v2:
- Dropped 'sched/fair: Use IRQ scaling for all sched classes'
- Added Reviewed-by from Dietmar.
This patch-set aims to improve find_energy_efficient_cpu()
by removing max_spare_cap_cpu from the candidate CPUs if
prev_cpu is already the CPU with the maximum spared capacity.
Pierre Gondois (1):
sched/fair: Check if prev_cpu has highest spare cap in feec()
kernel/sched/fair.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
--
2.25.1
When evaluating the CPU candidates in the perf domain (pd) containing
the previously used CPU (prev_cpu), find_energy_efficient_cpu()
evaluates the energy of the pd:
- without the task (base_energy)
- with the task placed on prev_cpu (if the task fits)
- with the task placed on the CPU with the highest spare capacity,
prev_cpu being excluded from this set
If prev_cpu is already the CPU with the highest spare capacity,
max_spare_cap_cpu will be the CPU with the second highest spare
capacity.
On an Arm64 Juno-r2, with a workload of 10 tasks at a 10% duty cycle,
when prev_cpu and max_spare_cap_cpu are both valid candidates,
prev_spare_cap > max_spare_cap at ~82%.
Thus the energy of the pd when placing the task on max_spare_cap_cpu
is computed with no possible positive outcome 82% most of the time.
Do not consider max_spare_cap_cpu as a valid candidate if
prev_spare_cap > max_spare_cap.
Reviewed-by: Dietmar Eggemann <[email protected]>
Signed-off-by: Pierre Gondois <[email protected]>
---
kernel/sched/fair.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 914096c5b1ae..bcae7bdd5582 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6900,7 +6900,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
for (; pd; pd = pd->next) {
unsigned long cpu_cap, cpu_thermal_cap, util;
unsigned long cur_delta, max_spare_cap = 0;
- bool compute_prev_delta = false;
+ unsigned long prev_spare_cap = 0;
int max_spare_cap_cpu = -1;
unsigned long base_energy;
@@ -6944,18 +6944,19 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
if (cpu == prev_cpu) {
/* Always use prev_cpu as a candidate. */
- compute_prev_delta = true;
+ prev_spare_cap = cpu_cap;
} else if (cpu_cap > max_spare_cap) {
/*
* Find the CPU with the maximum spare capacity
- * in the performance domain.
+ * among the remaining CPUs in the performance
+ * domain.
*/
max_spare_cap = cpu_cap;
max_spare_cap_cpu = cpu;
}
}
- if (max_spare_cap_cpu < 0 && !compute_prev_delta)
+ if (max_spare_cap_cpu < 0 && prev_spare_cap == 0)
continue;
eenv_pd_busy_time(&eenv, cpus, p);
@@ -6963,7 +6964,7 @@ 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 (compute_prev_delta) {
+ if (prev_spare_cap > 0) {
prev_delta = compute_energy(&eenv, pd, cpus, p,
prev_cpu);
/* CPU utilization has changed */
@@ -6974,7 +6975,7 @@ 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) {
+ if (max_spare_cap_cpu >= 0 && max_spare_cap > prev_spare_cap) {
cur_delta = compute_energy(&eenv, pd, cpus, p,
max_spare_cap_cpu);
/* CPU utilization has changed */
--
2.25.1
On Thu, 6 Oct 2022 at 10:11, Pierre Gondois <[email protected]> wrote:
>
> When evaluating the CPU candidates in the perf domain (pd) containing
> the previously used CPU (prev_cpu), find_energy_efficient_cpu()
> evaluates the energy of the pd:
> - without the task (base_energy)
> - with the task placed on prev_cpu (if the task fits)
> - with the task placed on the CPU with the highest spare capacity,
> prev_cpu being excluded from this set
>
> If prev_cpu is already the CPU with the highest spare capacity,
> max_spare_cap_cpu will be the CPU with the second highest spare
> capacity.
>
> On an Arm64 Juno-r2, with a workload of 10 tasks at a 10% duty cycle,
> when prev_cpu and max_spare_cap_cpu are both valid candidates,
> prev_spare_cap > max_spare_cap at ~82%.
> Thus the energy of the pd when placing the task on max_spare_cap_cpu
> is computed with no possible positive outcome 82% most of the time.
>
> Do not consider max_spare_cap_cpu as a valid candidate if
> prev_spare_cap > max_spare_cap.
>
> Reviewed-by: Dietmar Eggemann <[email protected]>
nit: the reviewed tag should be after the signed-off
> Signed-off-by: Pierre Gondois <[email protected]>
Reviewed-by: Vincent Guittot <[email protected]>
> ---
> kernel/sched/fair.c | 13 +++++++------
> 1 file changed, 7 insertions(+), 6 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 914096c5b1ae..bcae7bdd5582 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6900,7 +6900,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
> for (; pd; pd = pd->next) {
> unsigned long cpu_cap, cpu_thermal_cap, util;
> unsigned long cur_delta, max_spare_cap = 0;
> - bool compute_prev_delta = false;
> + unsigned long prev_spare_cap = 0;
> int max_spare_cap_cpu = -1;
> unsigned long base_energy;
>
> @@ -6944,18 +6944,19 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
>
> if (cpu == prev_cpu) {
> /* Always use prev_cpu as a candidate. */
> - compute_prev_delta = true;
> + prev_spare_cap = cpu_cap;
> } else if (cpu_cap > max_spare_cap) {
> /*
> * Find the CPU with the maximum spare capacity
> - * in the performance domain.
> + * among the remaining CPUs in the performance
> + * domain.
> */
> max_spare_cap = cpu_cap;
> max_spare_cap_cpu = cpu;
> }
> }
>
> - if (max_spare_cap_cpu < 0 && !compute_prev_delta)
> + if (max_spare_cap_cpu < 0 && prev_spare_cap == 0)
> continue;
>
> eenv_pd_busy_time(&eenv, cpus, p);
> @@ -6963,7 +6964,7 @@ 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 (compute_prev_delta) {
> + if (prev_spare_cap > 0) {
> prev_delta = compute_energy(&eenv, pd, cpus, p,
> prev_cpu);
> /* CPU utilization has changed */
> @@ -6974,7 +6975,7 @@ 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) {
> + if (max_spare_cap_cpu >= 0 && max_spare_cap > prev_spare_cap) {
> cur_delta = compute_energy(&eenv, pd, cpus, p,
> max_spare_cap_cpu);
> /* CPU utilization has changed */
> --
> 2.25.1
>
The following commit has been merged into the sched/core branch of tip:
Commit-ID: ad841e569f5c88e3332b32a000f251f33ff32187
Gitweb: https://git.kernel.org/tip/ad841e569f5c88e3332b32a000f251f33ff32187
Author: Pierre Gondois <[email protected]>
AuthorDate: Thu, 06 Oct 2022 10:10:52 +02:00
Committer: Peter Zijlstra <[email protected]>
CommitterDate: Thu, 27 Oct 2022 11:01:20 +02:00
sched/fair: Check if prev_cpu has highest spare cap in feec()
When evaluating the CPU candidates in the perf domain (pd) containing
the previously used CPU (prev_cpu), find_energy_efficient_cpu()
evaluates the energy of the pd:
- without the task (base_energy)
- with the task placed on prev_cpu (if the task fits)
- with the task placed on the CPU with the highest spare capacity,
prev_cpu being excluded from this set
If prev_cpu is already the CPU with the highest spare capacity,
max_spare_cap_cpu will be the CPU with the second highest spare
capacity.
On an Arm64 Juno-r2, with a workload of 10 tasks at a 10% duty cycle,
when prev_cpu and max_spare_cap_cpu are both valid candidates,
prev_spare_cap > max_spare_cap at ~82%.
Thus the energy of the pd when placing the task on max_spare_cap_cpu
is computed with no possible positive outcome 82% most of the time.
Do not consider max_spare_cap_cpu as a valid candidate if
prev_spare_cap > max_spare_cap.
Signed-off-by: Pierre Gondois <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Dietmar Eggemann <[email protected]>
Reviewed-by: Vincent Guittot <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
---
kernel/sched/fair.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 919d016..4cc56c9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7221,7 +7221,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
unsigned long cur_delta, max_spare_cap = 0;
unsigned long rq_util_min, rq_util_max;
unsigned long util_min, util_max;
- bool compute_prev_delta = false;
+ unsigned long prev_spare_cap = 0;
int max_spare_cap_cpu = -1;
unsigned long base_energy;
@@ -7283,18 +7283,19 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
if (cpu == prev_cpu) {
/* Always use prev_cpu as a candidate. */
- compute_prev_delta = true;
+ prev_spare_cap = cpu_cap;
} else if (cpu_cap > max_spare_cap) {
/*
* Find the CPU with the maximum spare capacity
- * in the performance domain.
+ * among the remaining CPUs in the performance
+ * domain.
*/
max_spare_cap = cpu_cap;
max_spare_cap_cpu = cpu;
}
}
- if (max_spare_cap_cpu < 0 && !compute_prev_delta)
+ if (max_spare_cap_cpu < 0 && prev_spare_cap == 0)
continue;
eenv_pd_busy_time(&eenv, cpus, p);
@@ -7302,7 +7303,7 @@ 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 (compute_prev_delta) {
+ if (prev_spare_cap > 0) {
prev_delta = compute_energy(&eenv, pd, cpus, p,
prev_cpu);
/* CPU utilization has changed */
@@ -7313,7 +7314,7 @@ 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) {
+ if (max_spare_cap_cpu >= 0 && max_spare_cap > prev_spare_cap) {
cur_delta = compute_energy(&eenv, pd, cpus, p,
max_spare_cap_cpu);
/* CPU utilization has changed */