[ntp:questions] strange time behaviour
vhfmeyer at t-online.de
vhfmeyer at t-online.de
Mon May 25 20:56:01 UTC 2009
On 25 Mai, 18:06, John Hasler <j... at dhh.gt.org> wrote:
> If it was a kernel bug I'd have seen it here, as would the many others
> who've run that kernel for thousands of hours. I suspect something in the
> application is loading down the kernel and causing it to lose ticks. 1000
> ticks is pretty fast for a Geode. Do these machines have HPET clocks?
> HPET is broken by design.
No, no HPET clock here. Clocksources are: tsc, pit, jiffies.
The application is light-weight and doesn't do any heavy things on the
kernel.
For the 13 minutes and 32 seconds the clock slew down, the behaviour
was monotonic: losing 14 or sometimes 13 seconds per minute: just as
if the pit had been reprogrammed for another frequency.
I see three possibilities, where the problem could be: ntp, the linux-
kernel or hardware. Since I can only upgrade ntp without interrupting
the working system, which is nearly as bad as unscheduled
interruptions, I would prefer the probem being in ntp. Would anybody
recommend me upgrading ntp?
Greetings, Volker Meyer
More information about the questions
mailing list