2006/1/11, Herbert Poetzl <herbert@13thfloor.at>:
> On Wed, Jan 11, 2006 at 09:01:31PM +0100, Grzegorz Nosek wrote:
> > Hello all,
> >
> > I'm writing to report a crash with the kernel mentioned in the
> > subject. Relevant netconsole output follows:
> >
> > Jan 11 20:41:13 40 [42949396.320000] updating scheduler params ... 173
> > Jan 11 20:41:13 40 [42949396.320000] updating scheduler params ... 173
> > Jan 11 20:41:13 40 [42949396.320000] BUG: spinlock recursion on CPU#0, swapper/0
> > Jan 11 20:43:59 40 [42949396.320000] BUG: spinlock lockup on CPU#0,
> > swapper/0, a05dd520
> >
> > Note: this kernel has also been patched with adaptive readahead
> > patches v10, which may also affect this but I'm reporting it here
> > (will try in a moment w/o readahead and update) because the string
> > printed to netconsole comes from kernel/vserver/sched.c
> > (vx_update_sched_param).
>
> yes, the 'updating scheduler params' is a harmless debug
> message I 'forgot' in the code, well, I could also say
> I left it there intentionally :) but IMHO the spinlock
> recursiona is not directly related to that, nevertheless
> I will investigate it ...
>
> > Unfortunately I have no other traces or anything at the moment. The
> > machine is my regularly beaten and abused dual HT Xeon.
>
> the register dump following that 'BUG' would be very
> interesting and probably conclusive ...
>
Without the readahead patches it's exactly the same. Unfortunately I
was unable to get a stack trace (via alt-sysrq-something) because the
keyboard was non-responsive (well, it blinked briefly when I plugged
it in but that's it), will try again tomorrow.
BTW, it dies when starting the first vserver.
Best regards,
Grzegorz Nosek
_______________________________________________
Vserver mailing list
Vserver@list.linux-vserver.org
http://list.linux-vserver.org/mailman/listinfo/vserver
Received on Wed Jan 11 21:09:32 2006