我有使用wholetextfile api读取文件的spark程序。应用程序使用1个执行程序，6GB RAM和4个核心。
当我提供几个小文件（文件总大小为3GB）时，应用程序正在成功处理所有文件。但是，如果我提供大小为2GB的单个大文件，则火花应用程序失败并出现以下错误。
无法激发2GB大小的app阅读文件？或者我是否需要更改任何内存设置？
17/06/14 21:56:22 ERROR Executor: Exception in task 0.46 in stage 0.0 (TID 46)
java.lang.OutOfMemoryError: Java heap space
at java.util.Arrays.copyOf(Arrays.java:3236)
at java.io.ByteArrayOutputStream.grow(ByteArrayOutputStream.java:118)
at java.io.ByteArrayOutputStream.ensureCapacity(ByteArrayOutputStream.java:93)
at java.io.ByteArrayOutputStream.write(ByteArrayOutputStream.java:153)
at org.spark_project.guava.io.ByteStreams.copy(ByteStreams.java:211)
at org.spark_project.guava.io.ByteStreams.toByteArray(ByteStreams.java:252)
at org.apache.spark.input.WholeTextFileRecordReader.nextKeyValue(WholeTextFileRecordReader.scala:79)
at org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader.nextKeyValue(CombineFileRecordReader.java:69)
at org.apache.spark.rdd.NewHadoopRDD$$anon$1.hasNext(NewHadoopRDD.scala:182)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:310)
at scala.collection.AbstractIterator.to(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:302)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:289)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1336)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$13.apply(RDD.scala:912)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$13.apply(RDD.scala:912)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1899)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1899)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
17/06/14 21:56:22 ERROR SparkUncaughtExceptionHandler: Uncaught exception in thread Thread[Executor task launch worker-0,5,main]