[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] dom0 hangs in xen 4.0.1-rc3-pre


  • To: Jeremy Fitzhardinge <jeremy@xxxxxxxx>
  • From: Jia Rao <rickenrao@xxxxxxxxx>
  • Date: Fri, 24 Sep 2010 17:01:08 -0400
  • Cc: xen-devel@xxxxxxxxxxxxxxxxxxx, xen-users@xxxxxxxxxxxxxxxxxxx
  • Delivery-date: Fri, 24 Sep 2010 14:02:24 -0700
  • Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; b=jSof8QO9zosl3kDDdg3zpGLMSPgVOad0yTn6Q1V68g9OvJh5y5F4xEwpW2dzSMzUTH R74HbqCzcCdQMOEDFE2ZpgQOhnoAbegE+xiyvkspQTn+MRs8cA2FCWW0KiOQwNrkeUrY CPnnwHJ5hQtHXSvfuwd/aCIEWKNA2hJMMyZPk=
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>

irqbalanced was not turned on when the server hanged.

On Fri, Sep 24, 2010 at 4:48 PM, Jia Rao <rickenrao@xxxxxxxxx> wrote:
Hi Jeremy,

The whole machine was locked. No response to ping, local VGA display.
I did not try the serial console and will let you know once I try it.

BTW. How to disable irqbalanced ?

Thank you for your reply.

On Fri, Sep 24, 2010 at 3:08 PM, Jeremy Fitzhardinge <jeremy@xxxxxxxx> wrote:
 On 09/23/2010 09:22 PM, Jia Rao wrote:
> Hi all,
>
> I saw reproducible hangs in dom0 when the system is under heavy load.
>
> Testbed settings:
> four dom0s share a nfs server for domU images. a total number of 24
> domUs (6 domUs on each dom0). When the system under heavy load, busy
> processing e-commerce requests, one or two of the dom0s hanged. no
> input can be accepted and reboot is necessary.

Is the whole machine locked solid, or does it still, for example,
respond to ping on its external interfaces, capslock works on the
keyboard (if any), console echos characters?

Does Xen still respond on the console (^A ^A ^A if you have a serial
console).

>
> Anyone had the same experience? The causes I can come up are following:
>
> 1. nfs is not configured properly. But before I upgraded to xen 4, xen
> 3 worked pretty well.
>
> 2. the domU's are using tap2 disk. Any similar problem in testing tap2?
>
> 3. Or the problem is from the new pvops kernel ? All the domU are cpu
> intensive and not generating a lot of IOs.
>
> Unfortunately, dom0's dmesg and xm log recorded nothing about the hangs.
>
> FYI:
>
> Xen: 4.0.1-rc3-pre
> dom0: centos 2.6.32.1 pvops 8G, 8 cores

Try disabling irqbalanced, which can cause lost events.

   J


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.