On Mon, Jun 30, 2008 at 7:38 AM, Bob Johnson <[EMAIL PROTECTED]> wrote:
> On 6/30/08, David Allen <[EMAIL PROTECTED]> wrote:
>> I've been seeing errors like the following appearing:
>> Jun 30 03:13:57 ford kernel: calcru: runtime went backwards from 261
>> usec to 258 usec for pid 516 (devd)
>> Jun 30 03:13:57 ford kernel: calcru: runtime went backwards from 486
>> usec to 481 usec for pid 0 (swapper)
>> and narrowed down the cause to openntpd.
>> Do these errors fall into the Mostly Harmless category?
> It's probably just an annoyance, unless it is happening so often it
> causes other problems.
I'll not worry then, but what's perplexing is that if "time going backwards"
leads to confusion, why is that ntpd, as a matter of course, doesn't result
in these error messages, but openntpd does? And then, why isn't anyone
using openntpd getting the errors?
> The FreeBSD FAQ used to have a nice explanation of this, but it has
> been replaced by a discussion that simply assumes the problem is
> caused by the Intel SpeedStep implementation on your motherboard:
My web searches turned a lot of noise about the above issue. Thanks for
clarifying what I was reading. As for the FAQ, didn't there was one. I guess
I've not needed it until now. ;-)
> But in general, this error can be caused by several things, including
> a device that is slow to respond to interrupts. One thing that often
> helps on SMP systems is to make sure your timecounter isn't using TSC:
> $ sysctl kern.timecounter
> kern.timecounter.tick: 1
> kern.timecounter.choice: TSC(-100) HPET(900) ACPI-fast(1000) i8254(0)
> kern.timecounter.hardware: ACPI-fast
Good to know, but this is an older single processor system (ACPI-safe).
Seems I'll have to decide whether I drop openntpd and shuffle things
around to other systems, or learn to live with the errors.
Thanks to everyone that replied.
firstname.lastname@example.org mailing list
To unsubscribe, send any mail to "[EMAIL PROTECTED]"