[SPARK-17321] YARN shuffle service should use good disk from yarn.nodemanager.local-dirs

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 1.6.2, 2.0.0, 2.1.1
• Fix Version/s: 2.3.0
• Component/s: Spark Core, YARN
• Assignee: Saisai Shao
• Reporter: yunjiong zhao
• Created: 30/Aug/16 22:38
• Updated: 17/May/20 18:13
• Resolved: 31/Aug/17 01:27

Description

We run spark on yarn, after enabled spark dynamic allocation, we notice some spark application failed randomly due to YarnShuffleService.
From log I found

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)

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?

Issue Links

• is duplicated by: SPARK-21660 Yarn ShuffleService failed to start when the chosen directory become read-only
• links to: [Github] Pull Request #14887 (zhaoyunjiong)
• links to: [Github] Pull Request #19032 (jerryshao)
• links to: [Github] Pull Request #19032 (jerryshao)