[
https://issues.apache.org/jira/browse/SPARK-10093?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Reynold Xin resolved SPARK-10093.
---------------------------------
Resolution: Fixed
Fix Version/s: 1.5.0
> Invalid transformations for TungstenProject of struct type
> ----------------------------------------------------------
>
> Key: SPARK-10093
> URL: https://issues.apache.org/jira/browse/SPARK-10093
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.5.0
> Reporter: Michael Armbrust
> Assignee: Michael Armbrust
> Priority: Blocker
> Fix For: 1.5.0
>
>
> Code to reproduce:
> {code}
> val df = Seq((1,1)).toDF("a", "b")
> df.where($"a" === 1)
> .select($"a", $"b", struct($"b"))
> .orderBy("a")
> .select(struct($"b"))
> .collect()
> {code}
> {code}
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in
> stage 37.0 failed 4 times, most recent failure: Lost task 1.3 in stage 37.0
> (TID 1118, 10.0.167.218):
> org.apache.spark.sql.catalyst.errors.package$TreeNodeException: makeCopy,
> tree:
> Exchange rangepartitioning(a#197 ASC)
> ConvertToSafe
> TungstenProject [_1#195 AS a#197,_2#196 AS b#198,struct(_2#196 AS b#198) AS
> struct(b)#199]
> Filter (_1#195 = 1)
> LocalTableScan [_1#195,_2#196], [[1,1]]
> at
> org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:49)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.makeCopy(TreeNode.scala:315)
> at org.apache.spark.sql.execution.SparkPlan.makeCopy(SparkPlan.scala:80)
> at org.apache.spark.sql.execution.SparkPlan.makeCopy(SparkPlan.scala:46)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:280)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:232)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:232)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:232)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:249)
> at scala.collection.Iterator$$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:279)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:232)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:232)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:232)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:249)
> at scala.collection.Iterator$$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:279)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:232)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$2.apply(TreeNode.scala:234)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$2.apply(TreeNode.scala:234)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:249)
> at scala.collection.Iterator$$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:279)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:234)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:217)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.transformAllExpressions(QueryPlan.scala:134)
> at
> org.apache.spark.sql.execution.TungstenProject$$anonfun$2.apply(basicOperators.scala:81)
> at
> org.apache.spark.sql.execution.TungstenProject$$anonfun$2.apply(basicOperators.scala:80)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.reflect.InvocationTargetException
> at sun.reflect.GeneratedConstructorAccessor48.newInstance(Unknown
> Source)
> at
> sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
> at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$makeCopy$1$$anonfun$apply$10.apply(TreeNode.scala:326)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$makeCopy$1$$anonfun$apply$10.apply(TreeNode.scala:325)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$makeCopy$1.apply(TreeNode.scala:323)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$makeCopy$1.apply(TreeNode.scala:315)
> at
> org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:48)
> ... 74 more
> Caused by: java.lang.NullPointerException
> at
> org.apache.spark.sql.execution.Exchange.sparkConf$lzycompute(Exchange.scala:130)
> at org.apache.spark.sql.execution.Exchange.sparkConf(Exchange.scala:130)
> at org.apache.spark.sql.execution.Exchange.<init>(Exchange.scala:137)
> ... 83 more
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
