You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Herman van Hovell (JIRA)" <ji...@apache.org> on 2016/11/28 12:21:58 UTC
[jira] [Updated] (SPARK-18609) [SQL] column mixup with CROSS JOIN
[ https://issues.apache.org/jira/browse/SPARK-18609?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Herman van Hovell updated SPARK-18609:
--------------------------------------
Labels: (was: sql)
> [SQL] column mixup with CROSS JOIN
> ----------------------------------
>
> Key: SPARK-18609
> URL: https://issues.apache.org/jira/browse/SPARK-18609
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.0.2, 2.1.0
> Reporter: Furcy Pin
>
> Reproduced on spark-sql v2.0.2 and on branch master.
> {code}
> DROP TABLE IF EXISTS p1 ;
> DROP TABLE IF EXISTS p2 ;
> CREATE TABLE p1 (col TIMESTAMP) ;
> CREATE TABLE p2 (col TIMESTAMP) ;
> set spark.sql.crossJoin.enabled = true;
> -- EXPLAIN
> WITH CTE AS (
> SELECT
> s2.col as col
> FROM p1
> CROSS JOIN (
> SELECT
> e.col as col
> FROM p2 E
> ) s2
> )
> SELECT
> T1.col as c1,
> T2.col as c2
> FROM CTE T1
> CROSS JOIN CTE T2
> ;
> {code}
> This returns the following stacktrace :
> {code}
> org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding attribute, tree: col#21
> at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:88)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:87)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:279)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:279)
> at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:278)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:284)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:268)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
> at org.apache.spark.sql.execution.ProjectExec$$anonfun$4.apply(basicPhysicalOperators.scala:55)
> at org.apache.spark.sql.execution.ProjectExec$$anonfun$4.apply(basicPhysicalOperators.scala:54)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.immutable.List.map(List.scala:285)
> at org.apache.spark.sql.execution.ProjectExec.doConsume(basicPhysicalOperators.scala:54)
> at org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:153)
> at org.apache.spark.sql.execution.InputAdapter.consume(WholeStageCodegenExec.scala:218)
> at org.apache.spark.sql.execution.InputAdapter.doProduce(WholeStageCodegenExec.scala:244)
> at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83)
> at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
> at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78)
> at org.apache.spark.sql.execution.InputAdapter.produce(WholeStageCodegenExec.scala:218)
> at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:40)
> at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83)
> at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
> at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78)
> at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:30)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:309)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:347)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
> at org.apache.spark.sql.execution.joins.CartesianProductExec.doExecute(CartesianProductExec.scala:107)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
> at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:233)
> at org.apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:36)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:361)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
> at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:240)
> at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:287)
> at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:310)
> at org.apache.spark.sql.execution.QueryExecution$$anonfun$hiveResultString$3.apply(QueryExecution.scala:129)
> at org.apache.spark.sql.execution.QueryExecution$$anonfun$hiveResultString$3.apply(QueryExecution.scala:128)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
> at org.apache.spark.sql.execution.QueryExecution.hiveResultString(QueryExecution.scala:128)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:63)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:331)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:247)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:736)
> at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
> at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: java.lang.RuntimeException: Couldn't find col#21 in []
> at scala.sys.package$.error(package.scala:27)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:94)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:88)
> at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
> ... 85 more
> org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding attribute, tree: col#21
> at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:88)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:87)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:279)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:279)
> at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:278)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:284)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:268)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
> at org.apache.spark.sql.execution.ProjectExec$$anonfun$4.apply(basicPhysicalOperators.scala:55)
> at org.apache.spark.sql.execution.ProjectExec$$anonfun$4.apply(basicPhysicalOperators.scala:54)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.immutable.List.map(List.scala:285)
> at org.apache.spark.sql.execution.ProjectExec.doConsume(basicPhysicalOperators.scala:54)
> at org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:153)
> at org.apache.spark.sql.execution.InputAdapter.consume(WholeStageCodegenExec.scala:218)
> at org.apache.spark.sql.execution.InputAdapter.doProduce(WholeStageCodegenExec.scala:244)
> at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83)
> at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
> at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78)
> at org.apache.spark.sql.execution.InputAdapter.produce(WholeStageCodegenExec.scala:218)
> at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:40)
> at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83)
> at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
> at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78)
> at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:30)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:309)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:347)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
> at org.apache.spark.sql.execution.joins.CartesianProductExec.doExecute(CartesianProductExec.scala:107)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
> at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:233)
> at org.apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:36)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:361)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
> at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:240)
> at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:287)
> at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:310)
> at org.apache.spark.sql.execution.QueryExecution$$anonfun$hiveResultString$3.apply(QueryExecution.scala:129)
> at org.apache.spark.sql.execution.QueryExecution$$anonfun$hiveResultString$3.apply(QueryExecution.scala:128)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
> at org.apache.spark.sql.execution.QueryExecution.hiveResultString(QueryExecution.scala:128)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:63)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:331)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:247)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:736)
> at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
> at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: java.lang.RuntimeException: Couldn't find col#21 in []
> at scala.sys.package$.error(package.scala:27)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:94)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:88)
> at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
> ... 85 more
> {code}
> The EXPLAIN works though:
> {code}
> == Physical Plan ==
> *Project [col#33 AS c1#26, col#36 AS c2#27]
> +- CartesianProduct
> :- CartesianProduct
> : :- HiveTableScan MetastoreRelation default, p1
> : +- HiveTableScan [col#33], MetastoreRelation default, p2, E
> +- *!Project [col#33 AS col#36]
> +- CartesianProduct
> :- HiveTableScan MetastoreRelation default, p1
> +- HiveTableScan MetastoreRelation default, p2, E
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org