On Mon, Mar 18, 2019 at 02:21:52PM +, Patrick Bellasi wrote:
> On 18-Mar 14:10, Peter Zijlstra wrote:
> > On Mon, Mar 18, 2019 at 12:18:04PM +, Patrick Bellasi wrote:
> > > On 13-Mar 21:18, Peter Zijlstra wrote:
> > > > On Fri, Feb 08, 2019 at 10:05:42AM +, Patrick Bellasi wrote:
> > >
On 18-Mar 14:10, Peter Zijlstra wrote:
> On Mon, Mar 18, 2019 at 12:18:04PM +, Patrick Bellasi wrote:
> > On 13-Mar 21:18, Peter Zijlstra wrote:
> > > On Fri, Feb 08, 2019 at 10:05:42AM +, Patrick Bellasi wrote:
> > > > +static void uclamp_fork(struct task_struct *p)
> > > > +{
> > > > +
On Mon, Mar 18, 2019 at 12:18:04PM +, Patrick Bellasi wrote:
> On 13-Mar 21:18, Peter Zijlstra wrote:
> > On Fri, Feb 08, 2019 at 10:05:42AM +, Patrick Bellasi wrote:
> > > +static void uclamp_fork(struct task_struct *p)
> > > +{
> > > + unsigned int clamp_id;
> > > +
> > > + if (unlikely(!
On 13-Mar 21:18, Peter Zijlstra wrote:
> On Fri, Feb 08, 2019 at 10:05:42AM +, Patrick Bellasi wrote:
> > +static void uclamp_fork(struct task_struct *p)
> > +{
> > + unsigned int clamp_id;
> > +
> > + if (unlikely(!p->sched_class->uclamp_enabled))
> > + return;
> > +
> > + for
On 13-Mar 21:10, Peter Zijlstra wrote:
> On Wed, Mar 13, 2019 at 05:09:40PM +, Patrick Bellasi wrote:
>
> > Yes, that should be possible... will look into splitting this out in
> > v8 to have something like:
> >
> > ---8<---
> > struct uclamp_req {
> > /* Clamp value "requested" by a sche
On Fri, Feb 08, 2019 at 10:05:42AM +, Patrick Bellasi wrote:
> +static void uclamp_fork(struct task_struct *p)
> +{
> + unsigned int clamp_id;
> +
> + if (unlikely(!p->sched_class->uclamp_enabled))
> + return;
> +
> + for (clamp_id = 0; clamp_id < UCLAMP_CNT; ++clamp_id)
On Fri, Feb 08, 2019 at 10:05:42AM +, Patrick Bellasi wrote:
> +int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
> + void __user *buffer, size_t *lenp,
> + loff_t *ppos)
> +{
> + int old_min, old_max;
> + int res
On Wed, Mar 13, 2019 at 05:09:40PM +, Patrick Bellasi wrote:
> Yes, that should be possible... will look into splitting this out in
> v8 to have something like:
>
> ---8<---
> struct uclamp_req {
> /* Clamp value "requested" by a scheduling entity */
> unsigned int value
On Wed, Mar 13, 2019 at 05:09:40PM +, Patrick Bellasi wrote:
> On 13-Mar 15:32, Peter Zijlstra wrote:
> > I still think that this effective thing is backwards.
> With respect to the previous v6, I've now moved this concept to the
> patch where we actually use it for the first time.
> The "ef
On 13-Mar 15:32, Peter Zijlstra wrote:
> On Fri, Feb 08, 2019 at 10:05:42AM +, Patrick Bellasi wrote:
>
> > diff --git a/include/linux/sched.h b/include/linux/sched.h
> > index 45460e7a3eee..447261cd23ba 100644
> > --- a/include/linux/sched.h
> > +++ b/include/linux/sched.h
> > @@ -584,14 +584
On Fri, Feb 08, 2019 at 10:05:42AM +, Patrick Bellasi wrote:
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 45460e7a3eee..447261cd23ba 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -584,14 +584,32 @@ struct sched_dl_entity {
> * Utilization cla
Tasks without a user-defined clamp value are considered not clamped
and by default their utilization can have any value in the
[0..SCHED_CAPACITY_SCALE] range.
Tasks with a user-defined clamp value are allowed to request any value
in that range, and we unconditionally enforce the required clamps.
12 matches
Mail list logo
