StackOverflow关于Spark 1.5.2上的窗口函数的异常

Question

我有一个数据框，为了横向移动。我使用了很多主要功能。当我运行程序并且发生了stackoverflow异常时。

是内存的原因以及如何进行内存调整。

val win = Window.partitionBy(df("KEY1"), df("KEY2"), df("KEY3"),df("KEY4"))
                  .orderBy(df("A").asc)

val df1 = df.withColumn("rank", rowNumber.over(win))
  .withColumn("A1", col("A"))
  .withColumn("A2", lead("A", 1).over(win))
  .withColumn("A3", lead("A", 2).over(win))
  .withColumn("A4", lead("A", 3).over(win))
  .withColumn("A5", lead("A", 4).over(win))
  .withColumn("A6", lead("A", 5).over(win))
  .withColumn("A7", lead("A", 6).over(win))
  .withColumn("A8", lead("A", 7).over(win))
  ...........          // there're 250 lead window functions
  .filter("rank = '1'")

df1.show()

异常信息：

    java.lang.StackOverflowError
        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$$anon$11.next(Iterator.scala:328)
        at scala.collection.Iterator$class.foreach(Iterator.scala:727)
        at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
        at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
        at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
        at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
        at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
        at scala.collection.AbstractIterator.to(Iterator.scala:1157)
        at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
        at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
        at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
        at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
        at org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:279)
        at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:232)
        at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionDown$1(QueryPlan.scala:75)
        at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:85)
        at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1.apply(QueryPlan.scala:93)
        at scala.collection.Iterator$$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.plans.QueryPlan.transformExpressionsDown(QueryPlan.scala:93)
        at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressions(QueryPlan.scala:64)
        at org.apache.spark.sql.hive.ResolveHiveWindowFunction$$anonfun$apply$1.applyOrElse(hiveUDFs.scala:239)
        at org.apache.spark.sql.hive.ResolveHiveWindowFunction$$anonfun$apply$1.applyOrElse(hiveUDFs.scala:233)
        at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:293)
        at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:293)
        at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
        at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:292)
        at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:290)
        at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:290)
        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)