当我尝试将数据帧转换为 javaRDD 时出现以下异常
17/05/22 09:18:41 WARN TaskSetManager: Lost task 57.0 in stage 29.0 (TID 3985, dayrhectod011.enterprisenet.org): FetchFailed(BlockManagerId(4, dayrhectod012.enterprisenet.org, 7337), shuffleId=4, mapId=167, reduceId=57, message=
org.apache.spark.shuffle.FetchFailedException: Adjusted frame length exceeds 2147483647: 2505744379 - discarded
at org.apache.spark.storage.ShuffleBlockFetcherIterator.throwFetchFailedException(ShuffleBlockFetcherIterator.scala:321)
at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:306)
at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:51)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:173)
at org.apache.spark.sql.execution.TungstenSort.org$apache$spark$sql$execution$TungstenSort$$executePartition$1(sort.scala:160)
at org.apache.spark.sql.execution.TungstenSort$$anonfun$doExecute$4.apply(sort.scala:169)
at org.apache.spark.sql.execution.TungstenSort$$anonfun$doExecute$4.apply(sort.scala:169)
at org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:64)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:99)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: io.netty.handler.codec.TooLongFrameException: Adjusted frame length exceeds 2147483647: 2505744379 - discarded
at io.netty.handler.codec.LengthFieldBasedFrameDecoder.fail(LengthFieldBasedFrameDecoder.java:499)
at io.netty.handler.codec.LengthFieldBasedFrameDecoder.failIfNecessary(LengthFieldBasedFrameDecoder.java:477)
at io.netty.handler.codec.LengthFieldBasedFrameDecoder.decode(LengthFieldBasedFrameDecoder.java:403)
at io.netty.handler.codec.LengthFieldBasedFrameDecoder.decode(LengthFieldBasedFrameDecoder.java:343)
at io.netty.handler.codec.ByteToMessageDecoder.callDecode(ByteToMessageDecoder.java:327)
at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:230)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:846)
at io.netty.channel.nio.AbstractNioByteChannel$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)
... 1 more
)
有人可以解释一下这个问题的根本原因吗？
Spark 版本：CDH 5.5.2 中的 1.5
导致此异常的代码
DataFrame hiveDF = hc.createDataFrame(df_es_item.toJavaRDD(), df_es_item.schema());
我认为一些正确的火花配置可以解决问题，但不知道如何到达
提前致谢。