Hi Stan, Looks like it is the same issue we are working to solve. Related PRs are:
https://github.com/apache/spark/pull/16998 https://github.com/apache/spark/pull/16785 You can take a look of those PRs and help review too. Thanks. StanZhai wrote > Hi all, > > > The driver hangs at DataFrame.rdd in Spark 2.1.0 when the DataFrame(SQL) > is complex, Following thread dump of my driver: > > > org.apache.spark.sql.catalyst.expressions.AttributeReference.equals(namedExpressions.scala:230) > org.apache.spark.sql.catalyst.expressions.IsNotNull.equals(nullExpressions.scala:312) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > org.apache.spark.sql.catalyst.expressions.Or.equals(predicates.scala:315) > scala.collection.mutable.FlatHashTable$class.addEntry(FlatHashTable.scala:151) > scala.collection.mutable.HashSet.addEntry(HashSet.scala:40) > scala.collection.mutable.FlatHashTable$class.addElem(FlatHashTable.scala:139) > scala.collection.mutable.HashSet.addElem(HashSet.scala:40) > scala.collection.mutable.HashSet.$plus$eq(HashSet.scala:59) > scala.collection.mutable.HashSet.$plus$eq(HashSet.scala:40) > scala.collection.generic.Growable$$anonfun$$plus$plus$eq$1.apply(Growable.scala:59) > scala.collection.generic.Growable$$anonfun$$plus$plus$eq$1.apply(Growable.scala:59) > scala.collection.mutable.HashSet.foreach(HashSet.scala:78) > scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59) > scala.collection.mutable.AbstractSet.$plus$plus$eq(Set.scala:46) > scala.collection.mutable.HashSet.clone(HashSet.scala:83) > scala.collection.mutable.HashSet.clone(HashSet.scala:40) > org.apache.spark.sql.catalyst.expressions.ExpressionSet.$plus(ExpressionSet.scala:65) > org.apache.spark.sql.catalyst.expressions.ExpressionSet.$plus(ExpressionSet.scala:50) > scala.collection.SetLike$$anonfun$$plus$plus$1.apply(SetLike.scala:141) > scala.collection.SetLike$$anonfun$$plus$plus$1.apply(SetLike.scala:141) > scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157) > scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157) > scala.collection.immutable.HashSet$HashSet1.foreach(HashSet.scala:316) > scala.collection.immutable.HashSet$HashTrieSet.foreach(HashSet.scala:972) > scala.collection.immutable.HashSet$HashTrieSet.foreach(HashSet.scala:972) > scala.collection.immutable.HashSet$HashTrieSet.foreach(HashSet.scala:972) > scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157) > scala.collection.AbstractTraversable.foldLeft(Traversable.scala:104) > scala.collection.TraversableOnce$class.$div$colon(TraversableOnce.scala:151) > scala.collection.AbstractTraversable.$div$colon(Traversable.scala:104) > scala.collection.SetLike$class.$plus$plus(SetLike.scala:141) > org.apache.spark.sql.catalyst.expressions.ExpressionSet.$plus$plus(ExpressionSet.scala:50) > org.apache.spark.sql.catalyst.plans.logical.UnaryNode$$anonfun$getAliasedConstraints$1.apply(LogicalPlan.scala:300) > org.apache.spark.sql.catalyst.plans.logical.UnaryNode$$anonfun$getAliasedConstraints$1.apply(LogicalPlan.scala:297) > scala.collection.immutable.List.foreach(List.scala:381) > org.apache.spark.sql.catalyst.plans.logical.UnaryNode.getAliasedConstraints(LogicalPlan.scala:297) > org.apache.spark.sql.catalyst.plans.logical.Project.validConstraints(basicLogicalOperators.scala:58) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints$lzycompute(QueryPlan.scala:187) > => holding > Monitor(org.apache.spark.sql.catalyst.plans.logical.Join@1365611745}) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints(QueryPlan.scala:187) > org.apache.spark.sql.catalyst.plans.logical.Project.validConstraints(basicLogicalOperators.scala:58) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints$lzycompute(QueryPlan.scala:187) > => holding > Monitor(org.apache.spark.sql.catalyst.plans.logical.Join@1365611745}) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints(QueryPlan.scala:187) > org.apache.spark.sql.catalyst.plans.logical.Project.validConstraints(basicLogicalOperators.scala:58) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints$lzycompute(QueryPlan.scala:187) > => holding > Monitor(org.apache.spark.sql.catalyst.plans.logical.Join@1365611745}) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints(QueryPlan.scala:187) > org.apache.spark.sql.catalyst.plans.logical.Project.validConstraints(basicLogicalOperators.scala:58) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints$lzycompute(QueryPlan.scala:187) > => holding > Monitor(org.apache.spark.sql.catalyst.plans.logical.Join@1365611745}) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints(QueryPlan.scala:187) > org.apache.spark.sql.catalyst.plans.logical.Project.validConstraints(basicLogicalOperators.scala:58) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints$lzycompute(QueryPlan.scala:187) > => holding > Monitor(org.apache.spark.sql.catalyst.plans.logical.Join@1365611745}) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints(QueryPlan.scala:187) > org.apache.spark.sql.catalyst.plans.logical.Join.validConstraints(basicLogicalOperators.scala:302) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints$lzycompute(QueryPlan.scala:187) > => holding > Monitor(org.apache.spark.sql.catalyst.plans.logical.Join@1365611745}) > org.apache.spark.sql.catalyst.plans.QueryPlan.constraints(QueryPlan.scala:187) > org.apache.spark.sql.catalyst.optimizer.InferFiltersFromConstraints$$anonfun$apply$13.applyOrElse(Optimizer.scala:618) > org.apache.spark.sql.catalyst.optimizer.InferFiltersFromConstraints$$anonfun$apply$13.applyOrElse(Optimizer.scala:605) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:332) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:332) > org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70) > org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:331) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$1.apply(TreeNode.scala:202) > org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188) > org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:200) > org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$1.apply(TreeNode.scala:202) > org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188) > org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:200) > org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$1.apply(TreeNode.scala:202) > org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188) > org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:200) > org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$1.apply(TreeNode.scala:202) > org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188) > org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:200) > org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:337) > org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:321) > org.apache.spark.sql.catalyst.optimizer.InferFiltersFromConstraints$.apply(Optimizer.scala:605) > org.apache.spark.sql.catalyst.optimizer.InferFiltersFromConstraints$.apply(Optimizer.scala:604) > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:85) > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:82) > scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:57) > scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:66) > scala.collection.mutable.WrappedArray.foldLeft(WrappedArray.scala:35) > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:82) > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:74) > scala.collection.immutable.List.foreach(List.scala:381) > org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:74) > org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:73) > => holding > Monitor(org.apache.spark.sql.execution.QueryExecution@184471747}) > org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:73) > org.apache.spark.sql.execution.QueryExecution$$anonfun$toString$2.apply(QueryExecution.scala:230) > org.apache.spark.sql.execution.QueryExecution$$anonfun$toString$2.apply(QueryExecution.scala:230) > org.apache.spark.sql.execution.QueryExecution.stringOrError(QueryExecution.scala:107) > org.apache.spark.sql.execution.QueryExecution.toString(QueryExecution.scala:230) > org.apache.spark.sql.Dataset.rdd$lzycompute(Dataset.scala:2544) > org.apache.spark.sql.Dataset.rdd(Dataset.scala:2544)... > > > The CPU usage of the driver remains 100% like this: > > > > I didn't find this issue in Spark 1.6.2, what causes this in Spark 2.1.0? > > > Any help is greatly appreciated! > > > Best, > Stan > > 25FEF70B@52873242.80CAAD58 (27K) > <http://apache-spark-developers-list.1001551.n3.nabble.com/attachment/21050/0/25FEF70B%4052873242.80CAAD58> ----- Liang-Chi Hsieh | @viirya Spark Technology Center http://www.spark.tc/ -- View this message in context: http://apache-spark-developers-list.1001551.n3.nabble.com/The-driver-hangs-at-DataFrame-rdd-in-Spark-2-1-0-tp21050p21083.html Sent from the Apache Spark Developers List mailing list archive at Nabble.com. --------------------------------------------------------------------- To unsubscribe e-mail: dev-unsubscr...@spark.apache.org
