec.scala:141)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:368)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
> at org.apache.spark.sql.execution.exchange.ShuffleExchange.prepareShuffleDependency(ShuffleExchange.scala:85)
> at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:121)
> at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:112)
> at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
> ... 75 more
> Caused by: java.lang.reflect.InvocationTargetException: org.apache.hadoop.hive.metastore.api.MetaException: Filtering is supported only on partition keys of type string
> 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:614)
> ... 110 more
> Caused by: org.apache.hadoop.hive.metastore.api.MetaException: Filtering is supported only on partition keys of type string
> at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$get_partitions_by_filter_result$get_partitions_by_filter_resultStandardScheme.read(ThriftHiveMetastore.java)
> at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$get_partitions_by_filter_result$get_partitions_by_filter_resultStandardScheme.read(ThriftHiveMetastore.java)
> at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$get_partitions_by_filter_result.read(ThriftHiveMetastore.java)
> at org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:86)
> at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.recv_get_partitions_by_filter(ThriftHiveMetastore.java:2216)
> at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.get_partitions_by_filter(ThriftHiveMetastore.java:2200)
> at org.apache.hadoop.hive.metastore.HiveMetaStoreClient.listPartitionsByFilter(HiveMetaStoreClient.java:1103)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:156)
> at com.sun.proxy.$Proxy21.listPartitionsByFilter(Unknown Source)
> at org.apache.hadoop.hive.ql.metadata.Hive.getPartitionsByFilter(Hive.java:2254)
> ... 115 more
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.14#76016)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org