我在Hadoop集群上运行的spark作业多次失败并出现以下错误：
com.esotericsoftware.kryo.KryoException：com.ning.compress.lzf.LZFException：损坏的输入数据，块没有以2字节签名（＆＃39; ZV＆＃39;）开头，后跟类型字节，2-字节长度）
这项工作多次成功，但也多次失败。它可能会失败几次并且下次成功使用相同的底层数据集，spark配置以及Hadoop配置。
这是堆栈跟踪。
User class threw exception: org.apache.spark.SparkException: Job aborted due to stage failure: Task 659 in stage 8.0 failed 24 times, most recent failure: Lost task 659.23 in stage 8.0 (TID 3662, atl-hdp-061.afy.gbl): com.esotericsoftware.kryo.KryoException: com.ning.compress.lzf.LZFException: Corrupt input data, block did not start with 2 byte signature ('ZV') followed by type byte, 2-byte length)
at com.esotericsoftware.kryo.io.Input.fill(Input.java:142)
at com.esotericsoftware.kryo.io.Input.require(Input.java:155)
at com.esotericsoftware.kryo.io.Input.readInt(Input.java:337)
at com.esotericsoftware.kryo.util.DefaultClassResolver.readClass(DefaultClassResolver.java:109)
at com.esotericsoftware.kryo.Kryo.readClass(Kryo.java:610)
at com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:721)
at org.apache.spark.serializer.KryoDeserializationStream.readObject(KryoSerializer.scala:228)
at org.apache.spark.serializer.DeserializationStream.readKey(Serializer.scala:169)
at org.apache.spark.serializer.DeserializationStream$$anon$2.getNext(Serializer.scala:201)
at org.apache.spark.serializer.DeserializationStream$$anon$2.getNext(Serializer.scala:198)
at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
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 org.apache.spark.util.collection.ExternalAppendOnlyMap.insertAll(ExternalAppendOnlyMap.scala:152)
at org.apache.spark.Aggregator.combineCombinersByKey(Aggregator.scala:58)
at org.apache.spark.shuffle.BlockStoreShuffleReader.read(BlockStoreShuffleReader.scala:91)
at org.apache.spark.rdd.ShuffledRDD.compute(ShuffledRDD.scala:98)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.UnionRDD.compute(UnionRDD.scala:87)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:268)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
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:89)
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: com.ning.compress.lzf.LZFException: Corrupt input data, block did not start with 2 byte signature ('ZV') followed by type byte, 2-byte length)
at com.ning.compress.lzf.ChunkDecoder._reportCorruptHeader(ChunkDecoder.java:267)
at com.ning.compress.lzf.impl.UnsafeChunkDecoder.decodeChunk(UnsafeChunkDecoder.java:55)
at com.ning.compress.lzf.LZFInputStream.readyBuffer(LZFInputStream.java:363)
at com.ning.compress.lzf.LZFInputStream.read(LZFInputStream.java:193)
at com.esotericsoftware.kryo.io.Input.fill(Input.java:140)
... 61 more