Re: [PATCH 1/3] sched/uclamp: Set max_spare_cap_cpu even if max_spare_cap is 0

[Qais Yousef]

On 01/30/23 15:44, Vincent Guittot wrote:
> On Sun, 29 Jan 2023 at 17:14, Qais Yousef <qyousef@xxxxxxxxxxx> wrote:
> >
> > When uclamp_max is being used, the util of the task could be higher than
> > the spare capacity of the CPU, but due to uclamp_max value we force fit
> > it there.
> >
> > The way the condition for checking for max_spare_cap in
> > find_energy_efficient_cpu() was constructed; it ignored any CPU that has
> > its spare_cap less than or _equal_ to max_spare_cap. Since we initialize
> > max_spare_cap to 0; this lead to never setting max_spare_cap_cpu and
> > hence ending up never performing compute_energy() for this cluster and
> > missing an opportunity for a better energy efficient placement to honour
> > uclamp_max setting.
> >
> >         max_spare_cap = 0;
> >         cpu_cap = capacity_of(cpu) - task_util(p);  // 0 if task_util(p) is high
> >
> >         ...
> >
> >         util_fits_cpu(...);             // will return true if uclamp_max forces it to fit
> >
> >         ...
> >
> >         // this logic will fail to update max_spare_cap_cpu if cpu_cap is 0
> >         if (cpu_cap > max_spare_cap) {
> >                 max_spare_cap = cpu_cap;
> >                 max_spare_cap_cpu = cpu;
> >         }
> >
> > prev_spare_cap suffers from a similar problem.
> >
> > Fix the logic by treating -1UL value as 'not populated' instead of
> > 0 which is a viable and correct spare capacity value.
> >
> > Fixes: 1d42509e475c ("sched/fair: Make EAS wakeup placement consider uclamp restrictions")
> > Signed-off-by: Qais Yousef (Google) <qyousef@xxxxxxxxxxx>
> > ---
> >  kernel/sched/fair.c | 14 ++++++++------
> >  1 file changed, 8 insertions(+), 6 deletions(-)
> >
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index e29e9ea4cde8..ca2c389d3180 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -7390,9 +7390,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
> >         for (; pd; pd = pd->next) {
> >                 unsigned long util_min = p_util_min, util_max = p_util_max;
> >                 unsigned long cpu_cap, cpu_thermal_cap, util;
> > -               unsigned long cur_delta, max_spare_cap = 0;
> > +               unsigned long cur_delta, max_spare_cap = -1UL;
> >                 unsigned long rq_util_min, rq_util_max;
> > -               unsigned long prev_spare_cap = 0;
> > +               unsigned long prev_spare_cap = -1UL;
> >                 int max_spare_cap_cpu = -1;
> >                 unsigned long base_energy;
> >                 int fits, max_fits = -1;
> > @@ -7457,7 +7457,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
> >                                 prev_spare_cap = cpu_cap;
> >                                 prev_fits = fits;
> >                         } else if ((fits > max_fits) ||
> > -                                  ((fits == max_fits) && (cpu_cap > max_spare_cap))) {
> > +                                  ((fits == max_fits) &&
> > +                                  (cpu_cap > max_spare_cap || max_spare_cap == -1UL) {
> 
> Can't we use a signed comparison to include the case of max_spare_cap
> == -1 in cpu_cap > max_spare_cap ?

By converting max_spare_cap to long, right?

My memory could be failing me, but I seem to remember we had mixed usage and
consolidated into unsigned long. That's why I didn't want to break the trend.

Anyway. If no one shouts against that, I don't mind going for that.


Thanks

--
Qais Yousef

> 
> >                                 /*
> >                                  * Find the CPU with the maximum spare capacity
> >                                  * among the remaining CPUs in the performance
> > @@ -7469,7 +7470,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
> >                         }
> >                 }
> >
> > -               if (max_spare_cap_cpu < 0 && prev_spare_cap == 0)
> > +               if (max_spare_cap_cpu < 0 && prev_spare_cap == -1UL)
> >                         continue;
> >
> >                 eenv_pd_busy_time(&eenv, cpus, p);
> > @@ -7477,7 +7478,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
> >                 base_energy = compute_energy(&eenv, pd, cpus, p, -1);
> >
> >                 /* Evaluate the energy impact of using prev_cpu. */
> > -               if (prev_spare_cap > 0) {
> > +               if (prev_spare_cap != -1UL) {
> >                         prev_delta = compute_energy(&eenv, pd, cpus, p,
> >                                                     prev_cpu);
> >                         /* CPU utilization has changed */
> > @@ -7489,7 +7490,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
> >                 }
> >
> >                 /* Evaluate the energy impact of using max_spare_cap_cpu. */
> > -               if (max_spare_cap_cpu >= 0 && max_spare_cap > prev_spare_cap) {
> > +               if (max_spare_cap_cpu >= 0 &&
> > +                   (max_spare_cap > prev_spare_cap || prev_spare_cap == -1UL)) {
> >                         /* Current best energy cpu fits better */
> >                         if (max_fits < best_fits)
> >                                 continue;
> > --
> > 2.25.1
> >