Messages in this thread | | | Date | Sun, 20 Aug 2023 22:13:07 +0100 | From | Qais Yousef <> | Subject | Re: [PATCH 1/4] sched: cpufreq: Rename map_util_perf to apply_dvfs_headroom |
| |
On 08/20/23 22:06, Qais Yousef wrote: > We are providing headroom for the utilization to grow until the next > decision point to pick the next frequency. Give the function a better > name and give it some documentation. It is not really mapping anything. > > Provide a dummy definition for !CONFIG_CPUFREQ which will be required > for later patches. > > Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io> > --- > include/linux/energy_model.h | 2 +- > include/linux/sched/cpufreq.h | 27 ++++++++++++++++++++++++++- > kernel/sched/cpufreq_schedutil.c | 6 +++--- > 3 files changed, 30 insertions(+), 5 deletions(-) > > diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h > index b9caa01dfac4..6ebde4e69e98 100644 > --- a/include/linux/energy_model.h > +++ b/include/linux/energy_model.h > @@ -243,7 +243,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, > scale_cpu = arch_scale_cpu_capacity(cpu); > ps = &pd->table[pd->nr_perf_states - 1]; > > - max_util = map_util_perf(max_util); > + max_util = apply_dvfs_headroom(max_util); > max_util = min(max_util, allowed_cpu_cap); > freq = map_util_freq(max_util, ps->frequency, scale_cpu); > > diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h > index bdd31ab93bc5..f0069b354ac8 100644 > --- a/include/linux/sched/cpufreq.h > +++ b/include/linux/sched/cpufreq.h > @@ -29,10 +29,35 @@ static inline unsigned long map_util_freq(unsigned long util, > return freq * util / cap; > } > > -static inline unsigned long map_util_perf(unsigned long util) > +/* > + * DVFS decision are made at discrete points. If CPU stays busy, the util will > + * continue to grow, which means it could need to run at a higher frequency > + * before the next decision point was reached. IOW, we can't follow the util as > + * it grows immediately, but there's a delay before we issue a request to go to > + * higher frequency. The headroom caters for this delay so the system continues > + * to run at adequate performance point. > + * > + * This function provides enough headroom to provide adequate performance > + * assuming the CPU continues to be busy. > + * > + * At the moment it is a constant multiplication with 1.25. > + * > + * TODO: The headroom should be a function of the delay. 25% is too high > + * especially on powerful systems. For example, if the delay is 500us, it makes > + * more sense to give a small headroom as the next decision point is not far > + * away and will follow the util if it continues to rise. On the other hand if > + * the delay is 10ms, then we need a bigger headroom so the CPU won't struggle > + * at a lower frequency if it never goes to idle until then. > + */
I'm happy to drop this TODO if it is controversial. I already have a series that works in that effect that I will hopefully get a chance to post soon enough.
Cheers
-- Qais Yousef
> +static inline unsigned long apply_dvfs_headroom(unsigned long util) > { > return util + (util >> 2); > } > +#else > +static inline unsigned long apply_dvfs_headroom(unsigned long util) > +{ > + return util; > +} > #endif /* CONFIG_CPU_FREQ */ > > #endif /* _LINUX_SCHED_CPUFREQ_H */ > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c > index 4492608b7d7f..916c4d3d6192 100644 > --- a/kernel/sched/cpufreq_schedutil.c > +++ b/kernel/sched/cpufreq_schedutil.c > @@ -143,7 +143,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, > unsigned int freq = arch_scale_freq_invariant() ? > policy->cpuinfo.max_freq : policy->cur; > > - util = map_util_perf(util); > + util = apply_dvfs_headroom(util); > freq = map_util_freq(util, freq, max); > > if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update) > @@ -406,8 +406,8 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, > sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util) > sg_cpu->util = prev_util; > > - cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl), > - map_util_perf(sg_cpu->util), max_cap); > + cpufreq_driver_adjust_perf(sg_cpu->cpu, apply_dvfs_headroom(sg_cpu->bw_dl), > + apply_dvfs_headroom(sg_cpu->util), max_cap); > > sg_cpu->sg_policy->last_freq_update_time = time; > } > -- > 2.34.1 >
| |