[
https://issues.apache.org/jira/browse/SPARK-29409?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16948145#comment-16948145
]
angerszhu commented on SPARK-29409:
-----------------------------------
Hive build in version and run version.
> spark drop partition always throws Exception
> --------------------------------------------
>
> Key: SPARK-29409
> URL: https://issues.apache.org/jira/browse/SPARK-29409
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.4.0
> Reporter: ant_nebula
> Priority: Major
>
> The table is:
> {code:java}
> CREATE TABLE `test_spark.test_drop_partition`(
> `platform` string,
> `product` string,
> `cnt` bigint)
> PARTITIONED BY (dt string)
> stored as orc;{code}
> hive 2.1.1:
> {code:java}
> spark-sql -e "alter table test_spark.test_drop_partition drop if exists
> partition(dt='2019-10-08')"{code}
> hive builtin:
> {code:java}
> spark-sql --conf spark.sql.hive.metastore.version=1.2.1 --conf
> spark.sql.hive.metastore.jars=builtin -e "alter table
> test_spark.test_drop_partition drop if exists
> partition(dt='2019-10-08')"{code}
> both would log Exception:
> {code:java}
> 19/10/09 18:21:27 INFO metastore: Opened a connection to metastore, current
> connections: 1
> 19/10/09 18:21:27 INFO metastore: Connected to metastore.
> 19/10/09 18:21:27 WARN RetryingMetaStoreClient: MetaStoreClient lost
> connection. Attempting to reconnect.
> org.apache.thrift.transport.TTransportException: Cannot write to null
> outputStream
> at
> org.apache.thrift.transport.TIOStreamTransport.write(TIOStreamTransport.java:142)
> at
> org.apache.thrift.protocol.TBinaryProtocol.writeI32(TBinaryProtocol.java:178)
> at
> org.apache.thrift.protocol.TBinaryProtocol.writeMessageBegin(TBinaryProtocol.java:106)
> at org.apache.thrift.TServiceClient.sendBase(TServiceClient.java:70)
> at org.apache.thrift.TServiceClient.sendBase(TServiceClient.java:62)
> at
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.send_get_partitions_ps_with_auth(ThriftHiveMetastore.java:2433)
> at
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.get_partitions_ps_with_auth(ThriftHiveMetastore.java:2420)
> at
> org.apache.hadoop.hive.metastore.HiveMetaStoreClient.listPartitionsWithAuthInfo(HiveMetaStoreClient.java:1199)
> 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:154)
> at com.sun.proxy.$Proxy30.listPartitionsWithAuthInfo(Unknown Source)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at
> org.apache.hadoop.hive.metastore.HiveMetaStoreClient$SynchronizedHandler.invoke(HiveMetaStoreClient.java:2265)
> at com.sun.proxy.$Proxy30.listPartitionsWithAuthInfo(Unknown Source)
> at org.apache.hadoop.hive.ql.metadata.Hive.getPartitions(Hive.java:2333)
> at org.apache.hadoop.hive.ql.metadata.Hive.getPartitions(Hive.java:2359)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$dropPartitions$1$$anonfun$16.apply(HiveClientImpl.scala:560)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$dropPartitions$1$$anonfun$16.apply(HiveClientImpl.scala:555)
> at
> scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241)
> at
> scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
> at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:241)
> at scala.collection.AbstractTraversable.flatMap(Traversable.scala:104)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$dropPartitions$1.apply$mcV$sp(HiveClientImpl.scala:555)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$dropPartitions$1.apply(HiveClientImpl.scala:550)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$dropPartitions$1.apply(HiveClientImpl.scala:550)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$withHiveState$1.apply(HiveClientImpl.scala:275)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl.liftedTree1$1(HiveClientImpl.scala:213)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:212)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:258)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl.dropPartitions(HiveClientImpl.scala:550)
> at
> org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$dropPartitions$1.apply$mcV$sp(HiveExternalCatalog.scala:972)
> at
> org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$dropPartitions$1.apply(HiveExternalCatalog.scala:970)
> at
> org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$dropPartitions$1.apply(HiveExternalCatalog.scala:970)
> at
> org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97)
> at
> org.apache.spark.sql.hive.HiveExternalCatalog.dropPartitions(HiveExternalCatalog.scala:970)
> at
> org.apache.spark.sql.catalyst.catalog.ExternalCatalogWithListener.dropPartitions(ExternalCatalogWithListener.scala:203)
> at
> org.apache.spark.sql.catalyst.catalog.SessionCatalog.dropPartitions(SessionCatalog.scala:846)
> at
> org.apache.spark.sql.execution.command.AlterTableDropPartitionCommand.run(ddl.scala:546)
> at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
> at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
> at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
> at org.apache.spark.sql.Dataset$$anonfun$6.apply(Dataset.scala:195)
> at org.apache.spark.sql.Dataset$$anonfun$6.apply(Dataset.scala:195)
> at org.apache.spark.sql.Dataset$$anonfun$53.apply(Dataset.scala:3365)
> at
> org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
> at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
> at
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
> at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3364)
> at org.apache.spark.sql.Dataset.<init>(Dataset.scala:195)
> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:80)
> at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
> at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:694)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:371)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:274)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at
> org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
> at
> org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:849)
> at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:167)
> at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:195)
> at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86)
> at
> org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:924)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:933)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> 19/10/09 18:21:28 INFO metastore: Trying to connect to metastore with URI
> thrift://dc.local.metastore.hy:9083
> 19/10/09 18:21:28 INFO metastore: Opened a connection to metastore, current
> connections: 2
> 19/10/09 18:21:28 INFO metastore: Connected to metastore.
> Time taken: 3.715 seconds{code}
> But this sql is normal
> {code:java}
> spark-sql -e "select * from test_spark.test_drop_partition where
> dt='2019-10-08' limit 3; alter table test_spark.test_drop_partition drop if
> exists partition(dt='2019-10-08');"{code}
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
