You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@spark.apache.org by Peng Xia <sp...@gmail.com> on 2015/03/09 20:54:21 UTC
error on training with logistic regression sgd
Hi,
I was launching a spark cluster with 4 work nodes, each work nodes contains
8 cores and 56gb ram, and I was testing my logistic regression problem.
The training set is around 1.2 million records.When I was using 2**10
(1024) features, the whole program works fine, but when I use 2**14
features, the program has encountered the error:
Py4JJavaError: An error occurred while calling
o84.trainLogisticRegressionModelWithSGD.
: org.apache.spark.SparkException: Job aborted due to stage failure:
Task 1 in stage 4.0 failed 4 times, most recent failure: Lost task 1.3
in stage 4.0 (TID 9,
workernode0.sparkexperience4a7.d5.internal.cloudapp.net):
java.lang.RuntimeException: java.lang.IllegalArgumentException: Size
exceeds Integer.MAX_VALUE
at sun.nio.ch.FileChannelImpl.map(FileChannelImpl.java:828)
at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:123)
at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:132)
at org.apache.spark.storage.BlockManager.doGetLocal(BlockManager.scala:517)
at org.apache.spark.storage.BlockManager.getBlockData(BlockManager.scala:307)
at org.apache.spark.network.netty.NettyBlockRpcServer$$anonfun$2.apply(NettyBlockRpcServer.scala:57)
at org.apache.spark.network.netty.NettyBlockRpcServer$$anonfun$2.apply(NettyBlockRpcServer.scala:57)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at org.apache.spark.network.netty.NettyBlockRpcServer.receive(NettyBlockRpcServer.scala:57)
at org.apache.spark.network.server.TransportRequestHandler.processRpcRequest(TransportRequestHandler.java:124)
at org.apache.spark.network.server.TransportRequestHandler.handle(TransportRequestHandler.java:97)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:91)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:44)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:103)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:163)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:787)
at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:130)
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$2.run(SingleThreadEventExecutor.java:116)
at java.lang.Thread.run(Thread.java:745)
at org.apache.spark.network.client.TransportResponseHandler.handle(TransportResponseHandler.java:156)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:93)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:44)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:103)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:163)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:787)
at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:130)
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$2.run(SingleThreadEventExecutor.java:116)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$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)
The data are transformed to LabeledPoint and I was using pyspark for this.
Can anyone help me on this?
Thanks,
Best,
Peng
Re: error on training with logistic regression sgd
Posted by Peng Xia <sp...@gmail.com>.
Hi,
Can anyone give an idea about this?
Just did some google search, it seems related to the 2gb limitation on
block size, https://issues.apache.org/jira/browse/SPARK-1476.
The whole process is that:
1. load the data
2. convert each line of data into labeled points using some feature hashing
algorithm in python.
3. train a logistic regression model with the converted labeled points.
Can any one give some advice for how to avoid the 2gb, if this is the cause?
Thanks very much for the help.
Best,
Peng
On Mon, Mar 9, 2015 at 3:54 PM, Peng Xia <sp...@gmail.com> wrote:
> Hi,
>
> I was launching a spark cluster with 4 work nodes, each work nodes
> contains 8 cores and 56gb ram, and I was testing my logistic regression
> problem.
> The training set is around 1.2 million records.When I was using 2**10
> (1024) features, the whole program works fine, but when I use 2**14
> features, the program has encountered the error:
>
> Py4JJavaError: An error occurred while calling o84.trainLogisticRegressionModelWithSGD.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 4.0 failed 4 times, most recent failure: Lost task 1.3 in stage 4.0 (TID 9, workernode0.sparkexperience4a7.d5.internal.cloudapp.net): java.lang.RuntimeException: java.lang.IllegalArgumentException: Size exceeds Integer.MAX_VALUE
> at sun.nio.ch.FileChannelImpl.map(FileChannelImpl.java:828)
> at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:123)
> at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:132)
> at org.apache.spark.storage.BlockManager.doGetLocal(BlockManager.scala:517)
> at org.apache.spark.storage.BlockManager.getBlockData(BlockManager.scala:307)
> at org.apache.spark.network.netty.NettyBlockRpcServer$$anonfun$2.apply(NettyBlockRpcServer.scala:57)
> at org.apache.spark.network.netty.NettyBlockRpcServer$$anonfun$2.apply(NettyBlockRpcServer.scala:57)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
> at org.apache.spark.network.netty.NettyBlockRpcServer.receive(NettyBlockRpcServer.scala:57)
> at org.apache.spark.network.server.TransportRequestHandler.processRpcRequest(TransportRequestHandler.java:124)
> at org.apache.spark.network.server.TransportRequestHandler.handle(TransportRequestHandler.java:97)
> at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:91)
> at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:44)
> at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
> at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:103)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
> at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:163)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
> at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:787)
> at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:130)
> 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$2.run(SingleThreadEventExecutor.java:116)
> at java.lang.Thread.run(Thread.java:745)
>
> at org.apache.spark.network.client.TransportResponseHandler.handle(TransportResponseHandler.java:156)
> at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:93)
> at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:44)
> at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
> at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:103)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
> at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:163)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
> at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:787)
> at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:130)
> 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$2.run(SingleThreadEventExecutor.java:116)
> at java.lang.Thread.run(Thread.java:745)
>
> Driver stacktrace:
> at org.apache.spark.scheduler.DAGScheduler.org$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)
>
>
>
> The data are transformed to LabeledPoint and I was using pyspark for this.
> Can anyone help me on this?
>
>
> Thanks,
> Best,
> Peng
>
>
>