[
https://issues.apache.org/jira/browse/SPARK-19933?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Zhenhua Wang updated SPARK-19933:
---------------------------------
Description:
The latest commit of my test version (master branch on Mar 13) is:
https://github.com/apache/spark/commit/9456688547522a62f1e7520e9b3564550c57aa5d
All tables are in parquet format.
Error messages are as follows:
TreeNodeException: Binding attribute, tree: s_state#4
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$$anonfun$2.apply(TreeNode.scala:267)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:267)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:266)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:272)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:272)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:272)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:256)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
at
org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.bind(GeneratePredicate.scala:45)
at
org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.bind(GeneratePredicate.scala:40)
at
org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:884)
at
org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:358)
at
org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec.org$apache$spark$sql$execution$joins$BroadcastNestedLoopJoinExec$$boundCondition$lzycompute(BroadcastNestedLoopJoinExec.scala:87)
at
org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec.org$apache$spark$sql$execution$joins$BroadcastNestedLoopJoinExec$$boundCondition(BroadcastNestedLoopJoinExec.scala:85)
at
org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec$$anonfun$4$$anonfun$apply$2$$anonfun$apply$3.apply(BroadcastNestedLoopJoinExec.scala:191)
at
org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec$$anonfun$4$$anonfun$apply$2$$anonfun$apply$3.apply(BroadcastNestedLoopJoinExec.scala:191)
at
scala.collection.IndexedSeqOptimized$class.prefixLengthImpl(IndexedSeqOptimized.scala:38)
at
scala.collection.IndexedSeqOptimized$class.exists(IndexedSeqOptimized.scala:46)
at scala.collection.mutable.ArrayOps$ofRef.exists(ArrayOps.scala:186)
at
org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec$$anonfun$4$$anonfun$apply$2.apply(BroadcastNestedLoopJoinExec.scala:191)
at
org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec$$anonfun$4$$anonfun$apply$2.apply(BroadcastNestedLoopJoinExec.scala:190)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:463)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:378)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at
org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:126)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:317)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.RuntimeException: Couldn't find s_state#4 in
[ss_store_sk#14,ss_net_profit#29,s_store_sk#58,s_county#81,s_state#82,s_state#136]
at scala.sys.package$.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)
... 42 more
was:
The latest commit of my test version (master branch on Mar 13) is:
https://github.com/apache/spark/commit/9456688547522a62f1e7520e9b3564550c57aa5d
All tables are in parquet format.
Error messages are as follows:
17/03/13 13:11:26 ERROR SparkSQLDriver: Failed in [explain SELECT
sum(ss_net_profit) AS total_sum,
s_state,
s_county,
grouping(s_state) + grouping(s_county) AS lochierarchy,
rank()
OVER (
PARTITION BY grouping(s_state) + grouping(s_county),
CASE WHEN grouping(s_county) = 0
THEN s_state END
ORDER BY sum(ss_net_profit) DESC) AS rank_within_parent
FROM
store_sales, date_dim d1, store
WHERE
d1.d_month_seq BETWEEN 1200 AND 1200 + 11
AND d1.d_date_sk = ss_sold_date_sk
AND s_store_sk = ss_store_sk
AND s_state IN
(SELECT s_state
FROM
(SELECT
s_state AS s_state,
rank()
OVER (PARTITION BY s_state
ORDER BY sum(ss_net_profit) DESC) AS ranking
FROM store_sales, store, date_dim
WHERE d_month_seq BETWEEN 1200 AND 1200 + 11
AND d_date_sk = ss_sold_date_sk
AND s_store_sk = ss_store_sk
GROUP BY s_state) tmp1
WHERE ranking <= 5)
GROUP BY ROLLUP (s_state, s_county)
ORDER BY
lochierarchy DESC
, CASE WHEN lochierarchy = 0
THEN s_state END
, rank_within_parent
LIMIT 100]
java.lang.NoSuchMethodError:
org.apache.spark.sql.catalyst.catalog.CatalogTable.<init>(Lorg/apache/spark/sql/catalyst/TableIdentifier;Lorg/apache/spark/sql/catalyst/catalog/CatalogTableType;Lorg/apache/spark/sql/catalyst/catalog/CatalogStorageFormat;Lorg/apache/spark/sql/types/StructType;Lscala/Option;Lscala/collection/Seq;Lscala/Option;Ljava/lang/String;JJLscala/collection/immutable/Map;Lscala/Option;Lscala/Option;Lscala/Option;Lscala/collection/Seq;Z)V
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getTableOption$1$$anonfun$apply$11.apply(HiveClientImpl.scala:397)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getTableOption$1$$anonfun$apply$11.apply(HiveClientImpl.scala:370)
at scala.Option.map(Option.scala:146)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getTableOption$1.apply(HiveClientImpl.scala:370)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getTableOption$1.apply(HiveClientImpl.scala:368)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$withHiveState$1.apply(HiveClientImpl.scala:287)
at
org.apache.spark.sql.hive.client.HiveClientImpl.liftedTree1$1(HiveClientImpl.scala:228)
at
org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:227)
at
org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:270)
at
org.apache.spark.sql.hive.client.HiveClientImpl.getTableOption(HiveClientImpl.scala:368)
at
org.apache.spark.sql.hive.client.HiveClient$class.getTable(HiveClient.scala:74)
at
org.apache.spark.sql.hive.client.HiveClientImpl.getTable(HiveClientImpl.scala:79)
at
org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$org$apache$spark$sql$hive$HiveExternalCatalog$$getRawTable$1.apply(HiveExternalCatalog.scala:110)
at
org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$org$apache$spark$sql$hive$HiveExternalCatalog$$getRawTable$1.apply(HiveExternalCatalog.scala:110)
at
org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:95)
at
org.apache.spark.sql.hive.HiveExternalCatalog.org$apache$spark$sql$hive$HiveExternalCatalog$$getRawTable(HiveExternalCatalog.scala:109)
at
org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$getTable$1.apply(HiveExternalCatalog.scala:620)
at
org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$getTable$1.apply(HiveExternalCatalog.scala:620)
at
org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:95)
at
org.apache.spark.sql.hive.HiveExternalCatalog.getTable(HiveExternalCatalog.scala:619)
at
org.apache.spark.sql.catalyst.catalog.SessionCatalog.lookupRelation(SessionCatalog.scala:600)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveRelations$$lookupTableFromCatalog(Analyzer.scala:629)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.resolveRelation(Analyzer.scala:590)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:614)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:607)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:62)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:62)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:61)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:607)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:559)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:85)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:82)
at
scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:82)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:74)
at scala.collection.immutable.List.foreach(List.scala:381)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:74)
at
org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:70)
at
org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:68)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:51)
at
org.apache.spark.sql.execution.QueryExecution.withCachedData$lzycompute(QueryExecution.scala:74)
at
org.apache.spark.sql.execution.QueryExecution.withCachedData(QueryExecution.scala:73)
at
org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:79)
at
org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:79)
at
org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:85)
at
org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:81)
at
org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:90)
at
org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:90)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$simpleString$1.apply(QueryExecution.scala:199)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$simpleString$1.apply(QueryExecution.scala:199)
at
org.apache.spark.sql.execution.QueryExecution.stringOrError(QueryExecution.scala:113)
at
org.apache.spark.sql.execution.QueryExecution.simpleString(QueryExecution.scala:199)
at
org.apache.spark.sql.execution.command.ExplainCommand.run(commands.scala:121)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:67)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:183)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:68)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:617)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:688)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:335)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.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:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:739)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:178)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:203)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:117)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
java.lang.NoSuchMethodError:
org.apache.spark.sql.catalyst.catalog.CatalogTable.<init>(Lorg/apache/spark/sql/catalyst/TableIdentifier;Lorg/apache/spark/sql/catalyst/catalog/CatalogTableType;Lorg/apache/spark/sql/catalyst/catalog/CatalogStorageFormat;Lorg/apache/spark/sql/types/StructType;Lscala/Option;Lscala/collection/Seq;Lscala/Option;Ljava/lang/String;JJLscala/collection/immutable/Map;Lscala/Option;Lscala/Option;Lscala/Option;Lscala/collection/Seq;Z)V
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getTableOption$1$$anonfun$apply$11.apply(HiveClientImpl.scala:397)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getTableOption$1$$anonfun$apply$11.apply(HiveClientImpl.scala:370)
at scala.Option.map(Option.scala:146)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getTableOption$1.apply(HiveClientImpl.scala:370)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getTableOption$1.apply(HiveClientImpl.scala:368)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$withHiveState$1.apply(HiveClientImpl.scala:287)
at
org.apache.spark.sql.hive.client.HiveClientImpl.liftedTree1$1(HiveClientImpl.scala:228)
at
org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:227)
at
org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:270)
at
org.apache.spark.sql.hive.client.HiveClientImpl.getTableOption(HiveClientImpl.scala:368)
at
org.apache.spark.sql.hive.client.HiveClient$class.getTable(HiveClient.scala:74)
at
org.apache.spark.sql.hive.client.HiveClientImpl.getTable(HiveClientImpl.scala:79)
at
org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$org$apache$spark$sql$hive$HiveExternalCatalog$$getRawTable$1.apply(HiveExternalCatalog.scala:110)
at
org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$org$apache$spark$sql$hive$HiveExternalCatalog$$getRawTable$1.apply(HiveExternalCatalog.scala:110)
at
org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:95)
at
org.apache.spark.sql.hive.HiveExternalCatalog.org$apache$spark$sql$hive$HiveExternalCatalog$$getRawTable(HiveExternalCatalog.scala:109)
at
org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$getTable$1.apply(HiveExternalCatalog.scala:620)
at
org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$getTable$1.apply(HiveExternalCatalog.scala:620)
at
org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:95)
at
org.apache.spark.sql.hive.HiveExternalCatalog.getTable(HiveExternalCatalog.scala:619)
at
org.apache.spark.sql.catalyst.catalog.SessionCatalog.lookupRelation(SessionCatalog.scala:600)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveRelations$$lookupTableFromCatalog(Analyzer.scala:629)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.resolveRelation(Analyzer.scala:590)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:614)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:607)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:62)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:62)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:61)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:59)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:607)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:559)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:85)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:82)
at
scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:82)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:74)
at scala.collection.immutable.List.foreach(List.scala:381)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:74)
at
org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:70)
at
org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:68)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:51)
at
org.apache.spark.sql.execution.QueryExecution.withCachedData$lzycompute(QueryExecution.scala:74)
at
org.apache.spark.sql.execution.QueryExecution.withCachedData(QueryExecution.scala:73)
at
org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:79)
at
org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:79)
at
org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:85)
at
org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:81)
at
org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:90)
at
org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:90)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$simpleString$1.apply(QueryExecution.scala:199)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$simpleString$1.apply(QueryExecution.scala:199)
at
org.apache.spark.sql.execution.QueryExecution.stringOrError(QueryExecution.scala:113)
at
org.apache.spark.sql.execution.QueryExecution.simpleString(QueryExecution.scala:199)
at
org.apache.spark.sql.execution.command.ExplainCommand.run(commands.scala:121)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:67)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:183)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:68)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:617)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:688)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:335)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:247)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:739)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:178)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:203)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:117)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> TPCDS Q70 went wrong while explaining
> -------------------------------------
>
> Key: SPARK-19933
> URL: https://issues.apache.org/jira/browse/SPARK-19933
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.2.0
> Reporter: Zhenhua Wang
>
> The latest commit of my test version (master branch on Mar 13) is:
> https://github.com/apache/spark/commit/9456688547522a62f1e7520e9b3564550c57aa5d
> All tables are in parquet format.
> Error messages are as follows:
> TreeNodeException: Binding attribute, tree: s_state#4
> at
> org.apache.spark.sql.catalyst.errors.package$.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$$anonfun$2.apply(TreeNode.scala:267)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:267)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:266)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:272)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:272)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:272)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:256)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.bind(GeneratePredicate.scala:45)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.bind(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:884)
> at
> org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:358)
> at
> org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec.org$apache$spark$sql$execution$joins$BroadcastNestedLoopJoinExec$$boundCondition$lzycompute(BroadcastNestedLoopJoinExec.scala:87)
> at
> org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec.org$apache$spark$sql$execution$joins$BroadcastNestedLoopJoinExec$$boundCondition(BroadcastNestedLoopJoinExec.scala:85)
> at
> org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec$$anonfun$4$$anonfun$apply$2$$anonfun$apply$3.apply(BroadcastNestedLoopJoinExec.scala:191)
> at
> org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec$$anonfun$4$$anonfun$apply$2$$anonfun$apply$3.apply(BroadcastNestedLoopJoinExec.scala:191)
> at
> scala.collection.IndexedSeqOptimized$class.prefixLengthImpl(IndexedSeqOptimized.scala:38)
> at
> scala.collection.IndexedSeqOptimized$class.exists(IndexedSeqOptimized.scala:46)
> at scala.collection.mutable.ArrayOps$ofRef.exists(ArrayOps.scala:186)
> at
> org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec$$anonfun$4$$anonfun$apply$2.apply(BroadcastNestedLoopJoinExec.scala:191)
> at
> org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec$$anonfun$4$$anonfun$apply$2.apply(BroadcastNestedLoopJoinExec.scala:190)
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:463)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
> at
> org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown
> Source)
> at
> org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown
> Source)
> at
> org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
> at
> org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:378)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
> at
> org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:126)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.scheduler.Task.run(Task.scala:108)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:317)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.RuntimeException: Couldn't find s_state#4 in
> [ss_store_sk#14,ss_net_profit#29,s_store_sk#58,s_county#81,s_state#82,s_state#136]
> at scala.sys.package$.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)
> ... 42 more
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
