On Wed, Apr 3, 2013 at 7:16 AM, Steven Timm <[log in to unmask]> wrote:
> Since upgrading to the 2.6.18-348.1.1 kernel I am
> seeing continuous kernel exceptions of this form
>
> 2013-04-03T04:02:13-05:00 [log in to unmask] kernel: Warning Timer
> ISR/1: T
> ime went backwards: delta=-500760595 delta_cpu=67239405
> shadow=1879913420310320
> off=249335587 processed=1879914170340430 cpu_processed=1879913602340430
> 2013-04-03T04:02:13-05:00 [log in to unmask] kernel: 0:
> 1879914170340430
> 2013-04-03T04:02:13-05:00 [log in to unmask] kernel: 1:
> 1879913602340430
>
>
> The system still is operational but the continuous error messages
> make it difficult to diagnose any other problems that may be happening.
>
> This hardware dual AMD Opteron 6134, has been running SL5 with
> Xen kernel ever since we bought it a year and a half ago and
> this is the first time we have seen this error message.  the
> error message happens both in Xen Dom0 and Xen DomU's.  We
> have three such identical machines and they all have the error.
> Our Intel-based hardware is not affected at all.
>
> Googling shows that there have been error messages of this sort
> that come and go ever since the Xen kernel was able to run on
> AMD64 hardware, and even a bugzilla against the upstream 5.6, but
> as yet no fix available.  Is anyone else seeing this error in
> the current kernels?
>
> Steve Timm

What options are available for CPU frequency governor on your system?

cat /sys/devices/system/cpu/cpu*/cpufreq/scaling_available_governors

and which one are you using? Look in /etc/sysconfig/cpuspeed .

Akemi