[ https://issues.apache.org/jira/browse/SPARK-10141?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Joseph K. Bradley closed SPARK-10141. ------------------------------------- Resolution: Done > Number of tasks on executors still become negative after failures > ----------------------------------------------------------------- > > Key: SPARK-10141 > URL: https://issues.apache.org/jira/browse/SPARK-10141 > Project: Spark > Issue Type: Bug > Components: Web UI > Affects Versions: 1.5.0 > Reporter: Joseph K. Bradley > Priority: Minor > Attachments: Screen Shot 2015-08-20 at 3.14.49 PM.png > > > I hit this failure when running LDA on EC2 (after I made the model size > really big). > I was using the LDAExample.scala code on an EC2 cluster with 16 workers > (r3.2xlarge), on a Wikipedia dataset: > {code} > Training set size (documents) 4534059 > Vocabulary size (terms) 10000 > Training set size (tokens) 895575317 > EM optimizer > 1K topics > {code} > Failure message: > {code} > org.apache.spark.SparkException: Job aborted due to stage failure: Task 55 in > stage 22.0 failed 4 times, most recent failure: Lost task 55.3 in stage 22.0 > (TID 2881, 10.0.202.128): java.io.IOException: Failed to connect to > /10.0.202.128:54740 > at > org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:193) > at > org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:156) > at > org.apache.spark.network.netty.NettyBlockTransferService$$anon$1.createAndStart(NettyBlockTransferService.scala:88) > at > org.apache.spark.network.shuffle.RetryingBlockFetcher.fetchAllOutstanding(RetryingBlockFetcher.java:140) > at > org.apache.spark.network.shuffle.RetryingBlockFetcher.access$200(RetryingBlockFetcher.java:43) > at > org.apache.spark.network.shuffle.RetryingBlockFetcher$1.run(RetryingBlockFetcher.java:170) > at > java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471) > at java.util.concurrent.FutureTask.run(FutureTask.java:262) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Caused by: java.net.ConnectException: Connection refused: /10.0.202.128:54740 > at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method) > at > sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:739) > at > io.netty.channel.socket.nio.NioSocketChannel.doFinishConnect(NioSocketChannel.java:224) > at > io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:289) > at > io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:528) > at > io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:468) > at > io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:382) > at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:354) > at > io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:111) > ... 1 more > Driver stacktrace: > at > org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1267) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1255) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1254) > at > scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) > at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) > at > org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1254) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:684) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:684) > at scala.Option.foreach(Option.scala:236) > at > org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:684) > at > org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1480) > at > org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1442) > at > org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1431) > at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) > at > org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:554) > at org.apache.spark.SparkContext.runJob(SparkContext.scala:1805) > at org.apache.spark.SparkContext.runJob(SparkContext.scala:1925) > at org.apache.spark.rdd.RDD$$anonfun$fold$1.apply(RDD.scala:1059) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108) > at org.apache.spark.rdd.RDD.withScope(RDD.scala:306) > at org.apache.spark.rdd.RDD.fold(RDD.scala:1053) > at > org.apache.spark.mllib.clustering.EMLDAOptimizer.computeGlobalTopicTotals(LDAOptimizer.scala:205) > at > org.apache.spark.mllib.clustering.EMLDAOptimizer.next(LDAOptimizer.scala:192) > at > org.apache.spark.mllib.clustering.EMLDAOptimizer.next(LDAOptimizer.scala:80) > at org.apache.spark.mllib.clustering.LDA.run(LDA.scala:332) > Caused by: java.io.IOException: Failed to connect to /10.0.202.128:54740 > at > org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:193) > at > org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:156) > at > org.apache.spark.network.netty.NettyBlockTransferService$$anon$1.createAndStart(NettyBlockTransferService.scala:88) > at > org.apache.spark.network.shuffle.RetryingBlockFetcher.fetchAllOutstanding(RetryingBlockFetcher.java:140) > at > org.apache.spark.network.shuffle.RetryingBlockFetcher.access$200(RetryingBlockFetcher.java:43) > at > org.apache.spark.network.shuffle.RetryingBlockFetcher$1.run(RetryingBlockFetcher.java:170) > at > java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471) > at java.util.concurrent.FutureTask.run(FutureTask.java:262) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Caused by: java.net.ConnectException: Connection refused: /10.0.202.128:54740 > at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method) > at > sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:739) > at > io.netty.channel.socket.nio.NioSocketChannel.doFinishConnect(NioSocketChannel.java:224) > at > io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:289) > at > io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:528) > 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:111) > at java.lang.Thread.run(Thread.java:745) > {code} -- This message was sent by Atlassian JIRA (v6.3.15#6346) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org