Anyone experiencing 100% CPU consumption in Netty NIO transports?

Ernesto A. eaneiros at gmail.com
Fri Aug 7 10:39:59 EDT 2009


Hello,

I don't know if it even applies in this case, but there used to be an
issue with NIO when a select() was inside a while(true) loop and, for
example, the network interface is down, select() would return
immediately with 0, the solution was to stop after 10 failed attempts.
However, if it works ok on the other OSes I think it could be an issue
with opensolaris. Just in case, check yout net interfaces :) Hope it
helps,

best regards, ernesto.

On Fri, Aug 7, 2009 at 8:56 AM, neilson9<neil at liquidlabs.co.uk> wrote:
>
> Hi Trustin,
> Im not 100% - but since porting onto OpenSolaris we are getting a CPU spin
> and the only thing we can pin it on is the NIO bug - we dont see it on
> Linux, OSX or windows platforms.
>
> We run an agent process and ensure its not doing any work and after a minute
> or so it starts to spin up on the CPU.
>
> Do you have any suggestions we could try?
>
> platform: OpenSolaris/Sunos, Java1.6_u12, Netty 3.1.0 (nightly build - just
> before GA)
>
> Regards Neil.
> Dump
> "New I/O server boss #2 (channelId: 22142166, /0.0.0.0:12004)" - Thread t at 48
>   java.lang.Thread.State: RUNNABLE
>        at sun.nio.ch.DevPollArrayWrapper.poll0(Native Method)
>        at sun.nio.ch.DevPollArrayWrapper.poll(DevPollArrayWrapper.java:164)
>        at sun.nio.ch.DevPollSelectorImpl.doSelect(DevPollSelectorImpl.java:68)
>        at sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:69)
>        - locked sun.nio.ch.Util$1 at 174b8f3
>        - locked java.util.Collections$UnmodifiableSet at 2861e0
>        - locked sun.nio.ch.DevPollSelectorImpl at 403e75
>        at sun.nio.ch.SelectorImpl.select(SelectorImpl.java:80)
>        at sun.nio.ch.ServerSocketAdaptor.accept(ServerSocketAdaptor.java:105)
>        - locked java.lang.Object at 1c49654
>        at
> org.jboss.netty.channel.socket.nio.NioServerSocketPipelineSink$Boss.run(NioServerSocketPipelineSink.java:216)
>        at
> org.jboss.netty.util.ThreadRenamingRunnable.run(ThreadRenamingRunnable.java:110)
>        at
> org.jboss.netty.util.internal.IoWorkerRunnable.run(IoWorkerRunnable.java:53)
>        at
> java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecutor.java:886)
>        at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:908)
>        at java.lang.Thread.run(Thread.java:619)
>
>   Locked ownable synchronizers:
>        - locked java.util.concurrent.locks.ReentrantLock$NonfairSync at 16990c9
>
>
> --
> View this message in context: http://n2.nabble.com/Anyone-experiencing-100--CPU-consumption-in-Netty-NIO-transports--tp3140291p3404186.html
> Sent from the Netty User Group mailing list archive at Nabble.com.
> _______________________________________________
> netty-users mailing list
> netty-users at lists.jboss.org
> https://lists.jboss.org/mailman/listinfo/netty-users
>



More information about the netty-users mailing list