2024-03-26 09:18:34

by Vincent Guittot

[permalink] [raw]
Subject: [PATCH v6 2/5] sched: Take cpufreq feedback into account

Aggregate the different pressures applied on the capacity of CPUs and
create a new function that returns the actual capacity of the CPU:
get_actual_cpu_capacity()

Signed-off-by: Vincent Guittot <[email protected]>
Reviewed-by: Lukasz Luba <[email protected]>
Reviewed-by: Qais Yousef <[email protected]>
Tested-by: Lukasz Luba <[email protected]>
---
kernel/sched/fair.c | 45 +++++++++++++++++++++++++--------------------
1 file changed, 25 insertions(+), 20 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 24a7530a7d3f..1896a3138df3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4965,13 +4965,22 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
trace_sched_util_est_se_tp(&p->se);
}

+static inline unsigned long get_actual_cpu_capacity(int cpu)
+{
+ unsigned long capacity = arch_scale_cpu_capacity(cpu);
+
+ capacity -= max(thermal_load_avg(cpu_rq(cpu)), cpufreq_get_pressure(cpu));
+
+ return capacity;
+}
+
static inline int util_fits_cpu(unsigned long util,
unsigned long uclamp_min,
unsigned long uclamp_max,
int cpu)
{
- unsigned long capacity_orig, capacity_orig_thermal;
unsigned long capacity = capacity_of(cpu);
+ unsigned long capacity_orig;
bool fits, uclamp_max_fits;

/*
@@ -5003,7 +5012,6 @@ static inline int util_fits_cpu(unsigned long util,
* goal is to cap the task. So it's okay if it's getting less.
*/
capacity_orig = arch_scale_cpu_capacity(cpu);
- capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu);

/*
* We want to force a task to fit a cpu as implied by uclamp_max.
@@ -5078,7 +5086,8 @@ static inline int util_fits_cpu(unsigned long util,
* handle the case uclamp_min > uclamp_max.
*/
uclamp_min = min(uclamp_min, uclamp_max);
- if (fits && (util < uclamp_min) && (uclamp_min > capacity_orig_thermal))
+ if (fits && (util < uclamp_min) &&
+ (uclamp_min > get_actual_cpu_capacity(cpu)))
return -1;

return fits;
@@ -7498,7 +7507,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
* Look for the CPU with best capacity.
*/
else if (fits < 0)
- cpu_cap = arch_scale_cpu_capacity(cpu) - thermal_load_avg(cpu_rq(cpu));
+ cpu_cap = get_actual_cpu_capacity(cpu);

/*
* First, select CPU which fits better (-1 being better than 0).
@@ -7991,8 +8000,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
struct root_domain *rd = this_rq()->rd;
int cpu, best_energy_cpu, target = -1;
int prev_fits = -1, best_fits = -1;
- unsigned long best_thermal_cap = 0;
- unsigned long prev_thermal_cap = 0;
+ unsigned long best_actual_cap = 0;
+ unsigned long prev_actual_cap = 0;
struct sched_domain *sd;
struct perf_domain *pd;
struct energy_env eenv;
@@ -8022,7 +8031,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)

for (; pd; pd = pd->next) {
unsigned long util_min = p_util_min, util_max = p_util_max;
- unsigned long cpu_cap, cpu_thermal_cap, util;
+ unsigned long cpu_cap, cpu_actual_cap, util;
long prev_spare_cap = -1, max_spare_cap = -1;
unsigned long rq_util_min, rq_util_max;
unsigned long cur_delta, base_energy;
@@ -8034,18 +8043,17 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
if (cpumask_empty(cpus))
continue;

- /* Account thermal pressure for the energy estimation */
+ /* Account external pressure for the energy estimation */
cpu = cpumask_first(cpus);
- cpu_thermal_cap = arch_scale_cpu_capacity(cpu);
- cpu_thermal_cap -= arch_scale_thermal_pressure(cpu);
+ cpu_actual_cap = get_actual_cpu_capacity(cpu);

- eenv.cpu_cap = cpu_thermal_cap;
+ eenv.cpu_cap = cpu_actual_cap;
eenv.pd_cap = 0;

for_each_cpu(cpu, cpus) {
struct rq *rq = cpu_rq(cpu);

- eenv.pd_cap += cpu_thermal_cap;
+ eenv.pd_cap += cpu_actual_cap;

if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
continue;
@@ -8116,7 +8124,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
if (prev_delta < base_energy)
goto unlock;
prev_delta -= base_energy;
- prev_thermal_cap = cpu_thermal_cap;
+ prev_actual_cap = cpu_actual_cap;
best_delta = min(best_delta, prev_delta);
}

@@ -8131,7 +8139,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
* but best energy cpu has better capacity.
*/
if ((max_fits < 0) &&
- (cpu_thermal_cap <= best_thermal_cap))
+ (cpu_actual_cap <= best_actual_cap))
continue;

cur_delta = compute_energy(&eenv, pd, cpus, p,
@@ -8152,14 +8160,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
best_delta = cur_delta;
best_energy_cpu = max_spare_cap_cpu;
best_fits = max_fits;
- best_thermal_cap = cpu_thermal_cap;
+ best_actual_cap = cpu_actual_cap;
}
}
rcu_read_unlock();

if ((best_fits > prev_fits) ||
((best_fits > 0) && (best_delta < prev_delta)) ||
- ((best_fits < 0) && (best_thermal_cap > prev_thermal_cap)))
+ ((best_fits < 0) && (best_actual_cap > prev_actual_cap)))
target = best_energy_cpu;

return target;
@@ -9564,8 +9572,8 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)

static unsigned long scale_rt_capacity(int cpu)
{
+ unsigned long max = get_actual_cpu_capacity(cpu);
struct rq *rq = cpu_rq(cpu);
- unsigned long max = arch_scale_cpu_capacity(cpu);
unsigned long used, free;
unsigned long irq;

@@ -9577,12 +9585,9 @@ static unsigned long scale_rt_capacity(int cpu)
/*
* avg_rt.util_avg and avg_dl.util_avg track binary signals
* (running and not running) with weights 0 and 1024 respectively.
- * avg_thermal.load_avg tracks thermal pressure and the weighted
- * average uses the actual delta max capacity(load).
*/
used = cpu_util_rt(rq);
used += cpu_util_dl(rq);
- used += thermal_load_avg(rq);

if (unlikely(used >= max))
return 1;
--
2.34.1



Subject: [tip: sched/core] sched/cpufreq: Take cpufreq feedback into account

The following commit has been merged into the sched/core branch of tip:

Commit-ID: f1f8d0a224227e4f19a8a8881dc6355bdfc51230
Gitweb: https://git.kernel.org/tip/f1f8d0a224227e4f19a8a8881dc6355bdfc51230
Author: Vincent Guittot <[email protected]>
AuthorDate: Tue, 26 Mar 2024 10:16:13 +01:00
Committer: Ingo Molnar <[email protected]>
CommitterDate: Wed, 24 Apr 2024 12:07:59 +02:00

sched/cpufreq: Take cpufreq feedback into account

Aggregate the different pressures applied on the capacity of CPUs and
create a new function that returns the actual capacity of the CPU:
get_actual_cpu_capacity().

Signed-off-by: Vincent Guittot <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Tested-by: Lukasz Luba <[email protected]>
Reviewed-by: Lukasz Luba <[email protected]>
Reviewed-by: Qais Yousef <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
---
kernel/sched/fair.c | 45 ++++++++++++++++++++++++--------------------
1 file changed, 25 insertions(+), 20 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bb1ae4e..19199c1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4965,13 +4965,22 @@ done:
trace_sched_util_est_se_tp(&p->se);
}

+static inline unsigned long get_actual_cpu_capacity(int cpu)
+{
+ unsigned long capacity = arch_scale_cpu_capacity(cpu);
+
+ capacity -= max(thermal_load_avg(cpu_rq(cpu)), cpufreq_get_pressure(cpu));
+
+ return capacity;
+}
+
static inline int util_fits_cpu(unsigned long util,
unsigned long uclamp_min,
unsigned long uclamp_max,
int cpu)
{
- unsigned long capacity_orig, capacity_orig_thermal;
unsigned long capacity = capacity_of(cpu);
+ unsigned long capacity_orig;
bool fits, uclamp_max_fits;

/*
@@ -5003,7 +5012,6 @@ static inline int util_fits_cpu(unsigned long util,
* goal is to cap the task. So it's okay if it's getting less.
*/
capacity_orig = arch_scale_cpu_capacity(cpu);
- capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu);

/*
* We want to force a task to fit a cpu as implied by uclamp_max.
@@ -5078,7 +5086,8 @@ static inline int util_fits_cpu(unsigned long util,
* handle the case uclamp_min > uclamp_max.
*/
uclamp_min = min(uclamp_min, uclamp_max);
- if (fits && (util < uclamp_min) && (uclamp_min > capacity_orig_thermal))
+ if (fits && (util < uclamp_min) &&
+ (uclamp_min > get_actual_cpu_capacity(cpu)))
return -1;

return fits;
@@ -7494,7 +7503,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
* Look for the CPU with best capacity.
*/
else if (fits < 0)
- cpu_cap = arch_scale_cpu_capacity(cpu) - thermal_load_avg(cpu_rq(cpu));
+ cpu_cap = get_actual_cpu_capacity(cpu);

/*
* First, select CPU which fits better (-1 being better than 0).
@@ -7987,8 +7996,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
struct root_domain *rd = this_rq()->rd;
int cpu, best_energy_cpu, target = -1;
int prev_fits = -1, best_fits = -1;
- unsigned long best_thermal_cap = 0;
- unsigned long prev_thermal_cap = 0;
+ unsigned long best_actual_cap = 0;
+ unsigned long prev_actual_cap = 0;
struct sched_domain *sd;
struct perf_domain *pd;
struct energy_env eenv;
@@ -8018,7 +8027,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)

for (; pd; pd = pd->next) {
unsigned long util_min = p_util_min, util_max = p_util_max;
- unsigned long cpu_cap, cpu_thermal_cap, util;
+ unsigned long cpu_cap, cpu_actual_cap, util;
long prev_spare_cap = -1, max_spare_cap = -1;
unsigned long rq_util_min, rq_util_max;
unsigned long cur_delta, base_energy;
@@ -8030,18 +8039,17 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
if (cpumask_empty(cpus))
continue;

- /* Account thermal pressure for the energy estimation */
+ /* Account external pressure for the energy estimation */
cpu = cpumask_first(cpus);
- cpu_thermal_cap = arch_scale_cpu_capacity(cpu);
- cpu_thermal_cap -= arch_scale_thermal_pressure(cpu);
+ cpu_actual_cap = get_actual_cpu_capacity(cpu);

- eenv.cpu_cap = cpu_thermal_cap;
+ eenv.cpu_cap = cpu_actual_cap;
eenv.pd_cap = 0;

for_each_cpu(cpu, cpus) {
struct rq *rq = cpu_rq(cpu);

- eenv.pd_cap += cpu_thermal_cap;
+ eenv.pd_cap += cpu_actual_cap;

if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
continue;
@@ -8112,7 +8120,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
if (prev_delta < base_energy)
goto unlock;
prev_delta -= base_energy;
- prev_thermal_cap = cpu_thermal_cap;
+ prev_actual_cap = cpu_actual_cap;
best_delta = min(best_delta, prev_delta);
}

@@ -8127,7 +8135,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
* but best energy cpu has better capacity.
*/
if ((max_fits < 0) &&
- (cpu_thermal_cap <= best_thermal_cap))
+ (cpu_actual_cap <= best_actual_cap))
continue;

cur_delta = compute_energy(&eenv, pd, cpus, p,
@@ -8148,14 +8156,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
best_delta = cur_delta;
best_energy_cpu = max_spare_cap_cpu;
best_fits = max_fits;
- best_thermal_cap = cpu_thermal_cap;
+ best_actual_cap = cpu_actual_cap;
}
}
rcu_read_unlock();

if ((best_fits > prev_fits) ||
((best_fits > 0) && (best_delta < prev_delta)) ||
- ((best_fits < 0) && (best_thermal_cap > prev_thermal_cap)))
+ ((best_fits < 0) && (best_actual_cap > prev_actual_cap)))
target = best_energy_cpu;

return target;
@@ -9560,8 +9568,8 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)

static unsigned long scale_rt_capacity(int cpu)
{
+ unsigned long max = get_actual_cpu_capacity(cpu);
struct rq *rq = cpu_rq(cpu);
- unsigned long max = arch_scale_cpu_capacity(cpu);
unsigned long used, free;
unsigned long irq;

@@ -9573,12 +9581,9 @@ static unsigned long scale_rt_capacity(int cpu)
/*
* avg_rt.util_avg and avg_dl.util_avg track binary signals
* (running and not running) with weights 0 and 1024 respectively.
- * avg_thermal.load_avg tracks thermal pressure and the weighted
- * average uses the actual delta max capacity(load).
*/
used = cpu_util_rt(rq);
used += cpu_util_dl(rq);
- used += thermal_load_avg(rq);

if (unlikely(used >= max))
return 1;