This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
Home Products Support Community News


Re: [Xen-users] Dom0 Crashes on High I/O

To: Stefan de Konink <skinkie@xxxxxxxxx>
Subject: Re: [Xen-users] Dom0 Crashes on High I/O
From: Henri Cook <henri@xxxxxxxxxxxxxxxxxxxxx>
Date: Fri, 04 Apr 2008 16:31:16 +0100
Cc: xen-users@xxxxxxxxxxxxxxxxxxx, "Ross S. W. Walker" <rwalker@xxxxxxxxxxxxx>
Delivery-date: Fri, 04 Apr 2008 08:31:46 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
In-reply-to: <13287.>
List-help: <mailto:xen-users-request@lists.xensource.com?subject=help>
List-id: Xen user discussion <xen-users.lists.xensource.com>
List-post: <mailto:xen-users@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=unsubscribe>
References: <13287.>
Sender: xen-users-bounces@xxxxxxxxxxxxxxxxxxx
User-agent: Thunderbird (X11/20080227)
I might be jinxing it by saying it - but I think that line in
sysctl.conf has done it!

The system always crashed previously when i was about 60% through the
installation file setup for WinXP - i've done that again and admittedly
the installer's not working properly (gets stuck at that 60% mark and
qemu-dm on dom0 takes up 110% of cpu (4 cpus)) but importantly DOM0

I'm going to try some other operations that crash it regularly like
creating new blank images with dd, i might even re-enable swap!

Thanks! (Hopefully!)


Stefan de Konink wrote:
>> Stefan de Konink wrote:
>>>> Unless there has been a recent radical change to Xen it isn't possible
>>> to overcommit memory like other virtualization systems.
>>> Trust me; this is totally unrelated to Xen and NFS problems were already
>>> causing this on 3.1.
>>> Reproducable with:
>>> Loopback file on NFS. Twice the size as the host ram.
>>> Now run bonnie++. In a VM.
>> So, what are you saying? What are you recommending? Is there a bug
>> filed somewhere that might apply here?
> I have mentioned it on xen-devel, and probably on bugzilla. And is one of
> the reasons to use iSCSI over NFS. Someone told me that it could be fixed
> by setting the memory overcommit for Linux to 'do not do it'. That is some
> setting in /etc/sysctl.conf
> Stefan
> ps. remove the annoying signature
> _______________________________________________
> Xen-users mailing list
> Xen-users@xxxxxxxxxxxxxxxxxxx
> http://lists.xensource.com/xen-users

Xen-users mailing list