system/linux
system/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2024-10-15 15:59:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

sched/fair: Refactor CPU utilization functions

Browse source 
There is a lot of code duplication in cpu_util_next() & cpu_util_cfs().

Remove this by allowing cpu_util_next() to be called with p = NULL.
Rename cpu_util_next() to cpu_util() since the '_next' suffix is no
longer necessary to distinct cpu utilization related functions.
Implement cpu_util_cfs(cpu) as cpu_util(cpu, p = NULL, -1).

This will allow to code future related cpu util changes only in one
place, namely in cpu_util().

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230515115735.296329-2-dietmar.eggemann@arm.com
This commit is contained in:
Dietmar Eggemann 2023-05-15 13:57:34 +02:00 committed by Peter Zijlstra
parent e6a15fa9ea
commit 3eb6d6ecec
2 changed files with 49 additions and 59 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

61
kernel/sched/fair.c
View file

@ -7202,11 +7202,41 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
return target;
}
/*
* Predicts what cpu_util(@cpu) would return if @p was removed from @cpu
* (@dst_cpu = -1) or migrated to @dst_cpu.
/**
* cpu_util() - Estimates the amount of CPU capacity used by CFS tasks.
* @cpu: the CPU to get the utilization for
* @p: task for which the CPU utilization should be predicted or NULL
* @dst_cpu: CPU @p migrates to, -1 if @p moves from @cpu or @p == NULL
*
* The unit of the return value must be the same as the one of CPU capacity
* so that CPU utilization can be compared with CPU capacity.
*
* CPU utilization is the sum of running time of runnable tasks plus the
* recent utilization of currently non-runnable tasks on that CPU.
* It represents the amount of CPU capacity currently used by CFS tasks in
* the range [0..max CPU capacity] with max CPU capacity being the CPU
* capacity at f_max.
*
* The estimated CPU utilization is defined as the maximum between CPU
* utilization and sum of the estimated utilization of the currently
* runnable tasks on that CPU. It preserves a utilization "snapshot" of
* previously-executed tasks, which helps better deduce how busy a CPU will
* be when a long-sleeping task wakes up. The contribution to CPU utilization
* of such a task would be significantly decayed at this point of time.
*
* CPU utilization can be higher than the current CPU capacity
* (f_curr/f_max * max CPU capacity) or even the max CPU capacity because
* of rounding errors as well as task migrations or wakeups of new tasks.
* CPU utilization has to be capped to fit into the [0..max CPU capacity]
* range. Otherwise a group of CPUs (CPU0 util = 121% + CPU1 util = 80%)
* could be seen as over-utilized even though CPU1 has 20% of spare CPU
* capacity. CPU utilization is allowed to overshoot current CPU capacity
* though since this is useful for predicting the CPU capacity required
* after task migrations (scheduler-driven DVFS).
*
* Return: (Estimated) utilization for the specified CPU.
*/
static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
static unsigned long cpu_util(int cpu, struct task_struct *p, int dst_cpu)
{
struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs;
unsigned long util = READ_ONCE(cfs_rq->avg.util_avg);
@ -7217,9 +7247,9 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
* contribution. In all the other cases @cpu is not impacted by the
* migration so its util_avg is already correct.
*/
if (task_cpu(p) == cpu && dst_cpu != cpu)
if (p && task_cpu(p) == cpu && dst_cpu != cpu)
lsub_positive(&util, task_util(p));
else if (task_cpu(p) != cpu && dst_cpu == cpu)
else if (p && task_cpu(p) != cpu && dst_cpu == cpu)
util += task_util(p);
if (sched_feat(UTIL_EST)) {
@ -7255,7 +7285,7 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
*/
if (dst_cpu == cpu)
util_est += _task_util_est(p);
else if (unlikely(task_on_rq_queued(p) || current == p))
else if (p && unlikely(task_on_rq_queued(p) || current == p))
lsub_positive(&util_est, _task_util_est(p));
util = max(util, util_est);
@ -7264,6 +7294,11 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
return min(util, capacity_orig_of(cpu));
}
unsigned long cpu_util_cfs(int cpu)
{
return cpu_util(cpu, NULL, -1);
}
/*
* cpu_util_without: compute cpu utilization without any contributions from *p
* @cpu: the CPU which utilization is requested
@ -7281,9 +7316,9 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p)
{
/* Task has no contribution or is new */
if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
return cpu_util_cfs(cpu);
p = NULL;
return cpu_util_next(cpu, p, -1);
return cpu_util(cpu, p, -1);
}
/*
@ -7330,7 +7365,7 @@ static inline void eenv_task_busy_time(struct energy_env *eenv,
* cpu_capacity.
*
* The contribution of the task @p for which we want to estimate the
* energy cost is removed (by cpu_util_next()) and must be calculated
* energy cost is removed (by cpu_util()) and must be calculated
* separately (see eenv_task_busy_time). This ensures:
*
* - A stable PD utilization, no matter which CPU of that PD we want to place
@ -7351,7 +7386,7 @@ static inline void eenv_pd_busy_time(struct energy_env *eenv,
int cpu;
for_each_cpu(cpu, pd_cpus) {
unsigned long util = cpu_util_next(cpu, p, -1);
unsigned long util = cpu_util(cpu, p, -1);
busy_time += effective_cpu_util(cpu, util, ENERGY_UTIL, NULL);
}
@ -7375,7 +7410,7 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
for_each_cpu(cpu, pd_cpus) {
struct task_struct *tsk = (cpu == dst_cpu) ? p : NULL;
unsigned long util = cpu_util_next(cpu, p, dst_cpu);
unsigned long util = cpu_util(cpu, p, dst_cpu);
unsigned long cpu_util;
/*
@ -7521,7 +7556,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
if (!cpumask_test_cpu(cpu, p->cpus_ptr))
continue;
util = cpu_util_next(cpu, p, cpu);
util = cpu_util(cpu, p, cpu);
cpu_cap = capacity_of(cpu);
/*

47
kernel/sched/sched.h
View file

@ -2955,53 +2955,8 @@ static inline unsigned long cpu_util_dl(struct rq *rq)
return READ_ONCE(rq->avg_dl.util_avg);
}
/**
* cpu_util_cfs() - Estimates the amount of CPU capacity used by CFS tasks.
* @cpu: the CPU to get the utilization for.
*
* The unit of the return value must be the same as the one of CPU capacity
* so that CPU utilization can be compared with CPU capacity.
*
* CPU utilization is the sum of running time of runnable tasks plus the
* recent utilization of currently non-runnable tasks on that CPU.
* It represents the amount of CPU capacity currently used by CFS tasks in
* the range [0..max CPU capacity] with max CPU capacity being the CPU
* capacity at f_max.
*
* The estimated CPU utilization is defined as the maximum between CPU
* utilization and sum of the estimated utilization of the currently
* runnable tasks on that CPU. It preserves a utilization "snapshot" of
* previously-executed tasks, which helps better deduce how busy a CPU will
* be when a long-sleeping task wakes up. The contribution to CPU utilization
* of such a task would be significantly decayed at this point of time.
*
* CPU utilization can be higher than the current CPU capacity
* (f_curr/f_max * max CPU capacity) or even the max CPU capacity because
* of rounding errors as well as task migrations or wakeups of new tasks.
* CPU utilization has to be capped to fit into the [0..max CPU capacity]
* range. Otherwise a group of CPUs (CPU0 util = 121% + CPU1 util = 80%)
* could be seen as over-utilized even though CPU1 has 20% of spare CPU
* capacity. CPU utilization is allowed to overshoot current CPU capacity
* though since this is useful for predicting the CPU capacity required
* after task migrations (scheduler-driven DVFS).
*
* Return: (Estimated) utilization for the specified CPU.
*/
static inline unsigned long cpu_util_cfs(int cpu)
{
struct cfs_rq *cfs_rq;
unsigned long util;
cfs_rq = &cpu_rq(cpu)->cfs;
util = READ_ONCE(cfs_rq->avg.util_avg);
if (sched_feat(UTIL_EST)) {
util = max_t(unsigned long, util,
READ_ONCE(cfs_rq->avg.util_est.enqueued));
}
return min(util, capacity_orig_of(cpu));
}
extern unsigned long cpu_util_cfs(int cpu);
static inline unsigned long cpu_util_rt(struct rq *rq)
{