[ https://issues.apache.org/jira/browse/SPARK-9943?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Davies Liu resolved SPARK-9943. ------------------------------- Resolution: Fixed Fix Version/s: 1.5.0 Issue resolved by pull request 8174 [https://github.com/apache/spark/pull/8174] > Failed to serialize a deserialized UnsafeHashedRelation > ------------------------------------------------------- > > Key: SPARK-9943 > URL: https://issues.apache.org/jira/browse/SPARK-9943 > Project: Spark > Issue Type: Bug > Components: SQL > Affects Versions: 1.5.0 > Reporter: Davies Liu > Assignee: Davies Liu > Priority: Critical > Fix For: 1.5.0 > > > When the free memory is executor go low, the cached broadcast object need to > serialized into disk, a deserialized UnsafeHashedRelation can't be serialized > , fail with NPE > {code} > 15/08/13 11:13:35 WARN TaskSetManager: Lost task 1.0 in stage 26.0 (TID 41, > 192.168.1.236): java.io.IOException: java.lang.NullPointerException > at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1163) > at > org.apache.spark.sql.execution.joins.UnsafeHashedRelation.writeExternal(HashedRelation.scala:249) > at > java.io.ObjectOutputStream.writeExternalData(ObjectOutputStream.java:1458) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1429) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177) > at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:347) > at > org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:44) > at > org.apache.spark.serializer.SerializationStream.writeAll(Serializer.scala:153) > at > org.apache.spark.storage.BlockManager.dataSerializeStream(BlockManager.scala:1190) > at > org.apache.spark.storage.DiskStore$$anonfun$putIterator$1.apply$mcV$sp(DiskStore.scala:81) > at > org.apache.spark.storage.DiskStore$$anonfun$putIterator$1.apply(DiskStore.scala:81) > at > org.apache.spark.storage.DiskStore$$anonfun$putIterator$1.apply(DiskStore.scala:81) > at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1206) > at org.apache.spark.storage.DiskStore.putIterator(DiskStore.scala:82) > at org.apache.spark.storage.DiskStore.putArray(DiskStore.scala:66) > at > org.apache.spark.storage.BlockManager.dropFromMemory(BlockManager.scala:1041) > at > org.apache.spark.storage.BlockManager.dropFromMemory(BlockManager.scala:1002) > at > org.apache.spark.storage.MemoryStore$$anonfun$ensureFreeSpace$4.apply(MemoryStore.scala:468) > at > org.apache.spark.storage.MemoryStore$$anonfun$ensureFreeSpace$4.apply(MemoryStore.scala:457) > at > scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) > at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) > at > org.apache.spark.storage.MemoryStore.ensureFreeSpace(MemoryStore.scala:457) > at > org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:292) > at > org.apache.spark.storage.MemoryStore.putIterator(MemoryStore.scala:165) > at > org.apache.spark.storage.MemoryStore.putIterator(MemoryStore.scala:143) > at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:791) > at > org.apache.spark.storage.BlockManager.putIterator(BlockManager.scala:638) > at > org.apache.spark.storage.BlockManager.putSingle(BlockManager.scala:996) > at > org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$1.apply(TorrentBroadcast.scala:182) > at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1175) > at > org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:165) > at > org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:64) > at > org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:64) > at > org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:88) > at org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70) > at > org.apache.spark.sql.execution.joins.BroadcastHashJoin$$anonfun$2.apply(BroadcastHashJoin.scala:113) > at > org.apache.spark.sql.execution.joins.BroadcastHashJoin$$anonfun$2.apply(BroadcastHashJoin.scala:112) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) > at > org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:46) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) > at > org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73) > at > org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) > at org.apache.spark.scheduler.Task.run(Task.scala:88) > at org.apache.spark.executor.Executor$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: java.lang.NullPointerException > at > org.apache.spark.sql.execution.joins.UnsafeHashedRelation$$anonfun$writeExternal$1.apply$mcV$sp(HashedRelation.scala:250) > at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1160) > ... 57 more > {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org