Hi. I'm running Spark 1.2.0. I have HiveContext and I execute the following query:
select sum(field1 / 100) from table1 group by field2; field1 in hive metastore is a smallint. The schema detected by hivecontext is a int32: fileSchema: message schema { ............ optional int32 field1; ................ } If table1 is an unpartitioned table it works well, however, if table1 is a partitioned table it crashs in spark-submit. The error is the following: java.lang.ClassCastException: java.lang.Integer cannot be cast to java.lang.Short at scala.runtime.BoxesRunTime.unboxToShort(BoxesRunTime.java:102) at scala.math.Numeric$ShortIsIntegral$.toInt(Numeric.scala:72) at org.apache.spark.sql.catalyst.expressions.Cast$$anonfun$castToInt$6.apply(Cast.scala:234) at org.apache.spark.sql.catalyst.expressions.Cast$$anonfun$castToInt$6.apply(Cast.scala:234) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:366) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Expression.f1(Expression.scala:162) at org.apache.spark.sql.catalyst.expressions.Divide.eval(arithmetic.scala:115) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:109) at org.apache.spark.sql.catalyst.expressions.Add.eval(arithmetic.scala:90) at org.apache.spark.sql.catalyst.expressions.Coalesce.eval(nullFunctions.scala:50) at org.apache.spark.sql.catalyst.expressions.MutableLiteral.update(literals.scala:72) at org.apache.spark.sql.catalyst.expressions.SumFunction.update(aggregates.scala:526) at org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:167) at org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:151) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263) at org.apache.spark.rdd.RDD.iterator(RDD.scala:230) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263) at org.apache.spark.rdd.RDD.iterator(RDD.scala:230) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:56) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 15/03/17 10:42:51 ERROR Executor: Exception in task 1.0 in stage 3.0 (TID 5) java.lang.ClassCastException: java.lang.Integer cannot be cast to java.lang.Short at scala.runtime.BoxesRunTime.unboxToShort(BoxesRunTime.java:102) at scala.math.Numeric$ShortIsIntegral$.toInt(Numeric.scala:72) at org.apache.spark.sql.catalyst.expressions.Cast$$anonfun$castToInt$6.apply(Cast.scala:234) at org.apache.spark.sql.catalyst.expressions.Cast$$anonfun$castToInt$6.apply(Cast.scala:234) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:366) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Expression.f1(Expression.scala:162) at org.apache.spark.sql.catalyst.expressions.Divide.eval(arithmetic.scala:115) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:109) at org.apache.spark.sql.catalyst.expressions.Add.eval(arithmetic.scala:90) at org.apache.spark.sql.catalyst.expressions.Coalesce.eval(nullFunctions.scala:50) at org.apache.spark.sql.catalyst.expressions.MutableLiteral.update(literals.scala:72) at org.apache.spark.sql.catalyst.expressions.SumFunction.update(aggregates.scala:526) at org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:167) at org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:151) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263) at org.apache.spark.rdd.RDD.iterator(RDD.scala:230) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263) at org.apache.spark.rdd.RDD.iterator(RDD.scala:230) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:56) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 15/03/17 10:42:51 INFO TaskSetManager: Starting task 2.0 in stage 3.0 (TID 6, localhost, PROCESS_LOCAL, 1527 bytes) 15/03/17 10:42:51 INFO TaskSetManager: Starting task 3.0 in stage 3.0 (TID 7, localhost, PROCESS_LOCAL, 1527 bytes) 15/03/17 10:42:51 INFO Executor: Running task 3.0 in stage 3.0 (TID 7) 15/03/17 10:42:51 INFO Executor: Running task 2.0 in stage 3.0 (TID 6) 15/03/17 10:42:51 WARN TaskSetManager: Lost task 0.0 in stage 3.0 (TID 4, localhost): java.lang.ClassCastException: java.lang.Integer cannot be cast to java.lang.Short at scala.runtime.BoxesRunTime.unboxToShort(BoxesRunTime.java:102) at scala.math.Numeric$ShortIsIntegral$.toInt(Numeric.scala:72) at org.apache.spark.sql.catalyst.expressions.Cast$$anonfun$castToInt$6.apply(Cast.scala:234) at org.apache.spark.sql.catalyst.expressions.Cast$$anonfun$castToInt$6.apply(Cast.scala:234) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:366) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Expression.f1(Expression.scala:162) at org.apache.spark.sql.catalyst.expressions.Divide.eval(arithmetic.scala:115) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:109) at org.apache.spark.sql.catalyst.expressions.Add.eval(arithmetic.scala:90) at org.apache.spark.sql.catalyst.expressions.Coalesce.eval(nullFunctions.scala:50) at org.apache.spark.sql.catalyst.expressions.MutableLiteral.update(literals.scala:72) at org.apache.spark.sql.catalyst.expressions.SumFunction.update(aggregates.scala:526) at org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:167) at org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:151) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263) at org.apache.spark.rdd.RDD.iterator(RDD.scala:230) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263) at org.apache.spark.rdd.RDD.iterator(RDD.scala:230) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:56) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 15/03/17 10:42:51 ERROR TaskSetManager: Task 0 in stage 3.0 failed 1 times; aborting job 15/03/17 10:42:51 INFO TaskSetManager: Lost task 1.0 in stage 3.0 (TID 5) on executor localhost: java.lang.ClassCastException (java.lang.Integer cannot be cast to java.lang.Short) [duplicate 1] 15/03/17 10:42:51 INFO TaskSchedulerImpl: Cancelling stage 3 15/03/17 10:42:51 INFO ShuffleBlockFetcherIterator: Getting 1 non-empty blocks out of 1 blocks 15/03/17 10:42:51 INFO ShuffleBlockFetcherIterator: Started 0 remote fetches in 3 ms 15/03/17 10:42:51 INFO ShuffleBlockFetcherIterator: Getting 1 non-empty blocks out of 1 blocks 15/03/17 10:42:51 INFO ShuffleBlockFetcherIterator: Started 0 remote fetches in 0 ms 15/03/17 10:42:51 INFO Executor: Executor is trying to kill task 2.0 in stage 3.0 (TID 6) 15/03/17 10:42:51 INFO Executor: Executor is trying to kill task 3.0 in stage 3.0 (TID 7) 15/03/17 10:42:51 INFO ShuffleBlockFetcherIterator: Getting 1 non-empty blocks out of 1 blocks 15/03/17 10:42:51 INFO ShuffleBlockFetcherIterator: Started 0 remote fetches in 1 ms 15/03/17 10:42:51 INFO ShuffleBlockFetcherIterator: Getting 1 non-empty blocks out of 1 blocks 15/03/17 10:42:51 INFO ShuffleBlockFetcherIterator: Started 0 remote fetches in 0 ms 15/03/17 10:42:51 INFO Executor: Executor killed task 2.0 in stage 3.0 (TID 6) 15/03/17 10:42:51 INFO Executor: Executor killed task 3.0 in stage 3.0 (TID 7) 15/03/17 10:42:51 INFO TaskSchedulerImpl: Stage 3 was cancelled 15/03/17 10:42:51 INFO DAGScheduler: Job 1 failed: runJob at basicOperators.scala:141, took 2.912831 s Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 3.0 failed 1 times, most recent failure: Lost task 0.0 in stage 3.0 (TID 4, localhost): java.lang.ClassCastException: java.lang.Integer cannot be cast to java.lang.Short at scala.runtime.BoxesRunTime.unboxToShort(BoxesRunTime.java:102) at scala.math.Numeric$ShortIsIntegral$.toInt(Numeric.scala:72) at org.apache.spark.sql.catalyst.expressions.Cast$$anonfun$castToInt$6.apply(Cast.scala:234) at org.apache.spark.sql.catalyst.expressions.Cast$$anonfun$castToInt$6.apply(Cast.scala:234) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:366) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Expression.f1(Expression.scala:162) at org.apache.spark.sql.catalyst.expressions.Divide.eval(arithmetic.scala:115) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:365) at org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:109) at org.apache.spark.sql.catalyst.expressions.Add.eval(arithmetic.scala:90) at org.apache.spark.sql.catalyst.expressions.Coalesce.eval(nullFunctions.scala:50) at org.apache.spark.sql.catalyst.expressions.MutableLiteral.update(literals.scala:72) at org.apache.spark.sql.catalyst.expressions.SumFunction.update(aggregates.scala:526) at org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:167) at org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:151) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263) at org.apache.spark.rdd.RDD.iterator(RDD.scala:230) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263) at org.apache.spark.rdd.RDD.iterator(RDD.scala:230) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:56) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org $apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696) at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420) at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498) at akka.actor.ActorCell.invoke(ActorCell.scala:456) at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237) at akka.dispatch.Mailbox.run(Mailbox.scala:219) at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386) at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339) at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107) 15/03/17 10:42:51 WARN TaskSetManager: Lost task 2.0 in stage 3.0 (TID 6, localhost): TaskKilled (killed intentionally) 15/03/17 10:42:51 WARN TaskSetManager: Lost task 3.0 in stage 3.0 (TID 7, localhost): TaskKilled (killed intentionally) 15/03/17 10:42:51 INFO TaskSchedulerImpl: Removed TaskSet 3.0, whose tasks have all completed, from pool Thanks!!!!!! -- Regards. Miguel Angel Sotomayor