What operation are you doing? I'm assuming you have enabled rdd compression and you are having an empty stream which it tries to uncompress (as seen from the Exceptions)
Thanks Best Regards On Fri, Mar 27, 2015 at 7:15 AM, Chen Song <chen.song...@gmail.com> wrote: > Using spark 1.3.0 on cdh5.1.0, I was running a fetch failed exception. > > I searched in this email list but not found anything like this reported. > What could be the reason for the error? > > org.apache.spark.shuffle.FetchFailedException: [EMPTY_INPUT] Cannot > decompress empty stream > at > org.apache.spark.shuffle.hash.BlockStoreShuffleFetcher$.org$apache$spark$shuffle$hash$BlockStoreShuffleFetcher$$unpackBlock$1(BlockStoreShuffleFetcher.scala:67) > at > org.apache.spark.shuffle.hash.BlockStoreShuffleFetcher$$anonfun$3.apply(BlockStoreShuffleFetcher.scala:83) > at > org.apache.spark.shuffle.hash.BlockStoreShuffleFetcher$$anonfun$3.apply(BlockStoreShuffleFetcher.scala:83) > at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371) > at > org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32) > at > org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39) > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) > at > org.apache.spark.util.collection.ExternalAppendOnlyMap.insertAll(ExternalAppendOnlyMap.scala:125) > at > org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$5.apply(CoGroupedRDD.scala:160) > at > org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$5.apply(CoGroupedRDD.scala:159) > at > scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772) > at > scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) > at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) > at > scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771) > at org.apache.spark.rdd.CoGroupedRDD.compute(CoGroupedRDD.scala:159) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$2.apply(CoGroupedRDD.scala:130) > at > org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$2.apply(CoGroupedRDD.scala:127) > at > scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772) > at > scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) > at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) > at > scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771) > at org.apache.spark.rdd.CoGroupedRDD.compute(CoGroupedRDD.scala:127) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61) > at org.apache.spark.scheduler.Task.run(Task.scala:64) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:203) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Caused by: org.xerial.snappy.SnappyIOException: [EMPTY_INPUT] Cannot > decompress empty stream > at > org.xerial.snappy.SnappyInputStream.readHeader(SnappyInputStream.java:88) > at org.xerial.snappy.SnappyInputStream.<init>(SnappyInputStream.java:58) > at > org.apache.spark.io.SnappyCompressionCodec.compressedInputStream(CompressionCodec.scala:160) > at > org.apache.spark.storage.BlockManager.wrapForCompression(BlockManager.scala:1165) > at > org.apache.spark.storage.ShuffleBlockFetcherIterator$$anonfun$4.apply(ShuffleBlockFetcherIterator.scala:301) > at > org.apache.spark.storage.ShuffleBlockFetcherIterator$$anonfun$4.apply(ShuffleBlockFetcherIterator.scala:300) > at scala.util.Success$$anonfun$map$1.apply(Try.scala:206) > at scala.util.Try$.apply(Try.scala:161) > at scala.util.Success.map(Try.scala:206) > at > org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:300) > at > org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:53) > ... 60 more > > > ---- > > Chen >