On 16-Aug 12:34, Dietmar Eggemann wrote:
> On 08/13/2018 05:01 PM, Patrick Bellasi wrote:
> >On 13-Aug 16:06, Vincent Guittot wrote:
> >>On Mon, 13 Aug 2018 at 14:49, Patrick Bellasi
> >>wrote:
> >>>On 13-Aug 14:07, Vincent Guittot wrote:
> On Mon, 13 Aug 2018 at 12:12, Patrick Bellasi
> >>
On 08/13/2018 05:01 PM, Patrick Bellasi wrote:
On 13-Aug 16:06, Vincent Guittot wrote:
On Mon, 13 Aug 2018 at 14:49, Patrick Bellasi wrote:
On 13-Aug 14:07, Vincent Guittot wrote:
On Mon, 13 Aug 2018 at 12:12, Patrick Bellasi wrote:
[...]
Yes I agree that the current behavior is not comp
On 13-Aug 16:06, Vincent Guittot wrote:
> On Mon, 13 Aug 2018 at 14:49, Patrick Bellasi wrote:
> > On 13-Aug 14:07, Vincent Guittot wrote:
> > > On Mon, 13 Aug 2018 at 12:12, Patrick Bellasi
> > > wrote:
[...]
> > Yes I agree that the current behavior is not completely clean... still
> > the q
On Mon, 13 Aug 2018 at 14:49, Patrick Bellasi wrote:
>
> On 13-Aug 14:07, Vincent Guittot wrote:
> > On Mon, 13 Aug 2018 at 12:12, Patrick Bellasi
> > wrote:
> > >
> > > Hi Vincent!
> > >
> > > On 09-Aug 18:03, Vincent Guittot wrote:
> > > > > On 07-Aug 15:26, Juri Lelli wrote:
> > >
> > > [...]
On 13-Aug 14:07, Vincent Guittot wrote:
> On Mon, 13 Aug 2018 at 12:12, Patrick Bellasi wrote:
> >
> > Hi Vincent!
> >
> > On 09-Aug 18:03, Vincent Guittot wrote:
> > > > On 07-Aug 15:26, Juri Lelli wrote:
> >
> > [...]
> >
> > > > > > + util_cfs = cpu_util_cfs(rq);
> > > > > > + util_rt = cp
On Mon, 13 Aug 2018 at 14:07, Vincent Guittot
wrote:
>
> On Mon, 13 Aug 2018 at 12:12, Patrick Bellasi wrote:
> >
> > Hi Vincent!
> >
> > On 09-Aug 18:03, Vincent Guittot wrote:
> > > > On 07-Aug 15:26, Juri Lelli wrote:
> >
> > [...]
> >
> > > > > > + util_cfs = cpu_util_cfs(rq);
> > > > > > +
On Mon, 13 Aug 2018 at 12:12, Patrick Bellasi wrote:
>
> Hi Vincent!
>
> On 09-Aug 18:03, Vincent Guittot wrote:
> > > On 07-Aug 15:26, Juri Lelli wrote:
>
> [...]
>
> > > > > + util_cfs = cpu_util_cfs(rq);
> > > > > + util_rt = cpu_util_rt(rq);
> > > > > + if (sched_feat(UCLAMP_SCHED_CLASS
On 13/08/18 11:12, Patrick Bellasi wrote:
> Hi Vincent!
>
> On 09-Aug 18:03, Vincent Guittot wrote:
> > > On 07-Aug 15:26, Juri Lelli wrote:
>
> [...]
>
> > > > > + util_cfs = cpu_util_cfs(rq);
> > > > > + util_rt = cpu_util_rt(rq);
> > > > > + if (sched_feat(UCLAMP_SCHED_CLASS)) {
> > >
Hi Quentin!
On 09-Aug 16:55, Quentin Perret wrote:
> Hi Patrick,
>
> On Thursday 09 Aug 2018 at 16:41:56 (+0100), Patrick Bellasi wrote:
> > > IIUC, not far below this you should still have something like:
> > >
> > > if (rt_rq_is_runnable(&rq->rt))
> > > return max;
> >
> > Do you
Hi Vincent!
On 09-Aug 18:03, Vincent Guittot wrote:
> > On 07-Aug 15:26, Juri Lelli wrote:
[...]
> > > > + util_cfs = cpu_util_cfs(rq);
> > > > + util_rt = cpu_util_rt(rq);
> > > > + if (sched_feat(UCLAMP_SCHED_CLASS)) {
> > > > + util = 0;
> > > > + if (util_cfs)
> >
Hi Patrick,
On Thu, 9 Aug 2018 at 17:34, Patrick Bellasi wrote:
>
> On 07-Aug 15:26, Juri Lelli wrote:
> > Hi,
> >
> > On 06/08/18 17:39, Patrick Bellasi wrote:
> >
> > [...]
> >
> > > @@ -223,13 +224,25 @@ static unsigned long sugov_get_util(struct
> > > sugov_cpu *sg_cpu)
> > > * utilizat
Hi Patrick,
On Thursday 09 Aug 2018 at 16:41:56 (+0100), Patrick Bellasi wrote:
> > IIUC, not far below this you should still have something like:
> >
> > if (rt_rq_is_runnable(&rq->rt))
> > return max;
>
> Do you mean that when RT tasks are RUNNABLE we still want to got to
> MAX
On 07-Aug 14:54, Quentin Perret wrote:
> Hi Patrick,
Hi Quentin!
> On Monday 06 Aug 2018 at 17:39:38 (+0100), Patrick Bellasi wrote:
> > diff --git a/kernel/sched/cpufreq_schedutil.c
> > b/kernel/sched/cpufreq_schedutil.c
> > index a7affc729c25..bb25ef66c2d3 100644
> > --- a/kernel/sched/cpufreq
On 07-Aug 15:26, Juri Lelli wrote:
> Hi,
>
> On 06/08/18 17:39, Patrick Bellasi wrote:
>
> [...]
>
> > @@ -223,13 +224,25 @@ static unsigned long sugov_get_util(struct sugov_cpu
> > *sg_cpu)
> > * utilization (PELT windows are synchronized) we can directly add them
> > * to obtain the
Hi Patrick,
On Monday 06 Aug 2018 at 17:39:38 (+0100), Patrick Bellasi wrote:
> diff --git a/kernel/sched/cpufreq_schedutil.c
> b/kernel/sched/cpufreq_schedutil.c
> index a7affc729c25..bb25ef66c2d3 100644
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -200,
Hi,
On 06/08/18 17:39, Patrick Bellasi wrote:
[...]
> @@ -223,13 +224,25 @@ static unsigned long sugov_get_util(struct sugov_cpu
> *sg_cpu)
>* utilization (PELT windows are synchronized) we can directly add them
>* to obtain the CPU's actual utilization.
>*
> - * CF
Currently schedutil enforces a maximum frequency when RT tasks are
RUNNABLE. Such a mandatory policy can be made more tunable from
userspace thus allowing for example to define a max frequency which is
still reasonable for the execution of a specific RT workload. This
will contribute to make the R
17 matches
Mail list logo