The exception drives me crazy, because it occurs randomly.
I didn't know which line of my code causes this exception.
I didn't even understand what "KryoException:
java.lang.NegativeArraySizeException" means, or even implies?
14/10/20 15:59:01 WARN scheduler.TaskSetManager: Lost task 32.2 in stage
0.0 (TID 181, gs-server-1000): com.esotericsoftware.kryo.KryoException:
java.lang.NegativeArraySizeException
Serialization trace:
value (org.apache.spark.sql.catalyst.expressions.MutableAny)
values (org.apache.spark.sql.catalyst.expressions.SpecificMutableRow)
otherElements (org.apache.spark.util.collection.CompactBuffer)
com.esotericsoftware.kryo.serializers.FieldSerializer$ObjectField.write(FieldSerializer.java:585)
com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:213)
com.esotericsoftware.kryo.Kryo.writeClassAndObject(Kryo.java:568)
com.esotericsoftware.kryo.serializers.DefaultArraySerializers$ObjectArraySerializer.write(DefaultArraySerializers.java:318)
com.esotericsoftware.kryo.serializers.DefaultArraySerializers$ObjectArraySerializer.write(DefaultArraySerializers.java:293)
com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:501)
com.esotericsoftware.kryo.serializers.FieldSerializer$ObjectField.write(FieldSerializer.java:564)
com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:213)
com.esotericsoftware.kryo.Kryo.writeClassAndObject(Kryo.java:568)
com.esotericsoftware.kryo.serializers.DefaultArraySerializers$ObjectArraySerializer.write(DefaultArraySerializers.java:318)
com.esotericsoftware.kryo.serializers.DefaultArraySerializers$ObjectArraySerializer.write(DefaultArraySerializers.java:293)
com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:501)
com.esotericsoftware.kryo.serializers.FieldSerializer$ObjectField.write(FieldSerializer.java:564)
com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:213)
com.esotericsoftware.kryo.Kryo.writeClassAndObject(Kryo.java:568)
com.twitter.chill.Tuple2Serializer.write(TupleSerializers.scala:38)
com.twitter.chill.Tuple2Serializer.write(TupleSerializers.scala:34)
com.esotericsoftware.kryo.Kryo.writeClassAndObject(Kryo.java:568)
org.apache.spark.serializer.KryoSerializationStream.writeObject(KryoSerializer.scala:119)
org.apache.spark.storage.DiskBlockObjectWriter.write(BlockObjectWriter.scala:195)
org.apache.spark.util.collection.ExternalAppendOnlyMap.spill(ExternalAppendOnlyMap.scala:203)
org.apache.spark.util.collection.ExternalAppendOnlyMap.insertAll(ExternalAppendOnlyMap.scala:150)
org.apache.spark.Aggregator.combineValuesByKey(Aggregator.scala:58)
org.apache.spark.rdd.PairRDDFunctions$$anonfun$combineByKey$2.apply(PairRDDFunctions.scala:90)
org.apache.spark.rdd.PairRDDFunctions$$anonfun$combineByKey$2.apply(PairRDDFunctions.scala:89)
org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:625)
org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:625)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.FlatMappedRDD.compute(FlatMappedRDD.scala:33)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
