On Thu, Apr 02, 2015 at 06:32:38PM +0100, Peter Zijlstra wrote:
> On Thu, Apr 02, 2015 at 05:53:09PM +0100, Morten Rasmussen wrote:
> > Could you enlighten me a bit about how to define the arch specific
> > implementation without getting into trouble? I'm failing miserably :(
>
> Hmm, this was not
On Thu, Apr 02, 2015 at 05:53:09PM +0100, Morten Rasmussen wrote:
> Could you enlighten me a bit about how to define the arch specific
> implementation without getting into trouble? I'm failing miserably :(
Hmm, this was not supposed to be difficult.. :/
> I thought the arm arch-specific topology
On Wed, Mar 25, 2015 at 05:33:09PM +, Peter Zijlstra wrote:
> On Tue, Mar 24, 2015 at 11:00:57AM +0100, Vincent Guittot wrote:
> > On 23 March 2015 at 14:19, Peter Zijlstra wrote:
> > > On Fri, Feb 27, 2015 at 04:54:07PM +0100, Vincent Guittot wrote:
> > >
> > >> + unsigned long scale_freq
On 27 March 2015 at 09:17, Vincent Guittot wrote:
> On 26 March 2015 at 18:38, Morten Rasmussen wrote:
>> On Wed, Mar 25, 2015 at 06:08:42PM +, Vincent Guittot wrote:
>>> On 25 March 2015 at 18:33, Peter Zijlstra wrote:
>>> > On Tue, Mar 24, 2015 at 11:00:57AM +0100, Vincent Guittot wrote:
>
On 26 March 2015 at 18:38, Morten Rasmussen wrote:
> On Wed, Mar 25, 2015 at 06:08:42PM +, Vincent Guittot wrote:
>> On 25 March 2015 at 18:33, Peter Zijlstra wrote:
>> > On Tue, Mar 24, 2015 at 11:00:57AM +0100, Vincent Guittot wrote:
>> >> On 23 March 2015 at 14:19, Peter Zijlstra wrote:
>
On Thu, Mar 26, 2015 at 05:47:00PM +, Peter Zijlstra wrote:
> On Thu, Mar 26, 2015 at 05:38:45PM +, Morten Rasmussen wrote:
> > Another potential solution is to stay with weak functions but move the
> > multiplication and shift into the arch_scale_*() functions by passing
> > the value we w
On Thu, Mar 26, 2015 at 05:38:45PM +, Morten Rasmussen wrote:
> Another potential solution is to stay with weak functions but move the
> multiplication and shift into the arch_scale_*() functions by passing
> the value we want to scale into the arch_scale_*() function. That way we
> can complet
On Thu, Mar 26, 2015 at 05:38:45PM +, Morten Rasmussen wrote:
> The only downside is that for frequency invariance we need three
> arch_scale_freq_capacity() calls instead of two.
It should have been instead of one...
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" i
On Wed, Mar 25, 2015 at 06:08:42PM +, Vincent Guittot wrote:
> On 25 March 2015 at 18:33, Peter Zijlstra wrote:
> > On Tue, Mar 24, 2015 at 11:00:57AM +0100, Vincent Guittot wrote:
> >> On 23 March 2015 at 14:19, Peter Zijlstra wrote:
> >> > On Fri, Feb 27, 2015 at 04:54:07PM +0100, Vincent G
On 25 March 2015 at 18:33, Peter Zijlstra wrote:
> On Tue, Mar 24, 2015 at 11:00:57AM +0100, Vincent Guittot wrote:
>> On 23 March 2015 at 14:19, Peter Zijlstra wrote:
>> > On Fri, Feb 27, 2015 at 04:54:07PM +0100, Vincent Guittot wrote:
>> >
>> >> + unsigned long scale_freq = arch_scale_freq
On Tue, Mar 24, 2015 at 11:00:57AM +0100, Vincent Guittot wrote:
> On 23 March 2015 at 14:19, Peter Zijlstra wrote:
> > On Fri, Feb 27, 2015 at 04:54:07PM +0100, Vincent Guittot wrote:
> >
> >> + unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
> >
> >> + sa-
On 23 March 2015 at 14:19, Peter Zijlstra wrote:
> On Fri, Feb 27, 2015 at 04:54:07PM +0100, Vincent Guittot wrote:
>
>> + unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
>
>> + sa->running_avg_sum += delta_w * scale_freq
>> + >>
On Fri, Feb 27, 2015 at 04:54:07PM +0100, Vincent Guittot wrote:
> + unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
> + sa->running_avg_sum += delta_w * scale_freq
> + >> SCHED_CAPACITY_SHIFT;
so the only thing that could be im
On 3 March 2015 at 13:51, Dietmar Eggemann wrote:
> On 27/02/15 15:54, Vincent Guittot wrote:
>> From: Morten Rasmussen
>>
>> Apply frequency scale-invariance correction factor to usage tracking.
>> Each segment of the running_load_avg geometric series is now scaled by the
>
> The same comment I
From: Morten Rasmussen
Apply frequency scale-invariance correction factor to usage tracking.
Each segment of the running_avg_sum geometric series is now scaled by the
current frequency so the utilization_avg_contrib of each entity will be
invariant with frequency scaling. As a result, utilization
On 27/02/15 15:54, Vincent Guittot wrote:
> From: Morten Rasmussen
>
> Apply frequency scale-invariance correction factor to usage tracking.
> Each segment of the running_load_avg geometric series is now scaled by the
The same comment I sent out on [PATCH v10 07/11]:
The use of underscores in r
From: Morten Rasmussen
Apply frequency scale-invariance correction factor to usage tracking.
Each segment of the running_load_avg geometric series is now scaled by the
current frequency so the utilization_avg_contrib of each entity will be
invariant with frequency scaling. As a result, utilizatio
17 matches
Mail list logo
