On Thu, Oct 04, 2018 at 11:55:09AM +0100, Quentin Perret wrote:
> On Thursday 04 Oct 2018 at 12:41:07 (+0200), Peter Zijlstra wrote:
> > Not sure, see what it looks like ;-) My main concern here was to get rid
> > of that giant blob in select_task_rq_fair().
>
> OK, got it. I'll probably just
On Thu, Oct 04, 2018 at 11:55:09AM +0100, Quentin Perret wrote:
> On Thursday 04 Oct 2018 at 12:41:07 (+0200), Peter Zijlstra wrote:
> > Not sure, see what it looks like ;-) My main concern here was to get rid
> > of that giant blob in select_task_rq_fair().
>
> OK, got it. I'll probably just
On Thursday 04 Oct 2018 at 12:41:07 (+0200), Peter Zijlstra wrote:
> Not sure, see what it looks like ;-) My main concern here was to get rid
> of that giant blob in select_task_rq_fair().
OK, got it. I'll probably just move the checks into the function and
merge that large comment into the
On Thursday 04 Oct 2018 at 12:41:07 (+0200), Peter Zijlstra wrote:
> Not sure, see what it looks like ;-) My main concern here was to get rid
> of that giant blob in select_task_rq_fair().
OK, got it. I'll probably just move the checks into the function and
merge that large comment into the
On Thu, Oct 04, 2018 at 11:27:22AM +0100, Quentin Perret wrote:
> > > + for_each_cpu_and(cpu, perf_domain_span(pd),
> > > sched_domain_span(sd)) {
> >
> > Which of the two masks do we expect to be the smallest?
>
> Typically, perf_domain_span is smaller.
OK, then the above expression
On Thu, Oct 04, 2018 at 11:27:22AM +0100, Quentin Perret wrote:
> > > + for_each_cpu_and(cpu, perf_domain_span(pd),
> > > sched_domain_span(sd)) {
> >
> > Which of the two masks do we expect to be the smallest?
>
> Typically, perf_domain_span is smaller.
OK, then the above expression
On Thursday 04 Oct 2018 at 11:44:12 (+0200), Peter Zijlstra wrote:
> On Wed, Sep 12, 2018 at 10:13:07AM +0100, Quentin Perret wrote:
> > + while (pd) {
> > + unsigned long cur_energy, spare_cap, max_spare_cap = 0;
> > + int max_spare_cap_cpu = -1;
> > +
> > +
On Thursday 04 Oct 2018 at 11:44:12 (+0200), Peter Zijlstra wrote:
> On Wed, Sep 12, 2018 at 10:13:07AM +0100, Quentin Perret wrote:
> > + while (pd) {
> > + unsigned long cur_energy, spare_cap, max_spare_cap = 0;
> > + int max_spare_cap_cpu = -1;
> > +
> > +
On Wed, Sep 12, 2018 at 10:13:07AM +0100, Quentin Perret wrote:
> + while (pd) {
> + unsigned long cur_energy, spare_cap, max_spare_cap = 0;
> + int max_spare_cap_cpu = -1;
> +
> + for_each_cpu_and(cpu, perf_domain_span(pd),
> sched_domain_span(sd)) {
On Wed, Sep 12, 2018 at 10:13:07AM +0100, Quentin Perret wrote:
> + while (pd) {
> + unsigned long cur_energy, spare_cap, max_spare_cap = 0;
> + int max_spare_cap_cpu = -1;
> +
> + for_each_cpu_and(cpu, perf_domain_span(pd),
> sched_domain_span(sd)) {
If an Energy Model (EM) is available and if the system isn't
overutilized, re-route waking tasks into an energy-aware placement
algorithm. The selection of an energy-efficient CPU for a task
is achieved by estimating the impact on system-level active energy
resulting from the placement of the task
If an Energy Model (EM) is available and if the system isn't
overutilized, re-route waking tasks into an energy-aware placement
algorithm. The selection of an energy-efficient CPU for a task
is achieved by estimating the impact on system-level active energy
resulting from the placement of the task
12 matches
Mail list logo