我有一个PySpark程序，它在大量记录上进行相当简单的数据转换。我偶尔会得到以下错误。我添加了代码以确保我写的IntegerType值都不在正常的32位整数值范围之外。这个超出范围的整数似乎是一些内部值，而不是我传入的内容。
这发生在简单的计数调用上。触发此错误的Python行非常简单：
data_frame_count = data_frame.count()
我在Amazon EMR 5.0下的Spark 2.0上运行它。
我已经对此错误进行了搜索。我看到另一个专注于更好的逻辑回归处理的对话线程。在这里，我正在做，非常简单，加载数据，基本解析/清理数据，以及写出数据。
Caused by: java.lang.RuntimeException: java.lang.IllegalArgumentException: Size exceeds Integer.MAX_VALUE
at sun.nio.ch.FileChannelImpl.map(FileChannelImpl.java:869)
at org.apache.spark.storage.DiskStore$$anonfun$getBytes$2.apply(DiskStore.scala:103)
at org.apache.spark.storage.DiskStore$$anonfun$getBytes$2.apply(DiskStore.scala:91)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1287)
at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:105)
at org.apache.spark.storage.BlockManager.org$apache$spark$storage$BlockManager$$doGetLocalBytes(BlockManager.scala:497)
at org.apache.spark.storage.BlockManager$$anonfun$getLocalBytes$2.apply(BlockManager.scala:475)
at org.apache.spark.storage.BlockManager$$anonfun$getLocalBytes$2.apply(BlockManager.scala:475)
at scala.Option.map(Option.scala:146)
at org.apache.spark.storage.BlockManager.getLocalBytes(BlockManager.scala:475)
at org.apache.spark.storage.BlockManager.getBlockData(BlockManager.scala:280)
at org.apache.spark.network.netty.NettyBlockRpcServer$$anonfun$2.apply(NettyBlockRpcServer.scala:60)
at org.apache.spark.network.netty.NettyBlockRpcServer$$anonfun$2.apply(NettyBlockRpcServer.scala:60)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
at org.apache.spark.network.netty.NettyBlockRpcServer.receive(NettyBlockRpcServer.scala:60)
at org.apache.spark.network.server.TransportRequestHandler.processRpcRequest(TransportRequestHandler.java:158)
at org.apache.spark.network.server.TransportRequestHandler.handle(TransportRequestHandler.java:106)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:119)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:51)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:266)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:103)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at org.apache.spark.network.util.TransportFrameDecoder.channelRead(TransportFrameDecoder.java:85)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:846)
at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:131)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:511)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:468)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:382)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:354)
at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:111)
at java.lang.Thread.run(Thread.java:745)