not sure why, but i am getting this today using spark 2 snapshots...
i am on java 7 and scala 2.11
16/04/15 12:35:46 WARN TaskSetManager: Lost task 2.0 in stage 3.0 (TID 15,
localhost): java.lang.ClassFormatError: Duplicate field name&signature in
class file
org/apache/spark/sql/catalyst/expressions/GeneratedClass$SpecificMutableProjection
at java.lang.ClassLoader.defineClass1(Native Method)
at java.lang.ClassLoader.defineClass(ClassLoader.java:800)
at
org.codehaus.janino.ByteArrayClassLoader.findClass(ByteArrayClassLoader.java:66)
at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass.generate(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$create$2.apply(GenerateMutableProjection.scala:140)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$create$2.apply(GenerateMutableProjection.scala:139)
at
org.apache.spark.sql.execution.aggregate.AggregationIterator.generateProcessRow(AggregationIterator.scala:178)
at
org.apache.spark.sql.execution.aggregate.AggregationIterator.<init>(AggregationIterator.scala:197)
at
org.apache.spark.sql.execution.aggregate.SortBasedAggregationIterator.<init>(SortBasedAggregationIterator.scala:39)
at
org.apache.spark.sql.execution.aggregate.SortBasedAggregate$$anonfun$doExecute$1$$anonfun$3.apply(SortBasedAggregate.scala:80)
at
org.apache.spark.sql.execution.aggregate.SortBasedAggregate$$anonfun$doExecute$1$$anonfun$3.apply(SortBasedAggregate.scala:71)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$23.apply(RDD.scala:768)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$23.apply(RDD.scala:768)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:318)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:282)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:318)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:282)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:72)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:239)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$
