[
https://issues.apache.org/jira/browse/SPARK-11596?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15019241#comment-15019241
]
Cristian commented on SPARK-11596:
----------------------------------
Ok, I found a much simpler repro. Note the below does not actually execute,
just generates the plans. DF.explain() takes a very long time here:
{code}
val c = (1 to 20).foldLeft[Option[DataFrame]] (None) { (curr, idx) =>
println(s"PROCESSING >>>>>>>>>>> $idx")
val df = sqlContext.sparkContext.parallelize((0 to
10).zipWithIndex).toDF("A", "B")
val union = curr.map(_.unionAll(df)).getOrElse(df)
union.cache()
Some(union)
}
c.get.explain(true) //<--- this is very expensive
{code}
> SQL execution very slow for nested query plans because of
> DataFrame.withNewExecutionId
> --------------------------------------------------------------------------------------
>
> Key: SPARK-11596
> URL: https://issues.apache.org/jira/browse/SPARK-11596
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.5.1
> Reporter: Cristian
> Attachments: screenshot-1.png
>
>
> For nested query plans like a recursive unionAll, withExecutionId is
> extremely slow, likely because of repeated string concatenation in
> QueryPlan.simpleString
> Test case:
> {code}
> (1 to 100).foldLeft[Option[DataFrame]] (None) { (curr, idx) =>
> println(s"PROCESSING >>>>>>>>>>> $idx")
> val df = sqlContext.sparkContext.parallelize((0 to
> 10).zipWithIndex).toDF("A", "B")
> val union = curr.map(_.unionAll(df)).getOrElse(df)
> union.cache()
> println(">>" + union.count)
> //union.show()
> Some(union)
> }
> {code}
> Stack trace:
> {quote}
> scala.collection.TraversableOnce$class.addString(TraversableOnce.scala:320)
> scala.collection.AbstractIterator.addString(Iterator.scala:1157)
> scala.collection.TraversableOnce$class.mkString(TraversableOnce.scala:286)
> scala.collection.AbstractIterator.mkString(Iterator.scala:1157)
> scala.collection.TraversableOnce$class.mkString(TraversableOnce.scala:288)
> scala.collection.AbstractIterator.mkString(Iterator.scala:1157)
> org.apache.spark.sql.catalyst.trees.TreeNode.argString(TreeNode.scala:364)
> org.apache.spark.sql.catalyst.trees.TreeNode.simpleString(TreeNode.scala:367)
> org.apache.spark.sql.catalyst.plans.QueryPlan.simpleString(QueryPlan.scala:168)
> org.apache.spark.sql.catalyst.trees.TreeNode.generateTreeString(TreeNode.scala:401)
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$generateTreeString$1.apply(TreeNode.scala:403)
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$generateTreeString$1.apply(TreeNode.scala:403)
> scala.collection.immutable.List.foreach(List.scala:318)
> org.apache.spark.sql.catalyst.trees.TreeNode.generateTreeString(TreeNode.scala:403)
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$generateTreeString$1.apply(TreeNode.scala:403)
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$generateTreeString$1.apply(TreeNode.scala:403)
> scala.collection.immutable.List.foreach(List.scala:318)
> org.apache.spark.sql.catalyst.trees.TreeNode.generateTreeString(TreeNode.scala:403)
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$generateTreeString$1.apply(TreeNode.scala:403)
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$generateTreeString$1.apply(TreeNode.scala:403)
> scala.collection.immutable.List.foreach(List.scala:318)
> org.apache.spark.sql.catalyst.trees.TreeNode.generateTreeString(TreeNode.scala:403)
> org.apache.spark.sql.catalyst.trees.TreeNode.treeString(TreeNode.scala:372)
> org.apache.spark.sql.catalyst.trees.TreeNode.toString(TreeNode.scala:369)
> org.apache.spark.sql.SQLContext$QueryExecution.stringOrError(SQLContext.scala:936)
> org.apache.spark.sql.SQLContext$QueryExecution.toString(SQLContext.scala:949)
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:52)
> org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1903)
> org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1384)
> org.apache.spark.sql.DataFrame.count(DataFrame.scala:1402)
> {quote}
--
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
