On Thu, 29 Nov 2007 20:36:24 +0100
Ingo Molnar <[EMAIL PROTECTED]> wrote:
> just to make sure there is no tsc impact, does booting with "notsc"
> change anything?
No, it doesn't.
> if not, does booting with idle=halt or idle=poll help? [your power usage
> will go up so it's not very useful - b
On Thu, Nov 29, 2007 at 08:25:46PM +0100, Stefano Brivio wrote:
> On Thu, 29 Nov 2007 13:24:02 -0500
> Dave Jones <[EMAIL PROTECTED]> wrote:
>
> > On Thu, Nov 29, 2007 at 06:57:43PM +0100, Stefano Brivio wrote:
>
> > > Do you want me to comment out adjust_jiffies() and see what happens?
>
* Stefano Brivio <[EMAIL PROTECTED]> wrote:
> On Thu, 29 Nov 2007 13:24:02 -0500
> Dave Jones <[EMAIL PROTECTED]> wrote:
>
> > On Thu, Nov 29, 2007 at 06:57:43PM +0100, Stefano Brivio wrote:
>
> > > Do you want me to comment out adjust_jiffies() and see what happens?
> >
> > Just for laughs,
On Thu, 29 Nov 2007 13:24:02 -0500
Dave Jones <[EMAIL PROTECTED]> wrote:
> On Thu, Nov 29, 2007 at 06:57:43PM +0100, Stefano Brivio wrote:
> > Do you want me to comment out adjust_jiffies() and see what happens?
>
> Just for laughs, why not.
I wanted to laugh, but the behaviour didn't change
On Thu, Nov 29, 2007 at 06:57:43PM +0100, Stefano Brivio wrote:
> > adjust_jiffies() always gets called on a speed transition. I'm wondering
> > if perhaps we shouldn't do that if we're using something other than
> > the tsc for timekeeping.
>
> I gave other clocksources a try:
>
> morte
On Thu, 29 Nov 2007 12:45:48 -0500
Dave Jones <[EMAIL PROTECTED]> wrote:
> Hmm, what's
> in /sys/devices/system/clocksource/clocksource0/current_clocksource ?
morte st3 # cat /sys/devices/system/clocksource/clocksource0/current_clocksource
acpi_pm
> adjust_jiffies() always gets called on a spe
On Thu, Nov 29, 2007 at 11:35:11AM +0100, Ingo Molnar wrote:
> * Stefano Brivio <[EMAIL PROTECTED]> wrote:
>
> > Ok, I found out how to reliably reproduce this bug. The root session issue
> > was a bit weird, but I noticed I usually switch to root only when I need to
> > change the CPU freq
* Stefano Brivio <[EMAIL PROTECTED]> wrote:
> Ok, I found out how to reliably reproduce this bug. The root session issue
> was a bit weird, but I noticed I usually switch to root only when I need to
> change the CPU frequency. And here's what happens:
>
> # cpuspeedy min
> [after some time...]
>
* Stefano Brivio <[EMAIL PROTECTED]> wrote:
> Please remember that this isn't just an aesthetic issue, as some
> drivers (e.g. b43 and b43legacy, but I guess a lot more) rely on
> jiffies. Do I need to file a bug to bugzilla.kernel.org? Thank you.
yes, please do file a bugzilla report too - th
Ok, I found out how to reliably reproduce this bug. The root session issue
was a bit weird, but I noticed I usually switch to root only when I need to
change the CPU frequency. And here's what happens:
# cpuspeedy min
[after some time...]
Nov 29 09:42:31 morte [ 4408.722597] b43-phy0 ERROR: PHY tr
On Sat, 24 Nov 2007 20:31:25 +0100
"Rafael J. Wysocki" <[EMAIL PROTECTED]> wrote:
> On Saturday, 24 of November 2007, Stefano Brivio wrote:
> > On Sat, 24 Nov 2007 19:48:58 +0100
> > "Rafael J. Wysocki" <[EMAIL PROTECTED]> wrote:
> >
> > > NO_HZ? Highres timers?
> >
> > CONFIG_HZ_1000=y
> > # C
On Sat, 24 Nov 2007 20:31:25 +0100
"Rafael J. Wysocki" <[EMAIL PROTECTED]> wrote:
> On Saturday, 24 of November 2007, Stefano Brivio wrote:
> > On Sat, 24 Nov 2007 19:48:58 +0100
> > "Rafael J. Wysocki" <[EMAIL PROTECTED]> wrote:
> >
> > > NO_HZ? Highres timers?
> >
> > CONFIG_HZ_1000=y
> > # C
On Saturday, 24 of November 2007, Stefano Brivio wrote:
> On Sat, 24 Nov 2007 19:48:58 +0100
> "Rafael J. Wysocki" <[EMAIL PROTECTED]> wrote:
>
> > NO_HZ? Highres timers?
>
> CONFIG_HZ_1000=y
> # CONFIG_HIGH_RES_TIMERS is not set
>
> > I understand that the previous kernels behave correctly.
On Sat, 24 Nov 2007 19:48:58 +0100
"Rafael J. Wysocki" <[EMAIL PROTECTED]> wrote:
> NO_HZ? Highres timers?
CONFIG_HZ_1000=y
# CONFIG_HIGH_RES_TIMERS is not set
> I understand that the previous kernels behave correctly. All of them?
2.6.21 behaved correctly. Sorry but git-bisect would take a
On Saturday, 24 of November 2007, Stefano Brivio wrote:
> It looks like the jiffies counter sometimes jumps back and forth of some
> hundreds seconds in 2.6.24-rc3. I observed that this happens when I use the
> su(1) command, e.g.:
>
> Nov 24 06:17:17 morte [190769.065301] wmaster0: STA 00:14:c1:3
On Sat, 24 Nov 2007 18:56:57 +0100
Frans Pop <[EMAIL PROTECTED]> wrote:
> Stefano Brivio wrote:
> > It looks like the jiffies counter sometimes jumps back and forth of some
> > hundreds seconds in 2.6.24-rc3. I observed that this happens when I use
> > the su(1) command, e.g.:
>
> Can you please
Stefano Brivio wrote:
> It looks like the jiffies counter sometimes jumps back and forth of some
> hundreds seconds in 2.6.24-rc3. I observed that this happens when I use
> the su(1) command, e.g.:
Can you please explain what exactly the problem is here?
Are you perhaps referring to the number be
17 matches
Mail list logo
