[
https://issues.apache.org/jira/browse/SPARK-38884?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17522885#comment-17522885
]
Bruce Robbins commented on SPARK-38884:
---------------------------------------
{quote}what`s self-contained reproducer？{quote}
[~chopperChen] A self-contained reproducer would be like the reproduction steps
provided in the descriptions of SPARK-38717, SPARK-38655, SPARK-38614. The
steps include everything needed to reproduce, _including sample data_, and
usually (but not always) given as a set of commands a Spark dev can just
cut-and-paste into {{spark-shell}}, {{pyspark}}, or {{spark-sql}}.
> java.util.NoSuchElementException: key not found: numPartitions
> --------------------------------------------------------------
>
> Key: SPARK-38884
> URL: https://issues.apache.org/jira/browse/SPARK-38884
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 3.0.1
> Environment: hadoop 3.1.1
> spark 3.0.1
> Reporter: chopperChen
> Priority: Major
>
> When running function spark.sql("sql").isEmpty, the logs print
> {*}_java.util.NoSuchElementException: key not found: numPartitions_{*}.
> My sql like:
>
> {code:java}
> // hr is a partition column
> select * from (select col1, '24' as hr from table1
> union all select col1, '2' as hr from table2
> union all select col1, hr from table3) df1
> inner join (select col1, '24' as hr from table4
> union all select col1, '2' as hr from table5
> union all select col1, hr from table6) df2
> on df1.col1=df2.col1
> {code}
>
> *exception:*
> Caused by: java.util.NoSuchElementException: key not found: numPartitions
> at scala.collection.MapLike.default(MapLike.scala:235)
> at scala.collection.MapLike.default$(MapLike.scala:234)
> at scala.collection.AbstractMap.default(Map.scala:63)
> at scala.collection.MapLike.apply(MapLike.scala:144)
> at scala.collection.MapLike.apply$(MapLike.scala:143)
> at scala.collection.AbstractMap.apply(Map.scala:63)
> at
> org.apache.spark.sql.execution.FileSourceScanExec.$anonfun$sendDriverMetrics$1(DataSourceScanExec.scala:197)
> at
> org.apache.spark.sql.execution.FileSourceScanExec.$anonfun$sendDriverMetrics$1$adapted(DataSourceScanExec.scala:197)
> at scala.collection.mutable.HashMap.$anonfun$foreach$1(HashMap.scala:149)
> at scala.collection.mutable.HashTable.foreachEntry(HashTable.scala:237)
> at scala.collection.mutable.HashTable.foreachEntry$(HashTable.scala:230)
> at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:44)
> at scala.collection.mutable.HashMap.foreach(HashMap.scala:149)
> at
> org.apache.spark.sql.execution.FileSourceScanExec.sendDriverMetrics(DataSourceScanExec.scala:197)
> at
> org.apache.spark.sql.execution.FileSourceScanExec.inputRDD$lzycompute(DataSourceScanExec.scala:407)
> at
> org.apache.spark.sql.execution.FileSourceScanExec.inputRDD(DataSourceScanExec.scala:390)
> at
> org.apache.spark.sql.execution.FileSourceScanExec.doExecuteColumnar(DataSourceScanExec.scala:485)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeColumnar$1(SparkPlan.scala:202)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:213)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:210)
> at
> org.apache.spark.sql.execution.SparkPlan.executeColumnar(SparkPlan.scala:198)
> at
> org.apache.spark.sql.execution.InputAdapter.doExecuteColumnar(WholeStageCodegenExec.scala:519)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeColumnar$1(SparkPlan.scala:202)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:213)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:210)
> at
> org.apache.spark.sql.execution.SparkPlan.executeColumnar(SparkPlan.scala:198)
> at
> org.apache.spark.sql.execution.ColumnarToRowExec.inputRDDs(Columnar.scala:196)
> at
> org.apache.spark.sql.execution.FilterExec.inputRDDs(basicPhysicalOperators.scala:133)
> at
> org.apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:47)
> at
> org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:720)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:175)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:213)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:210)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:171)
> at
> org.apache.spark.sql.execution.UnionExec.$anonfun$doExecute$5(basicPhysicalOperators.scala:644)
> at
> scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
> at
> scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
> at
> scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
> at scala.collection.TraversableLike.map(TraversableLike.scala:238)
> at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
> at scala.collection.AbstractTraversable.map(Traversable.scala:108)
> at
> org.apache.spark.sql.execution.UnionExec.doExecute(basicPhysicalOperators.scala:644)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:175)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:213)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:210)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:171)
> at
> org.apache.spark.sql.execution.InputAdapter.inputRDD(WholeStageCodegenExec.scala:525)
> at
> org.apache.spark.sql.execution.InputRDDCodegen.inputRDDs(WholeStageCodegenExec.scala:453)
> at
> org.apache.spark.sql.execution.InputRDDCodegen.inputRDDs$(WholeStageCodegenExec.scala:452)
> at
> org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:496)
> at
> org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.inputRDDs(BroadcastHashJoinExec.scala:74)
> at
> org.apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:47)
> at
> org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.inputRDDs(BroadcastHashJoinExec.scala:74)
> at
> org.apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:47)
> at
> org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.inputRDDs(BroadcastHashJoinExec.scala:74)
> at
> org.apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:47)
> at
> org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.inputRDDs(BroadcastHashJoinExec.scala:74)
> at
> org.apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:47)
> at
> org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:720)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:175)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:213)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:210)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:171)
> at
> org.apache.spark.sql.execution.exchange.ShuffleExchangeExec.inputRDD$lzycompute(ShuffleExchangeExec.scala:106)
> at
> org.apache.spark.sql.execution.exchange.ShuffleExchangeExec.inputRDD(ShuffleExchangeExec.scala:106)
> at
> org.apache.spark.sql.execution.exchange.ShuffleExchangeExec.shuffleDependency$lzycompute(ShuffleExchangeExec.scala:139)
> at
> org.apache.spark.sql.execution.exchange.ShuffleExchangeExec.shuffleDependency(ShuffleExchangeExec.scala:137)
> at
> org.apache.spark.sql.execution.exchange.ShuffleExchangeExec.$anonfun$doExecute$1(ShuffleExchangeExec.scala:154)
> at
> org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
