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 <[email protected]>
---
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 Tue, 5 Nov 2019 at 19:49, Thara Gopinath <[email protected]> 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 <[email protected]>
Reviewed-by: Vincent Guittot <[email protected]>
> ---
> 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 <[email protected]>
> ---
> 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 <[email protected]>
>> ---
>> 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 <[email protected]>
> ---
> 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
<[email protected]> 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 <[email protected]>
> ---
> 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
>