spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "lishuming (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (SPARK-17321) YARN shuffle service should use good disk from yarn.nodemanager.local-dirs
Date Thu, 24 Aug 2017 02:56:00 GMT

    [ https://issues.apache.org/jira/browse/SPARK-17321?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16139488#comment-16139488
] 

lishuming commented on SPARK-17321:
-----------------------------------

[~jerryshao] I agree with what you said, however there are some questions in my mind:

1. The current chosen strategy is puzzling somehow, because both `yarn.nodemanager.local-dirs`
and `NM recovery path` are available to choose to store leveldb now, so we can always pick
an available disk to store, avoiding the disk problem(https://github.com/apache/spark/pull/18905#issuecomment-323287272).

2. If as [~jerryshao] said, `yarn.nodemanager.local-dirs` should not be used whenever NM recovery
is enabled or not, am I right ?

3. Can someone check that If we don't use leveldb, ShuffleService which uses `Map` will affect
NM's memory or something else?

> YARN shuffle service should use good disk from yarn.nodemanager.local-dirs
> --------------------------------------------------------------------------
>
>                 Key: SPARK-17321
>                 URL: https://issues.apache.org/jira/browse/SPARK-17321
>             Project: Spark
>          Issue Type: Bug
>          Components: YARN
>    Affects Versions: 1.6.2, 2.0.0, 2.1.1
>            Reporter: yunjiong zhao
>
> We run spark on yarn, after enabled spark dynamic allocation, we notice some spark application
failed randomly due to YarnShuffleService.
> From log I found
> {quote}
> 2016-08-29 11:33:03,450 ERROR org.apache.spark.network.TransportContext: Error while
initializing Netty pipeline
> java.lang.NullPointerException
>         at org.apache.spark.network.server.TransportRequestHandler.<init>(TransportRequestHandler.java:77)
>         at org.apache.spark.network.TransportContext.createChannelHandler(TransportContext.java:159)
>         at org.apache.spark.network.TransportContext.initializePipeline(TransportContext.java:135)
>         at org.apache.spark.network.server.TransportServer$1.initChannel(TransportServer.java:123)
>         at org.apache.spark.network.server.TransportServer$1.initChannel(TransportServer.java:116)
>         at io.netty.channel.ChannelInitializer.channelRegistered(ChannelInitializer.java:69)
>         at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRegistered(AbstractChannelHandlerContext.java:133)
>         at io.netty.channel.AbstractChannelHandlerContext.fireChannelRegistered(AbstractChannelHandlerContext.java:119)
>         at io.netty.channel.DefaultChannelPipeline.fireChannelRegistered(DefaultChannelPipeline.java:733)
>         at io.netty.channel.AbstractChannel$AbstractUnsafe.register0(AbstractChannel.java:450)
>         at io.netty.channel.AbstractChannel$AbstractUnsafe.access$100(AbstractChannel.java:378)
>         at io.netty.channel.AbstractChannel$AbstractUnsafe$1.run(AbstractChannel.java:424)
>         at io.netty.util.concurrent.SingleThreadEventExecutor.runAllTasks(SingleThreadEventExecutor.java:357)
>         at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:357)
>         at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:111)
>         at java.lang.Thread.run(Thread.java:745)
> {quote} 
> Which caused by the first disk in yarn.nodemanager.local-dirs was broken.
> If we enabled spark.yarn.shuffle.stopOnFailure(SPARK-16505) we might lost hundred nodes
which is unacceptable.
> We have 12 disks in yarn.nodemanager.local-dirs, so why not use other good disks if the
first one is broken?



--
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


Mime
View raw message