Re: [Xen-users] Report of "soft lockup" for a domU when paused and unpaused

["john maclean" <jayeola@xxxxxxxxx>]

Hey chaps,

I'm having **more** of these soft lockup warnings. This time around I
start domUs with no network, (mainly for testing scripts). They all
get very slooooow. Take about 10 seconds to echo key presses and after
a minute they flood the terminal with the " soft lockup detected on
CPU#0!" warnings. I'd love to able to work this out myself so that I
can fix things...
[1] Would looking at /boot/System.map-2.6.16-xen help me at all?
[2]google is a very big *vserse and it's very easy to get
lost,sidetracke and distracted. What files in /var/log/can i use to
examine these errors?
[3] Anything in proc?
[4] Is this a call for *shudder* the devel list?

On 19/10/06, Tim Post <tim.post@xxxxxxxxxxxxxxx> wrote:
> I've gotten that on my Desktop (which currently runs xen 3.0.2)
>
> Dom-0 is my desktop, KDE/Gnome with no dom0_maxmem set, I just let it
> balloon as I bring up guests.
>
> My lab VM's are file backed VBD's also (including swap). I see those
> messages a few times a week but have yet to pin anything of any kind of
> serious consequence on them. I've just been logging when I see them and
> ignoring the messages otherwise.
>
> Since this doesn't happen on a similar machine using partition backed
> VBD's for swap, my guess is it has something to do with the host having
> to write to a few dom-u file systems as they're swapping too, when all
> use loops it happens.
>
> Anyone else shed some light on why? I'm not really concerned about it,
> but I'd love to be able to explain it.
>
> Best,
> -Tim
>
> On Thu, 2006-10-19 at 01:12 +0100, john maclean wrote:
> > This is a message from within the domU "etch_play", based on Debian
> > Etch. I have a number of foo_play templates that I experiment with.
> >
> > It is a file-based image filled with packages using Debian's
> > debootstrap. The domU was idling away not doing anything at all and I
> > ran `xm pause <domu id>` and unpaused it after five minutes or so. I'd
> > love to learn *myself* how to trace/debug this error but in the
> > meantime can any one tell me if this unusual or serious? Let me know
> > if there's any more info required as I'd rather not flood this list
> > with over enthusiastic data.
> >
> > etch_play:~# BUG: soft lockup detected on CPU#0!
> >
> > Pid: 0, comm:              swapper
> > EIP: 0061:[<c01013a7>] CPU: 0
> > EIP is at 0xc01013a7
> >   EFLAGS: 00000246    Tainted: GF      (2.6.16-xen #1)
> >   EAX: 00000000 EBX: 00000001 ECX: 00000000 EDX: 00000001
> >   ESI: 00000000 EDI: c03c0000 EBP: 00000000 DS: 007b ES: 007b
> >  CR0: 8005003b CR2: b7f73ef0 CR3: 003e4000 CR4: 00000640
> >  [<c010301a>] xen_idle+0x4a/0xb0
> >  [<c03c2260>] unknown_bootoption+0x0/0x280
> >  [<c03c2260>] unknown_bootoption+0x0/0x280
> >  [<c0103194>] cpu_idle+0x74/0xf0
> >  [<c03c2260>] unknown_bootoption+0x0/0x280
> >  [<c03c2808>] start_kernel+0x328/0x3e0
> >  [<c03c2260>] unknown_bootoption+0x0/0x280
> >
> >

--
John Maclean  - 07739 171 531
MSc (DIC)

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