Messages in this thread | | | Date | Mon, 30 Jan 2023 19:24:54 +0000 | From | Qais Yousef <> | Subject | Re: [PATCH 1/3] sched/uclamp: Set max_spare_cap_cpu even if max_spare_cap is 0 |
| |
On 01/30/23 15:44, Vincent Guittot wrote: > On Sun, 29 Jan 2023 at 17:14, Qais Yousef <qyousef@layalina.io> 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@layalina.io> > > --- > > 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 > >
| |