| Message ID | 1572979786-20361-2-git-send-email-thara.gopinath@linaro.org |
|---|---|
| State | New |
| Headers | show |
| Series | Introduce Thermal Pressure | expand |
On Tue, 5 Nov 2019 at 19:49, Thara Gopinath <thara.gopinath@linaro.org> wrote: > > Extrapolating on the exisiting framework to track rt/dl utilization using > pelt signals, add a similar mechanism to track thermal pressure. The > difference here from rt/dl utilization tracking is that, instead of > tracking time spent by a cpu running a rt/dl task through util_avg, > the average thermal pressure is tracked through load_avg. This is > because thermal pressure signal is weighted "delta" capacity > and is not binary(util_avg is binary). "delta capacity" here > means delta between the actual capacity of a cpu and the decreased > capacity a cpu due to a thermal event. > In order to track average thermal pressure, a new sched_avg variable > avg_thermal is introduced. Function update_thermal_load_avg can be called > to do the periodic bookeeping (accumulate, decay and average) > of the thermal pressure. > > Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org> Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org> > --- > kernel/sched/pelt.c | 13 +++++++++++++ > kernel/sched/pelt.h | 7 +++++++ > kernel/sched/sched.h | 1 + > 3 files changed, 21 insertions(+) > > diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c > index a96db50..3821069 100644 > --- a/kernel/sched/pelt.c > +++ b/kernel/sched/pelt.c > @@ -353,6 +353,19 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) > return 0; > } > > +int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) > +{ > + if (___update_load_sum(now, &rq->avg_thermal, > + capacity, > + capacity, > + capacity)) { > + ___update_load_avg(&rq->avg_thermal, 1, 1); > + return 1; > + } > + > + return 0; > +} > + > #ifdef CONFIG_HAVE_SCHED_AVG_IRQ > /* > * irq: > diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h > index afff644..c74226d 100644 > --- a/kernel/sched/pelt.h > +++ b/kernel/sched/pelt.h > @@ -6,6 +6,7 @@ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se > int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq); > int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); > int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); > +int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity); > > #ifdef CONFIG_HAVE_SCHED_AVG_IRQ > int update_irq_load_avg(struct rq *rq, u64 running); > @@ -159,6 +160,12 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running) > } > > static inline int > +update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) > +{ > + return 0; > +} > + > +static inline int > update_irq_load_avg(struct rq *rq, u64 running) > { > return 0; > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h > index 0db2c1b..d5d82c8 100644 > --- a/kernel/sched/sched.h > +++ b/kernel/sched/sched.h > @@ -944,6 +944,7 @@ struct rq { > #ifdef CONFIG_HAVE_SCHED_AVG_IRQ > struct sched_avg avg_irq; > #endif > + struct sched_avg avg_thermal; > u64 idle_stamp; > u64 avg_idle; > > -- > 2.1.4 >
On 05/11/2019 19:49, Thara Gopinath wrote: > Extrapolating on the exisiting framework to track rt/dl utilization using s/exisiting/existing > pelt signals, add a similar mechanism to track thermal pressure. The > difference here from rt/dl utilization tracking is that, instead of > tracking time spent by a cpu running a rt/dl task through util_avg, > the average thermal pressure is tracked through load_avg. This is > because thermal pressure signal is weighted "delta" capacity > and is not binary(util_avg is binary). "delta capacity" here > means delta between the actual capacity of a cpu and the decreased > capacity a cpu due to a thermal event. > In order to track average thermal pressure, a new sched_avg variable > avg_thermal is introduced. Function update_thermal_load_avg can be called > to do the periodic bookeeping (accumulate, decay and average) s/bookeeping/bookkeeping > of the thermal pressure. > > Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org> > --- > kernel/sched/pelt.c | 13 +++++++++++++ > kernel/sched/pelt.h | 7 +++++++ > kernel/sched/sched.h | 1 + > 3 files changed, 21 insertions(+) > > diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c > index a96db50..3821069 100644 > --- a/kernel/sched/pelt.c > +++ b/kernel/sched/pelt.c > @@ -353,6 +353,19 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) > return 0; > } Minor thing: There are function headers for rt_rq, dl_rq and irq. rt_rq even explains that 'load_avg and runnable_load_avg are not supported and meaningless.' Could you do something similar for thermal here? It's not self-explanatory why we track load_avg, runnable_load_avg and util_avg for thermal but only use load_avg. > +int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) > +{ > + if (___update_load_sum(now, &rq->avg_thermal, > + capacity, > + capacity, > + capacity)) { > + ___update_load_avg(&rq->avg_thermal, 1, 1); > + return 1; > + } > + > + return 0; > +} > + [...]
Hi Dietmar, Thanks for the review. On 11/06/2019 07:50 AM, Dietmar Eggemann wrote: > On 05/11/2019 19:49, Thara Gopinath wrote: >> Extrapolating on the exisiting framework to track rt/dl utilization using > > s/exisiting/existing > >> pelt signals, add a similar mechanism to track thermal pressure. The >> difference here from rt/dl utilization tracking is that, instead of >> tracking time spent by a cpu running a rt/dl task through util_avg, >> the average thermal pressure is tracked through load_avg. This is >> because thermal pressure signal is weighted "delta" capacity >> and is not binary(util_avg is binary). "delta capacity" here >> means delta between the actual capacity of a cpu and the decreased >> capacity a cpu due to a thermal event. >> In order to track average thermal pressure, a new sched_avg variable >> avg_thermal is introduced. Function update_thermal_load_avg can be called >> to do the periodic bookeeping (accumulate, decay and average) > > s/bookeeping/bookkeeping > >> of the thermal pressure. >> >> Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org> >> --- >> kernel/sched/pelt.c | 13 +++++++++++++ >> kernel/sched/pelt.h | 7 +++++++ >> kernel/sched/sched.h | 1 + >> 3 files changed, 21 insertions(+) >> >> diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c >> index a96db50..3821069 100644 >> --- a/kernel/sched/pelt.c >> +++ b/kernel/sched/pelt.c >> @@ -353,6 +353,19 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) >> return 0; >> } > > Minor thing: There are function headers for rt_rq, dl_rq and irq. rt_rq > even explains that 'load_avg and runnable_load_avg are not supported and > meaningless.' Could you do something similar for thermal here? It's not > self-explanatory why we track load_avg, runnable_load_avg and util_avg > for thermal but only use load_avg. Will put a function header and update the nits above. > >> +int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) >> +{ >> + if (___update_load_sum(now, &rq->avg_thermal, >> + capacity, >> + capacity, >> + capacity)) { >> + ___update_load_avg(&rq->avg_thermal, 1, 1); >> + return 1; >> + } >> + >> + return 0; >> +} >> + > > [...] > -- Warm Regards Thara
Hi Thara On 11/05/19 13:49, Thara Gopinath wrote: > Extrapolating on the exisiting framework to track rt/dl utilization using > pelt signals, add a similar mechanism to track thermal pressure. The > difference here from rt/dl utilization tracking is that, instead of > tracking time spent by a cpu running a rt/dl task through util_avg, > the average thermal pressure is tracked through load_avg. This is > because thermal pressure signal is weighted "delta" capacity > and is not binary(util_avg is binary). "delta capacity" here > means delta between the actual capacity of a cpu and the decreased > capacity a cpu due to a thermal event. > In order to track average thermal pressure, a new sched_avg variable > avg_thermal is introduced. Function update_thermal_load_avg can be called > to do the periodic bookeeping (accumulate, decay and average) > of the thermal pressure. > > Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org> > --- > kernel/sched/pelt.c | 13 +++++++++++++ > kernel/sched/pelt.h | 7 +++++++ > kernel/sched/sched.h | 1 + > 3 files changed, 21 insertions(+) > > diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c > index a96db50..3821069 100644 > --- a/kernel/sched/pelt.c > +++ b/kernel/sched/pelt.c > @@ -353,6 +353,19 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) > return 0; > } > > +int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) > +{ > + if (___update_load_sum(now, &rq->avg_thermal, > + capacity, > + capacity, > + capacity)) { > + ___update_load_avg(&rq->avg_thermal, 1, 1); > + return 1; > + } > + > + return 0; > +} Care to add a tracepoint to this new signal like we now have for the other ones? Thanks -- Qais Yousef > + > #ifdef CONFIG_HAVE_SCHED_AVG_IRQ > /* > * irq: > diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h > index afff644..c74226d 100644 > --- a/kernel/sched/pelt.h > +++ b/kernel/sched/pelt.h > @@ -6,6 +6,7 @@ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se > int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq); > int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); > int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); > +int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity); > > #ifdef CONFIG_HAVE_SCHED_AVG_IRQ > int update_irq_load_avg(struct rq *rq, u64 running); > @@ -159,6 +160,12 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running) > } > > static inline int > +update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) > +{ > + return 0; > +} > + > +static inline int > update_irq_load_avg(struct rq *rq, u64 running) > { > return 0; > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h > index 0db2c1b..d5d82c8 100644 > --- a/kernel/sched/sched.h > +++ b/kernel/sched/sched.h > @@ -944,6 +944,7 @@ struct rq { > #ifdef CONFIG_HAVE_SCHED_AVG_IRQ > struct sched_avg avg_irq; > #endif > + struct sched_avg avg_thermal; > u64 idle_stamp; > u64 avg_idle; > > -- > 2.1.4 >
On Wed, Nov 6, 2019 at 12:20 AM Thara Gopinath <thara.gopinath@linaro.org> wrote: > > Extrapolating on the exisiting framework to track rt/dl utilization using > pelt signals, add a similar mechanism to track thermal pressure. The > difference here from rt/dl utilization tracking is that, instead of > tracking time spent by a cpu running a rt/dl task through util_avg, > the average thermal pressure is tracked through load_avg. This is > because thermal pressure signal is weighted "delta" capacity > and is not binary(util_avg is binary). "delta capacity" here > means delta between the actual capacity of a cpu and the decreased > capacity a cpu due to a thermal event. Use a blank line here. And reflow the paragraph text. > In order to track average thermal pressure, a new sched_avg variable > avg_thermal is introduced. Function update_thermal_load_avg can be called > to do the periodic bookeeping (accumulate, decay and average) > of the thermal pressure. > > Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org> > --- > kernel/sched/pelt.c | 13 +++++++++++++ > kernel/sched/pelt.h | 7 +++++++ > kernel/sched/sched.h | 1 + > 3 files changed, 21 insertions(+) > > diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c > index a96db50..3821069 100644 > --- a/kernel/sched/pelt.c > +++ b/kernel/sched/pelt.c > @@ -353,6 +353,19 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) > return 0; > } > > +int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) > +{ > + if (___update_load_sum(now, &rq->avg_thermal, > + capacity, > + capacity, > + capacity)) { > + ___update_load_avg(&rq->avg_thermal, 1, 1); > + return 1; > + } > + > + return 0; > +} > + > #ifdef CONFIG_HAVE_SCHED_AVG_IRQ > /* > * irq: > diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h > index afff644..c74226d 100644 > --- a/kernel/sched/pelt.h > +++ b/kernel/sched/pelt.h > @@ -6,6 +6,7 @@ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se > int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq); > int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); > int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); > +int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity); > > #ifdef CONFIG_HAVE_SCHED_AVG_IRQ > int update_irq_load_avg(struct rq *rq, u64 running); > @@ -159,6 +160,12 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running) > } > > static inline int > +update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) > +{ > + return 0; > +} > + > +static inline int > update_irq_load_avg(struct rq *rq, u64 running) > { > return 0; > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h > index 0db2c1b..d5d82c8 100644 > --- a/kernel/sched/sched.h > +++ b/kernel/sched/sched.h > @@ -944,6 +944,7 @@ struct rq { > #ifdef CONFIG_HAVE_SCHED_AVG_IRQ > struct sched_avg avg_irq; > #endif > + struct sched_avg avg_thermal; Have your considered putting this inside a #ifdef CONFIG_HAVE_SCHED_THERMAL_PRESSURE? > u64 idle_stamp; > u64 avg_idle; > > -- > 2.1.4 >
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index a96db50..3821069 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -353,6 +353,19 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) return 0; } +int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) +{ + if (___update_load_sum(now, &rq->avg_thermal, + capacity, + capacity, + capacity)) { + ___update_load_avg(&rq->avg_thermal, 1, 1); + return 1; + } + + return 0; +} + #ifdef CONFIG_HAVE_SCHED_AVG_IRQ /* * irq: diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index afff644..c74226d 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -6,6 +6,7 @@ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq); int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); +int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity); #ifdef CONFIG_HAVE_SCHED_AVG_IRQ int update_irq_load_avg(struct rq *rq, u64 running); @@ -159,6 +160,12 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running) } static inline int +update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) +{ + return 0; +} + +static inline int update_irq_load_avg(struct rq *rq, u64 running) { return 0; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0db2c1b..d5d82c8 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -944,6 +944,7 @@ struct rq { #ifdef CONFIG_HAVE_SCHED_AVG_IRQ struct sched_avg avg_irq; #endif + struct sched_avg avg_thermal; u64 idle_stamp; u64 avg_idle;
Extrapolating on the exisiting framework to track rt/dl utilization using pelt signals, add a similar mechanism to track thermal pressure. The difference here from rt/dl utilization tracking is that, instead of tracking time spent by a cpu running a rt/dl task through util_avg, the average thermal pressure is tracked through load_avg. This is because thermal pressure signal is weighted "delta" capacity and is not binary(util_avg is binary). "delta capacity" here means delta between the actual capacity of a cpu and the decreased capacity a cpu due to a thermal event. In order to track average thermal pressure, a new sched_avg variable avg_thermal is introduced. Function update_thermal_load_avg can be called to do the periodic bookeeping (accumulate, decay and average) of the thermal pressure. Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org> --- kernel/sched/pelt.c | 13 +++++++++++++ kernel/sched/pelt.h | 7 +++++++ kernel/sched/sched.h | 1 + 3 files changed, 21 insertions(+) -- 2.1.4