Yin Huai created SPARK-13867:
--------------------------------
Summary: Failed to bind reference when cume_dist is used
Key: SPARK-13867
URL: https://issues.apache.org/jira/browse/SPARK-13867
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 2.0.0
Reporter: Yin Huai
When cume_dist is used, we got the following error.
{code}
org.apache.spark.SparkException: Job aborted due to stage failure: Task 10 in
stage 102.0 failed 4 times, most recent failure: Lost task 10.3 in stage 102.0
(TID 8448, ip-10-216-233-112.eu-west-1.compute.internal):
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding
attribute, tree: window__partition__size#206
at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:49)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:86)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:85)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:259)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:259)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:258)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:281)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:321)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:281)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:321)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:249)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:85)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection$$anonfun$$init$$2.apply(Projection.scala:62)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection$$anonfun$$init$$2.apply(Projection.scala:62)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.AbstractTraversable.map(Traversable.scala:105)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.<init>(Projection.scala:62)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$newMutableProjection$1.apply(SparkPlan.scala:234)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$newMutableProjection$1.apply(SparkPlan.scala:234)
at
org.apache.spark.sql.execution.AggregateProcessor$.apply(Window.scala:925)
at
org.apache.spark.sql.execution.Window$$anonfun$windowFrameExpressionFactoryPairs$2.org$apache$spark$sql$execution$Window$$anonfun$$processor$1(Window.scala:201)
at
org.apache.spark.sql.execution.Window$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(Window.scala:221)
at
org.apache.spark.sql.execution.Window$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(Window.scala:218)
at
org.apache.spark.sql.execution.Window$$anonfun$14$$anon$1$$anonfun$16.apply(Window.scala:315)
at
org.apache.spark.sql.execution.Window$$anonfun$14$$anon$1$$anonfun$16.apply(Window.scala:315)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at
org.apache.spark.sql.execution.Window$$anonfun$14$$anon$1.<init>(Window.scala:315)
at
org.apache.spark.sql.execution.Window$$anonfun$14.apply(Window.scala:287)
at
org.apache.spark.sql.execution.Window$$anonfun$14.apply(Window.scala:286)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.RuntimeException: Couldn't find
window__partition__size#206 in [window__partition__size#3,rowNumber#248]
at scala.sys.package$.error(package.scala:27)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:92)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:86)
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:48)
... 86 more
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1835)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1848)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1925)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1213)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1156)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1156)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at
org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopDataset(PairRDDFunctions.scala:1156)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply$mcV$sp(PairRDDFunctions.scala:1060)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1026)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1026)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at
org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:1026)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply$mcV$sp(PairRDDFunctions.scala:952)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply(PairRDDFunctions.scala:952)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply(PairRDDFunctions.scala:952)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at
org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:951)
at
org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply$mcV$sp(RDD.scala:1457)
at
org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply(RDD.scala:1436)
at
org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply(RDD.scala:1436)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1436)
at
com.databricks.spark.csv.package$CsvSchemaRDD.saveAsCsvFile(package.scala:180)
at
com.databricks.spark.csv.DefaultSource.createRelation(DefaultSource.scala:185)
at
org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:222)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:148)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:139)
Caused by: org.apache.spark.sql.catalyst.errors.package$TreeNodeException:
Binding attribute, tree: window__partition__size#206
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:49)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:86)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:85)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:259)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:259)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:258)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:281)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:321)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:281)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:321)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:249)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:85)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection$$anonfun$$init$$2.apply(Projection.scala:62)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection$$anonfun$$init$$2.apply(Projection.scala:62)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.AbstractTraversable.map(Traversable.scala:105)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.<init>(Projection.scala:62)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$newMutableProjection$1.apply(SparkPlan.scala:234)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$newMutableProjection$1.apply(SparkPlan.scala:234)
at
org.apache.spark.sql.execution.AggregateProcessor$.apply(Window.scala:925)
at
org.apache.spark.sql.execution.Window$$anonfun$windowFrameExpressionFactoryPairs$2.org$apache$spark$sql$execution$Window$$anonfun$$processor$1(Window.scala:201)
at
org.apache.spark.sql.execution.Window$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(Window.scala:221)
at
org.apache.spark.sql.execution.Window$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(Window.scala:218)
at
org.apache.spark.sql.execution.Window$$anonfun$14$$anon$1$$anonfun$16.apply(Window.scala:315)
at
org.apache.spark.sql.execution.Window$$anonfun$14$$anon$1$$anonfun$16.apply(Window.scala:315)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at
org.apache.spark.sql.execution.Window$$anonfun$14$$anon$1.<init>(Window.scala:315)
at
org.apache.spark.sql.execution.Window$$anonfun$14.apply(Window.scala:287)
at
org.apache.spark.sql.execution.Window$$anonfun$14.apply(Window.scala:286)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.RuntimeException: Couldn't find
window__partition__size#206 in [window__partition__size#3,rowNumber#248]
at scala.sys.package$.error(package.scala:27)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:92)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:86)
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:48)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:86)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:85)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:259)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:259)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:258)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:281)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:321)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:281)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:321)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:249)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:85)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection$$anonfun$$init$$2.apply(Projection.scala:62)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection$$anonfun$$init$$2.apply(Projection.scala:62)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.AbstractTraversable.map(Traversable.scala:105)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.<init>(Projection.scala:62)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$newMutableProjection$1.apply(SparkPlan.scala:234)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$newMutableProjection$1.apply(SparkPlan.scala:234)
at
org.apache.spark.sql.execution.AggregateProcessor$.apply(Window.scala:925)
at
org.apache.spark.sql.execution.Window$$anonfun$windowFrameExpressionFactoryPairs$2.org$apache$spark$sql$execution$Window$$anonfun$$processor$1(Window.scala:201)
at
org.apache.spark.sql.execution.Window$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(Window.scala:221)
at
org.apache.spark.sql.execution.Window$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(Window.scala:218)
at
org.apache.spark.sql.execution.Window$$anonfun$14$$anon$1$$anonfun$16.apply(Window.scala:315)
at
org.apache.spark.sql.execution.Window$$anonfun$14$$anon$1$$anonfun$16.apply(Window.scala:315)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at
org.apache.spark.sql.execution.Window$$anonfun$14$$anon$1.<init>(Window.scala:315)
at
org.apache.spark.sql.execution.Window$$anonfun$14.apply(Window.scala:287)
at
org.apache.spark.sql.execution.Window$$anonfun$14.apply(Window.scala:286)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
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)
{code}
The line 201 of Window.scala is {{def processor = AggregateProcessor(functions,
ordinal, child.output, newMutableProjection)}} and the AggregateProcessor is
defined as
{code}
private[execution] object AggregateProcessor {
def apply(functions: Array[Expression],
ordinal: Int,
inputAttributes: Seq[Attribute],
newMutableProjection: (Seq[Expression], Seq[Attribute]) => () =>
MutableProjection):
AggregateProcessor = {
val aggBufferAttributes = mutable.Buffer.empty[AttributeReference]
val initialValues = mutable.Buffer.empty[Expression]
val updateExpressions = mutable.Buffer.empty[Expression]
val evaluateExpressions = mutable.Buffer.fill[Expression](ordinal)(NoOp)
val imperatives = mutable.Buffer.empty[ImperativeAggregate]
// Check if there are any SizeBasedWindowFunctions. If there are, we add
the partition size to
// the aggregation buffer. Note that the ordinal of the partition size
value will always be 0.
val trackPartitionSize =
functions.exists(_.isInstanceOf[SizeBasedWindowFunction])
if (trackPartitionSize) {
aggBufferAttributes += SizeBasedWindowFunction.n
initialValues += NoOp
updateExpressions += NoOp
}
// Add an AggregateFunction to the AggregateProcessor.
functions.foreach {
case agg: DeclarativeAggregate =>
aggBufferAttributes ++= agg.aggBufferAttributes
initialValues ++= agg.initialValues
updateExpressions ++= agg.updateExpressions
evaluateExpressions += agg.evaluateExpression
case agg: ImperativeAggregate =>
val offset = aggBufferAttributes.size
val imperative = BindReferences.bindReference(agg
.withNewInputAggBufferOffset(offset)
.withNewMutableAggBufferOffset(offset),
inputAttributes)
imperatives += imperative
aggBufferAttributes ++= imperative.aggBufferAttributes
val noOps = Seq.fill(imperative.aggBufferAttributes.size)(NoOp)
initialValues ++= noOps
updateExpressions ++= noOps
evaluateExpressions += imperative
case other =>
sys.error(s"Unsupported Aggregate Function: $other")
}
// Create the projections.
val initialProjection = newMutableProjection(
initialValues,
Seq(SizeBasedWindowFunction.n))()
val updateProjection = newMutableProjection(
updateExpressions,
aggBufferAttributes ++ inputAttributes)()
val evaluateProjection = newMutableProjection(
evaluateExpressions,
aggBufferAttributes)()
// Create the processor
new AggregateProcessor(
aggBufferAttributes.toArray,
initialProjection,
updateProjection,
evaluateProjection,
imperatives.toArray,
trackPartitionSize)
}
{code}
The exception is thrown from
{code}
val evaluateProjection = newMutableProjection(
evaluateExpressions,
aggBufferAttributes)()
{code}
Looks like we are using SizeBasedWindowFunction.n (the attribute of
window_partition_size) generated by driver and executor together.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
