Below is the stacktrace for error. Please suggest. Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1283) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1271) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1270) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1270) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1496) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1447) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1824) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1837) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1850) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:215) at org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:207) at org.apache.spark.sql.hive.HiveContext$QueryExecution.stringResult(HiveContext.scala:591) at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:63) at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:308) at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376) at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:226) at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:685) at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180) at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205) at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:120) at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala) Caused by: java.io.IOException: Unable to acquire 1048576 bytes of memory at org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.acquireNewPage(UnsafeExternalSorter.java:351) at org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.<init>(UnsafeExternalSorter.java:138) at org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.create(UnsafeExternalSorter.java:106) at org.apache.spark.sql.execution.UnsafeExternalRowSorter.<init>(UnsafeExternalRowSorter.java:68) at org.apache.spark.sql.execution.TungstenSort.org$apache$spark$sql$execution$TungstenSort$$preparePartition$1(sort.scala:146) at org.apache.spark.sql.execution.TungstenSort$$anonfun$doExecute$3.apply(sort.scala:169) at org.apache.spark.sql.execution.TungstenSort$$anonfun$doExecute$3.apply(sort.scala:169) at org.apache.spark.rdd.MapPartitionsWithPreparationRDD.prepare(MapPartitionsWithPreparationRDD.scala:50) at org.apache.spark.rdd.ZippedPartitionsBaseRDD$$anonfun$tryPrepareParents$1.applyOrElse(ZippedPartitionsRDD.scala:83) at org.apache.spark.rdd.ZippedPartitionsBaseRDD$$anonfun$tryPrepareParents$1.applyOrElse(ZippedPartitionsRDD.scala:82) at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33) at scala.collection.TraversableLike$$anonfun$collect$1.apply(TraversableLike.scala:278) at scala.collection.immutable.List.foreach(List.scala:318) at scala.collection.TraversableLike$class.collect(TraversableLike.scala:278) at scala.collection.AbstractTraversable.collect(Traversable.scala:105) at org.apache.spark.rdd.ZippedPartitionsBaseRDD.tryPrepareParents(ZippedPartitionsRDD.scala:82) at org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:97) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:300) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:300) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:300) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:300) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) ... View more