forked from mirrors/linux
sched/fair: Move effective_cpu_util() and effective_cpu_util() in fair.c
Move effective_cpu_util() and sched_cpu_util() functions in fair.c file with others utilization related functions. No functional change. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20240904092417.20660-1-vincent.guittot@linaro.org
This commit is contained in:
Vincent Guittot
Peter Zijlstra
parent
3dcac251b0
commit
5d871a6399
2 changed files with 99 additions and 101 deletions
|
|
@ -8084,6 +8084,105 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p)
|
|||
return cpu_util(cpu, p, -1, 0);
|
||||
}
|
||||
|
||||
/*
|
||||
* This function computes an effective utilization for the given CPU, to be
|
||||
* used for frequency selection given the linear relation: f = u * f_max.
|
||||
*
|
||||
* The scheduler tracks the following metrics:
|
||||
*
|
||||
* cpu_util_{cfs,rt,dl,irq}()
|
||||
* cpu_bw_dl()
|
||||
*
|
||||
* Where the cfs,rt and dl util numbers are tracked with the same metric and
|
||||
* synchronized windows and are thus directly comparable.
|
||||
*
|
||||
* The cfs,rt,dl utilization are the running times measured with rq->clock_task
|
||||
* which excludes things like IRQ and steal-time. These latter are then accrued
|
||||
* in the IRQ utilization.
|
||||
*
|
||||
* The DL bandwidth number OTOH is not a measured metric but a value computed
|
||||
* based on the task model parameters and gives the minimal utilization
|
||||
* required to meet deadlines.
|
||||
*/
|
||||
unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
|
||||
unsigned long *min,
|
||||
unsigned long *max)
|
||||
{
|
||||
unsigned long util, irq, scale;
|
||||
struct rq *rq = cpu_rq(cpu);
|
||||
|
||||
scale = arch_scale_cpu_capacity(cpu);
|
||||
|
||||
/*
|
||||
* Early check to see if IRQ/steal time saturates the CPU, can be
|
||||
* because of inaccuracies in how we track these -- see
|
||||
* update_irq_load_avg().
|
||||
*/
|
||||
irq = cpu_util_irq(rq);
|
||||
if (unlikely(irq >= scale)) {
|
||||
if (min)
|
||||
*min = scale;
|
||||
if (max)
|
||||
*max = scale;
|
||||
return scale;
|
||||
}
|
||||
|
||||
if (min) {
|
||||
/*
|
||||
* The minimum utilization returns the highest level between:
|
||||
* - the computed DL bandwidth needed with the IRQ pressure which
|
||||
* steals time to the deadline task.
|
||||
* - The minimum performance requirement for CFS and/or RT.
|
||||
*/
|
||||
*min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN));
|
||||
|
||||
/*
|
||||
* When an RT task is runnable and uclamp is not used, we must
|
||||
* ensure that the task will run at maximum compute capacity.
|
||||
*/
|
||||
if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt))
|
||||
*min = max(*min, scale);
|
||||
}
|
||||
|
||||
/*
|
||||
* Because the time spend on RT/DL tasks is visible as 'lost' time to
|
||||
* CFS tasks and we use the same metric to track the effective
|
||||
* utilization (PELT windows are synchronized) we can directly add them
|
||||
* to obtain the CPU's actual utilization.
|
||||
*/
|
||||
util = util_cfs + cpu_util_rt(rq);
|
||||
util += cpu_util_dl(rq);
|
||||
|
||||
/*
|
||||
* The maximum hint is a soft bandwidth requirement, which can be lower
|
||||
* than the actual utilization because of uclamp_max requirements.
|
||||
*/
|
||||
if (max)
|
||||
*max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX));
|
||||
|
||||
if (util >= scale)
|
||||
return scale;
|
||||
|
||||
/*
|
||||
* There is still idle time; further improve the number by using the
|
||||
* IRQ metric. Because IRQ/steal time is hidden from the task clock we
|
||||
* need to scale the task numbers:
|
||||
*
|
||||
* max - irq
|
||||
* U' = irq + --------- * U
|
||||
* max
|
||||
*/
|
||||
util = scale_irq_capacity(util, irq, scale);
|
||||
util += irq;
|
||||
|
||||
return min(scale, util);
|
||||
}
|
||||
|
||||
unsigned long sched_cpu_util(int cpu)
|
||||
{
|
||||
return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL);
|
||||
}
|
||||
|
||||
/*
|
||||
* energy_env - Utilization landscape for energy estimation.
|
||||
* @task_busy_time: Utilization contribution by the task for which we test the
|
||||
|
|
|
|||
|
|
@ -258,107 +258,6 @@ int sched_core_idle_cpu(int cpu)
|
|||
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
/*
|
||||
* This function computes an effective utilization for the given CPU, to be
|
||||
* used for frequency selection given the linear relation: f = u * f_max.
|
||||
*
|
||||
* The scheduler tracks the following metrics:
|
||||
*
|
||||
* cpu_util_{cfs,rt,dl,irq}()
|
||||
* cpu_bw_dl()
|
||||
*
|
||||
* Where the cfs,rt and dl util numbers are tracked with the same metric and
|
||||
* synchronized windows and are thus directly comparable.
|
||||
*
|
||||
* The cfs,rt,dl utilization are the running times measured with rq->clock_task
|
||||
* which excludes things like IRQ and steal-time. These latter are then accrued
|
||||
* in the IRQ utilization.
|
||||
*
|
||||
* The DL bandwidth number OTOH is not a measured metric but a value computed
|
||||
* based on the task model parameters and gives the minimal utilization
|
||||
* required to meet deadlines.
|
||||
*/
|
||||
unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
|
||||
unsigned long *min,
|
||||
unsigned long *max)
|
||||
{
|
||||
unsigned long util, irq, scale;
|
||||
struct rq *rq = cpu_rq(cpu);
|
||||
|
||||
scale = arch_scale_cpu_capacity(cpu);
|
||||
|
||||
/*
|
||||
* Early check to see if IRQ/steal time saturates the CPU, can be
|
||||
* because of inaccuracies in how we track these -- see
|
||||
* update_irq_load_avg().
|
||||
*/
|
||||
irq = cpu_util_irq(rq);
|
||||
if (unlikely(irq >= scale)) {
|
||||
if (min)
|
||||
*min = scale;
|
||||
if (max)
|
||||
*max = scale;
|
||||
return scale;
|
||||
}
|
||||
|
||||
if (min) {
|
||||
/*
|
||||
* The minimum utilization returns the highest level between:
|
||||
* - the computed DL bandwidth needed with the IRQ pressure which
|
||||
* steals time to the deadline task.
|
||||
* - The minimum performance requirement for CFS and/or RT.
|
||||
*/
|
||||
*min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN));
|
||||
|
||||
/*
|
||||
* When an RT task is runnable and uclamp is not used, we must
|
||||
* ensure that the task will run at maximum compute capacity.
|
||||
*/
|
||||
if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt))
|
||||
*min = max(*min, scale);
|
||||
}
|
||||
|
||||
/*
|
||||
* Because the time spend on RT/DL tasks is visible as 'lost' time to
|
||||
* CFS tasks and we use the same metric to track the effective
|
||||
* utilization (PELT windows are synchronized) we can directly add them
|
||||
* to obtain the CPU's actual utilization.
|
||||
*/
|
||||
util = util_cfs + cpu_util_rt(rq);
|
||||
util += cpu_util_dl(rq);
|
||||
|
||||
/*
|
||||
* The maximum hint is a soft bandwidth requirement, which can be lower
|
||||
* than the actual utilization because of uclamp_max requirements.
|
||||
*/
|
||||
if (max)
|
||||
*max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX));
|
||||
|
||||
if (util >= scale)
|
||||
return scale;
|
||||
|
||||
/*
|
||||
* There is still idle time; further improve the number by using the
|
||||
* IRQ metric. Because IRQ/steal time is hidden from the task clock we
|
||||
* need to scale the task numbers:
|
||||
*
|
||||
* max - irq
|
||||
* U' = irq + --------- * U
|
||||
* max
|
||||
*/
|
||||
util = scale_irq_capacity(util, irq, scale);
|
||||
util += irq;
|
||||
|
||||
return min(scale, util);
|
||||
}
|
||||
|
||||
unsigned long sched_cpu_util(int cpu)
|
||||
{
|
||||
return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL);
|
||||
}
|
||||
#endif /* CONFIG_SMP */
|
||||
|
||||
/**
|
||||
* find_process_by_pid - find a process with a matching PID value.
|
||||
* @pid: the pid in question.
|
||||
|
|
|
|||
Loading…
Reference in a new issue