You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Apache Spark (JIRA)" <ji...@apache.org> on 2017/06/29 10:57:00 UTC
[jira] [Assigned] (SPARK-21253) Cannot fetch big blocks to disk
[ https://issues.apache.org/jira/browse/SPARK-21253?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Apache Spark reassigned SPARK-21253:
------------------------------------
Assignee: Apache Spark
> Cannot fetch big blocks to disk
> --------------------------------
>
> Key: SPARK-21253
> URL: https://issues.apache.org/jira/browse/SPARK-21253
> Project: Spark
> Issue Type: Bug
> Components: Spark Core
> Affects Versions: 2.2.0
> Reporter: Yuming Wang
> Assignee: Apache Spark
>
> Spark *cluster* can reproduce, *local* can't:
> 1. Start a spark context with {{spark.reducer.maxReqSizeShuffleToMem=1K}}:
> {code:actionscript}
> $ spark-shell --conf spark.reducer.maxReqSizeShuffleToMem=1K
> {code}
> 2. Need a shuffe:
> {code:actionscript}
> scala> val count = sc.parallelize(0 until 3000000, 10).repartition(2001).collect().length
> {code}
> The error messages:
> {noformat}
> org.apache.spark.shuffle.FetchFailedException: Failed to send request for 1649611690367_2 to yhd-jqhadoop166.int.yihaodian.com/10.17.28.166:7337: java.io.IOException: Connection reset by peer
> at org.apache.spark.storage.ShuffleBlockFetcherIterator.throwFetchFailedException(ShuffleBlockFetcherIterator.scala:442)
> at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:418)
> at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:59)
> at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
> at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
> at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
> at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
> at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:438)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
> at scala.collection.Iterator$class.foreach(Iterator.scala:893)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:310)
> at scala.collection.AbstractIterator.to(Iterator.scala:1336)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:302)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1336)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:289)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1336)
> at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$13.apply(RDD.scala:936)
> at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$13.apply(RDD.scala:936)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2062)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2062)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
> at org.apache.spark.scheduler.Task.run(Task.scala:108)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.io.IOException: Failed to send request for 1649611690367_2 to yhd-jqhadoop166.int.yihaodian.com/10.17.28.166:7337: java.io.IOException: Connection reset by peer
> at org.apache.spark.network.client.TransportClient.lambda$stream$1(TransportClient.java:196)
> at io.netty.util.concurrent.DefaultPromise.notifyListener0(DefaultPromise.java:507)
> at io.netty.util.concurrent.DefaultPromise.notifyListenersNow(DefaultPromise.java:481)
> at io.netty.util.concurrent.DefaultPromise.notifyListeners(DefaultPromise.java:420)
> at io.netty.util.concurrent.DefaultPromise.addListener(DefaultPromise.java:163)
> at io.netty.channel.DefaultChannelPromise.addListener(DefaultChannelPromise.java:93)
> at io.netty.channel.DefaultChannelPromise.addListener(DefaultChannelPromise.java:28)
> at org.apache.spark.network.client.TransportClient.stream(TransportClient.java:183)
> at org.apache.spark.network.shuffle.OneForOneBlockFetcher$1.onSuccess(OneForOneBlockFetcher.java:123)
> at org.apache.spark.network.client.TransportResponseHandler.handle(TransportResponseHandler.java:176)
> at org.apache.spark.network.server.TransportChannelHandler.channelRead(TransportChannelHandler.java:120)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
> at io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:287)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
> at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:102)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
> at org.apache.spark.network.util.TransportFrameDecoder.channelRead(TransportFrameDecoder.java:85)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
> at io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1294)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
> at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:911)
> at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:131)
> at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:643)
> at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:566)
> at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:480)
> at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:442)
> at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:131)
> at io.netty.util.concurrent.DefaultThreadFactory$DefaultRunnableDecorator.run(DefaultThreadFactory.java:144)
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org