| Message ID | 20210310110212.26512-5-daniel.lezcano@linaro.org |
|---|---|
| State | Superseded |
| Headers | show |
| Series | [v3,1/5] powercap/drivers/dtpm: Encapsulate even more the code | expand |
On 3/10/21 11:02 AM, Daniel Lezcano wrote: > Currently the power consumption is based on the current OPP power > assuming the entire performance domain is fully loaded. > > That gives very gross power estimation and we can do much better by > using the load to scale the power consumption. > > Use the utilization to normalize and scale the power usage over the > max possible power. > > Tested on a rock960 with 2 big CPUS, the power consumption estimation > conforms with the expected one. > > Before this change: > > ~$ ~/dhrystone -t 1 -l 10000& > ~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw > 2260000 > > After this change: > > ~$ ~/dhrystone -t 1 -l 10000& > ~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw > 1130000 > > ~$ ~/dhrystone -t 2 -l 10000& > ~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw > 2260000 > > Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org> > --- > > V3: > - Fixed uninitialized 'cpu' in scaled_power_uw() > V2: > - Replaced cpumask by em_span_cpus > - Changed 'util' metrics variable types > - Optimized utilization scaling power computation > - Renamed parameter name for scale_pd_power_uw() > --- > drivers/powercap/dtpm_cpu.c | 46 +++++++++++++++++++++++++++++++------ > 1 file changed, 39 insertions(+), 7 deletions(-) > > diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c > index ac7f2e7e262f..47854923d958 100644 > --- a/drivers/powercap/dtpm_cpu.c > +++ b/drivers/powercap/dtpm_cpu.c > @@ -68,27 +68,59 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) > return power_limit; > } > > +static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power) > +{ > + unsigned long max = 0, sum_util = 0; > + int cpu; > + > + for_each_cpu_and(cpu, pd_mask, cpu_online_mask) { > + > + /* > + * The capacity is the same for all CPUs belonging to > + * the same perf domain, so a single call to > + * arch_scale_cpu_capacity() is enough. However, we > + * need the CPU parameter to be initialized by the > + * loop, so the call ends up in this block. > + * > + * We can initialize 'max' with a cpumask_first() call > + * before the loop but the bits computation is not > + * worth given the arch_scale_cpu_capacity() just > + * returns a value where the resulting assembly code > + * will be optimized by the compiler. > + */ > + max = arch_scale_cpu_capacity(cpu); > + sum_util += sched_cpu_util(cpu, max); > + } > + > + /* > + * In the improbable case where all the CPUs of the perf > + * domain are offline, 'max' will be zero and will lead to an > + * illegal operation with a zero division. > + */ > + return max ? (power * ((sum_util << 10) / max)) >> 10 : 0; > +} > + > static u64 get_pd_power_uw(struct dtpm *dtpm) > { > struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm); > struct em_perf_domain *pd; > - struct cpumask cpus; > + struct cpumask *pd_mask; > unsigned long freq; > - int i, nr_cpus; > + int i; > > pd = em_cpu_get(dtpm_cpu->cpu); > - freq = cpufreq_quick_get(dtpm_cpu->cpu); > > - cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus)); > - nr_cpus = cpumask_weight(&cpus); > + pd_mask = em_span_cpus(pd); > + > + freq = cpufreq_quick_get(dtpm_cpu->cpu); > > for (i = 0; i < pd->nr_perf_states; i++) { > > if (pd->table[i].frequency < freq) > continue; > > - return pd->table[i].power * > - MICROWATT_PER_MILLIWATT * nr_cpus; > + return scale_pd_power_uw(pd_mask, pd->table[i].power * > + MICROWATT_PER_MILLIWATT); > } > > return 0; > LGTM Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index ac7f2e7e262f..47854923d958 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -68,27 +68,59 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) return power_limit; } +static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power) +{ + unsigned long max = 0, sum_util = 0; + int cpu; + + for_each_cpu_and(cpu, pd_mask, cpu_online_mask) { + + /* + * The capacity is the same for all CPUs belonging to + * the same perf domain, so a single call to + * arch_scale_cpu_capacity() is enough. However, we + * need the CPU parameter to be initialized by the + * loop, so the call ends up in this block. + * + * We can initialize 'max' with a cpumask_first() call + * before the loop but the bits computation is not + * worth given the arch_scale_cpu_capacity() just + * returns a value where the resulting assembly code + * will be optimized by the compiler. + */ + max = arch_scale_cpu_capacity(cpu); + sum_util += sched_cpu_util(cpu, max); + } + + /* + * In the improbable case where all the CPUs of the perf + * domain are offline, 'max' will be zero and will lead to an + * illegal operation with a zero division. + */ + return max ? (power * ((sum_util << 10) / max)) >> 10 : 0; +} + static u64 get_pd_power_uw(struct dtpm *dtpm) { struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm); struct em_perf_domain *pd; - struct cpumask cpus; + struct cpumask *pd_mask; unsigned long freq; - int i, nr_cpus; + int i; pd = em_cpu_get(dtpm_cpu->cpu); - freq = cpufreq_quick_get(dtpm_cpu->cpu); - cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus)); - nr_cpus = cpumask_weight(&cpus); + pd_mask = em_span_cpus(pd); + + freq = cpufreq_quick_get(dtpm_cpu->cpu); for (i = 0; i < pd->nr_perf_states; i++) { if (pd->table[i].frequency < freq) continue; - return pd->table[i].power * - MICROWATT_PER_MILLIWATT * nr_cpus; + return scale_pd_power_uw(pd_mask, pd->table[i].power * + MICROWATT_PER_MILLIWATT); } return 0;
Currently the power consumption is based on the current OPP power assuming the entire performance domain is fully loaded. That gives very gross power estimation and we can do much better by using the load to scale the power consumption. Use the utilization to normalize and scale the power usage over the max possible power. Tested on a rock960 with 2 big CPUS, the power consumption estimation conforms with the expected one. Before this change: ~$ ~/dhrystone -t 1 -l 10000& ~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw 2260000 After this change: ~$ ~/dhrystone -t 1 -l 10000& ~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw 1130000 ~$ ~/dhrystone -t 2 -l 10000& ~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw 2260000 Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org> --- V3: - Fixed uninitialized 'cpu' in scaled_power_uw() V2: - Replaced cpumask by em_span_cpus - Changed 'util' metrics variable types - Optimized utilization scaling power computation - Renamed parameter name for scale_pd_power_uw() --- drivers/powercap/dtpm_cpu.c | 46 +++++++++++++++++++++++++++++++------ 1 file changed, 39 insertions(+), 7 deletions(-) -- 2.17.1