Re: [fbsd] Re: [fbsd] timer goes sluggish

On Saturday 05 August 2006 05:01, Jeremie Le Hen wrote:
> Hi John,
> 
> On Thu, Jun 01, 2006 at 02:41:07PM -0400, John Baldwin wrote:
> > On Tuesday 30 May 2006 18:32, Jeremie Le Hen wrote:
> > > Hi,
> > > 
> > > On Mon, May 29, 2006 at 05:31:03PM +0200, Jeremie Le Hen wrote:
> > > > Hi,
> > > > 
> > > > I won't write too much, the following session will tell much more:
> > > > 
> > > > % jarjarbinks:root# ntpdate -b chronos.cru.fr
> > > > % 29 May 17:08:44 ntpdate[4254]: step time server 195.220.94.163 
offset 
> > 0.000273 sec
> > > > % jarjarbinks:root# sysctl kern.timecounter.hardware
> > > > % kern.timecounter.hardware: ACPI-fast
> > > > % jarjarbinks:root# while : ; do date ; sleep 1 ; done
> > > > % Mon May 29 17:08:56 CEST 2006
> > > > % Mon May 29 17:09:03 CEST 2006
> > > > % Mon May 29 17:09:09 CEST 2006
> > > > % Mon May 29 17:09:16 CEST 2006
> > > > % Mon May 29 17:09:22 CEST 2006
> > > > % ^C
> > > 
> > > Sometimes, I feel dumb.
> > > 
> > > I noticed that the clock sped up when the CPU makes heavy computing,
> > > which meant there was some power saving on idleness.
> > > 
> > > I dug a bit I found that hw.acpi.cpu.cx_lowest=C4.
> > > Setting it hw.acpi.cpu.cx_lowest=C1 makes the clock goes ``in time'' :).
> > 
> > If you are using APIC, try disabling APIC and see if it works ok with 
higher 
> > Cx states.
> 
> Sorry for the delay.
> 
> I was indeed using APIC, and got a chance to disable it.  I am writing
> this mail with C4 state set and it works flawlessly:
> 
> % # sysctl hw.acpi.cpu.cx_lowest
> % hw.acpi.cpu.cx_lowest: C4
> % # while : ; do date ; sleep 1 ; done
> % Sat Aug  5 10:54:19 UTC 2006
> % Sat Aug  5 10:54:20 UTC 2006
> % Sat Aug  5 10:54:21 UTC 2006
> % Sat Aug  5 10:54:22 UTC 2006
> 
> 
> What's the point in disabling apic ?  Am I supposed to lose some
> features along with the apic support removal, or is it something I
> won't notice ?

On a laptop you probably won't notice unless it is a dual-core CPU or one with 
HT (and you want to use the HT) as disabling APIC disables support for SMP on 
x86.

-- 
John Baldwin