Hi
My Spark is 1.1.0 and Hive is 0.12, I tried to run the same query in both
Hive-0.12.0 then Spark-1.1.0, HiveQL works while SparkSQL failed.
hive> select l_orderkey, sum(l_extendedprice*(1-l_discount)) as revenue,
o_orderdate, o_shippriority from customer c join orders o on c.c_mktsegment =
'BUILDING' and c.c_custkey = o.o_custkey join lineitem l on l.l_orderkey =
o.o_orderkey where o_orderdate < '1995-03-15' and l_shipdate > '1995-03-15'
group by l_orderkey, o_orderdate, o_shippriority order by revenue desc,
o_orderdate limit 10;
Ended Job = job_1414067367860_0011
MapReduce Jobs Launched:
Job 0: Map: 1 Reduce: 1 Cumulative CPU: 2.0 sec HDFS Read: 261 HDFS Write:
96 SUCCESS
Job 1: Map: 1 Reduce: 1 Cumulative CPU: 0.88 sec HDFS Read: 458 HDFS
Write: 0 SUCCESS
Total MapReduce CPU Time Spent: 2 seconds 880 msec
OK
Time taken: 38.771 seconds
scala> sqlContext.sql("""select l_orderkey, sum(l_extendedprice*(1-l_discount))
as revenue, o_orderdate, o_shippriority from customer c join orders o on
c.c_mktsegment = 'BUILDING' and c.c_custkey = o.o_custkey join lineitem l on
l.l_orderkey = o.o_orderkey where o_orderdate < '1995-03-15' and l_shipdate >
'1995-03-15' group by l_orderkey, o_orderdate, o_shippriority order by revenue
desc, o_orderdate limit 10""").collect().foreach(println);
org.apache.spark.SparkException: Job aborted due to stage failure: Task 14 in
stage 5.0 failed 4 times, most recent failure: Lost task 14.3 in stage 5.0 (TID
568, m34): java.lang.ClassCastException: java.lang.String cannot be cast to
scala.math.BigDecimal
scala.math.Numeric$BigDecimalIsFractional$.minus(Numeric.scala:182)
org.apache.spark.sql.catalyst.expressions.Subtract$$anonfun$eval$3.apply(arithmetic.scala:64)
org.apache.spark.sql.catalyst.expressions.Subtract$$anonfun$eval$3.apply(arithmetic.scala:64)
org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:114)
org.apache.spark.sql.catalyst.expressions.Subtract.eval(arithmetic.scala:64)
org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:108)
org.apache.spark.sql.catalyst.expressions.Multiply.eval(arithmetic.scala:70)
org.apache.spark.sql.catalyst.expressions.Coalesce.eval(nullFunctions.scala:47)
org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:108)
org.apache.spark.sql.catalyst.expressions.Add.eval(arithmetic.scala:58)
org.apache.spark.sql.catalyst.expressions.MutableLiteral.update(literals.scala:69)
org.apache.spark.sql.catalyst.expressions.SumFunction.update(aggregates.scala:433)
org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:167)
org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:151)
org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596)
org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1185)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1174)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1173)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1173)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:688)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1391)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at
akka.dispatch.ForkJoinExecutorConfigurator$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)
Regards
Arthur