ERROR [2023-10-16 18:19:46,962] ({Executor task launch worker for task 27030} Logging.scala[logError]:94) - Exception in task 197.0 in stage 319.0 (TID 27030)
java.lang.OutOfMemoryError: GC overhead limit exceeded
at sun.nio.cs.UTF_8.newDecoder(UTF_8.java:68)
at java.lang.StringCoding.decode(StringCoding.java:213)
at java.lang.String.<init>(String.java:463)
at java.lang.String.<init>(String.java:515)
at com.teragrep.blf_01.Token.toString(Token.java:85)
at com.teragrep.functions.dpf_03.TokenAggregator.$anonfun$finish$1(TokenAggregator.scala:82)
at com.teragrep.functions.dpf_03.TokenAggregator$$Lambda$36/263211599.apply(Unknown Source)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.mutable.HashMap$$anon$1$$anonfun$foreach$2.apply(HashMap.scala:134)
at scala.collection.mutable.HashMap$$anon$1$$anonfun$foreach$2.apply(HashMap.scala:134)
at scala.collection.mutable.HashTable$class.foreachEntry(HashTable.scala:236)
at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:40)
at scala.collection.mutable.HashMap$$anon$1.foreach(HashMap.scala:134)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractSet.scala$collection$SetLike$$super$map(Set.scala:47)
at scala.collection.SetLike$class.map(SetLike.scala:92)
at scala.collection.AbstractSet.map(Set.scala:47)
at com.teragrep.functions.dpf_03.TokenAggregator.finish(TokenAggregator.scala:82)
at com.teragrep.functions.dpf_03.TokenAggregator.finish(TokenAggregator.scala:59)
at org.apache.spark.sql.execution.aggregate.ComplexTypedAggregateExpression.eval(TypedAggregateExpression.scala:261)
at org.apache.spark.sql.catalyst.expressions.aggregate.TypedImperativeAggregate.eval(interfaces.scala:545)
at org.apache.spark.sql.execution.aggregate.AggregationIterator$$anonfun$generateResultProjection$1.apply(AggregationIterator.scala:231)
at org.apache.spark.sql.execution.aggregate.AggregationIterator$$anonfun$generateResultProjection$1.apply(AggregationIterator.scala:223)
at org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.next(ObjectAggregationIterator.scala:86)
at org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.next(ObjectAggregationIterator.scala:33)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:410)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:410)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$11$$anon$1.hasNext(WholeStageCodegenExec.scala:624)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)