我在一个8节点的spark集群上运行logistic回归算法,每个节点有8个内核和56gb的Ram(每个节点都运行windows系统)。spark安装驱动程序的容量为1.9 TB。我在are上训练的数据集有大约4000万条记录,有大约6600个特征。但在培训过程中,我总是会遇到这样的错误:Py4JJavaError: An error occurred while calling o70.trainLogisticRegressionModelWithLBFGS.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 2709 in stage 3.0 failed 4 times, most recent failure: Lost task 2709.3 in stage 3.0 (TID 2766, workernode0.rbaHdInsightCluster5.b6.internal.cloudapp.net): java.io.IOException: There is not enough space on the disk
at java.io.FileOutputStream.writeBytes(Native Method)
at java.io.FileOutputStream.write(FileOutputStream.java:345)
at java.io.BufferedOutputStream.write(BufferedOutputStream.java:122)
at org.xerial.snappy.SnappyOutputStream.dumpOutput(SnappyOutputStream.java:300)
at org.xerial.snappy.SnappyOutputStream.rawWrite(SnappyOutputStream.java:247)
at org.xerial.snappy.SnappyOutputStream.write(SnappyOutputStream.java:107)
at java.io.ObjectOutputStream$BlockDataOutputStream.drain(ObjectOutputStream.java:1876)
at java.io.ObjectOutputStream$BlockDataOutputStream.writeByte(ObjectOutputStream.java:1914)
at java.io.ObjectOutputStream.writeFatalException(ObjectOutputStream.java:1575)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:350)
at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:42)
at org.apache.spark.serializer.SerializationStream.writeAll(Serializer.scala:110)
at org.apache.spark.storage.BlockManager.dataSerializeStream(BlockManager.scala:1177)
at org.apache.spark.storage.DiskStore.putIterator(DiskStore.scala:78)
at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:787)
at org.apache.spark.storage.BlockManager.putIterator(BlockManager.scala:638)
at org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:145)
at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:70)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:243)
at org.apache.spark.rdd.FilteredRDD.compute(FilteredRDD.scala:34)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:278)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:245)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:200)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
at akka.actor.ActorCell.invoke(ActorCell.scala:487)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
at akka.dispatch.Mailbox.run(Mailbox.scala:220)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
代码如下:
^{pr2}$
有谁能分享一下这方面的经验吗?在