Re: [patch] clockevents: drivers for i386, fix #2

[Andrew Morton]

On Wed, 4 Oct 2006 08:46:20 +0200
Ingo Molnar <mingo@xxxxxxx> wrote:

> 
> * Andrew Morton <akpm@xxxxxxxx> wrote:
> 
> > Disabling LOCAL_APIC does fix it.
> 
> thanks, that narrows it down quite a bit. (We've double-checked the 
> lapic path and it seemed all our changes are NOP, but obviously it isnt 
> and we'll check it all again.)
> 
> (if you have that kernel still booted by any chance then do you see the 
> 'LOC' IRQ count in /proc/interrupts or any other count in /proc/stats 
> increasing at an alarming rate? That would narrow it down to lapic timer 
> misprogramming.)
> 

None of the interrupts are doing anything wrong.  oprofile shows nothing
alarming.

Disabling cpufreq in config doesn't fix it.

Userspace can count to a billion in 3.9 seconds when this problem is
present, which is the same time as it takes on a non-slow kernel.

`sleep 5' takes 5 seconds.

Yet initscripts take a long time (especially applying the ipfilter firewall
rues for some reason), and `startx' takes a long time, etc.  This kernel
takes 112 seconds to boot to a login prompt - other kernels take 56 seconds
(interesting ratio..)

Weird.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/