hadoop for spark：增加分区数
hadoop for spark: Increase number of partitions
每次尝试使用 hadoop-2.6.0-for-spark 连接器加载巨大的 elasticsearch 索引时，我都会遇到错误。
是 运行 纱线上的火花。
15/09/30 17:57:21 ERROR shuffle.OneForOneBlockFetcher: Failed while starting block fetches
java.lang.RuntimeException: java.lang.IllegalArgumentException: Size exceeds Integer.MAX_VALUE
at sun.nio.ch.FileChannelImpl.map(FileChannelImpl.java:836)
at org.apache.spark.storage.DiskStore$$anonfun$getBytes.apply(DiskStore.scala:125)
at org.apache.spark.storage.DiskStore$$anonfun$getBytes.apply(DiskStore.scala:113)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1206)
at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:127)
at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:134)
at org.apache.spark.storage.BlockManager.doGetLocal(BlockManager.scala:512)
at org.apache.spark.storage.BlockManager.getBlockData(BlockManager.scala:302)
at org.apache.spark.network.netty.NettyBlockRpcServer$$anonfun.apply(NettyBlockRpcServer.scala:57)
at org.apache.spark.network.netty.NettyBlockRpcServer$$anonfun.apply(NettyBlockRpcServer.scala:57)
at scala.collection.TraversableLike$$anonfun$map.apply(TraversableLike.scala:244)
at scala.collection.TraversableLike$$anonfun$map.apply(TraversableLike.scala:244)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at org.apache.spark.network.netty.NettyBlockRpcServer.receive(NettyBlockRpcServer.scala:57)
at org.apache.spark.network.server.TransportRequestHandler.processRpcRequest(TransportRequestHandler.java:114)
at org.apache.spark.network.server.TransportRequestHandler.handle(TransportRequestHandler.java:87)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:101)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:51)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:266)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:103)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:244)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:846)
at io.netty.channel.nio.AbstractNioByteChannel$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.run(SingleThreadEventExecutor.java:111)
at java.lang.Thread.run(Thread.java:745)
at org.apache.spark.network.client.TransportResponseHandler.handle(TransportResponseHandler.java:162)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:103)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:51)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
到目前为止，我看到的解决方案是增加分区的数量，但我如何使用 hadoop-2.6.0-for-spark 做到这一点。
有什么想法吗？
我终于通过增加执行程序内存解决了这个问题，似乎在尝试将 RDD 缓存到磁盘时由于缓存到磁盘的块的大小而抛出异常。
每次尝试使用 hadoop-2.6.0-for-spark 连接器加载巨大的 elasticsearch 索引时，我都会遇到错误。
是 运行 纱线上的火花。
15/09/30 17:57:21 ERROR shuffle.OneForOneBlockFetcher: Failed while starting block fetches
java.lang.RuntimeException: java.lang.IllegalArgumentException: Size exceeds Integer.MAX_VALUE
at sun.nio.ch.FileChannelImpl.map(FileChannelImpl.java:836)
at org.apache.spark.storage.DiskStore$$anonfun$getBytes.apply(DiskStore.scala:125)
at org.apache.spark.storage.DiskStore$$anonfun$getBytes.apply(DiskStore.scala:113)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1206)
at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:127)
at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:134)
at org.apache.spark.storage.BlockManager.doGetLocal(BlockManager.scala:512)
at org.apache.spark.storage.BlockManager.getBlockData(BlockManager.scala:302)
at org.apache.spark.network.netty.NettyBlockRpcServer$$anonfun.apply(NettyBlockRpcServer.scala:57)
at org.apache.spark.network.netty.NettyBlockRpcServer$$anonfun.apply(NettyBlockRpcServer.scala:57)
at scala.collection.TraversableLike$$anonfun$map.apply(TraversableLike.scala:244)
at scala.collection.TraversableLike$$anonfun$map.apply(TraversableLike.scala:244)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at org.apache.spark.network.netty.NettyBlockRpcServer.receive(NettyBlockRpcServer.scala:57)
at org.apache.spark.network.server.TransportRequestHandler.processRpcRequest(TransportRequestHandler.java:114)
at org.apache.spark.network.server.TransportRequestHandler.handle(TransportRequestHandler.java:87)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:101)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:51)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:266)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:103)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:244)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:846)
at io.netty.channel.nio.AbstractNioByteChannel$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.run(SingleThreadEventExecutor.java:111)
at java.lang.Thread.run(Thread.java:745)
at org.apache.spark.network.client.TransportResponseHandler.handle(TransportResponseHandler.java:162)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:103)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:51)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
到目前为止，我看到的解决方案是增加分区的数量，但我如何使用 hadoop-2.6.0-for-spark 做到这一点。
有什么想法吗？
我终于通过增加执行程序内存解决了这个问题，似乎在尝试将 RDD 缓存到磁盘时由于缓存到磁盘的块的大小而抛出异常。