davidlt/kernel-ark
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
0538421343
kernel-ark/include/linux/tick.h
Rafael J. Wysocki b7eaf1aab9 cpufreq: schedutil: Avoid reducing frequency of busy CPUs prematurely 
The way the schedutil governor uses the PELT metric causes it to
underestimate the CPU utilization in some cases.

That can be easily demonstrated by running kernel compilation on
a Sandy Bridge Intel processor, running turbostat in parallel with
it and looking at the values written to the MSR_IA32_PERF_CTL
register.  Namely, the expected result would be that when all CPUs
were 100% busy, all of them would be requested to run in the maximum
P-state, but observation shows that this clearly isn't the case.
The CPUs run in the maximum P-state for a while and then are
requested to run slower and go back to the maximum P-state after
a while again.  That causes the actual frequency of the processor to
visibly oscillate below the sustainable maximum in a jittery fashion
which clearly is not desirable.

That has been attributed to CPU utilization metric updates on task
migration that cause the total utilization value for the CPU to be
reduced by the utilization of the migrated task.  If that happens,
the schedutil governor may see a CPU utilization reduction and will
attempt to reduce the CPU frequency accordingly right away.  That
may be premature, though, for example if the system is generally
busy and there are other runnable tasks waiting to be run on that
CPU already.

This is unlikely to be an issue on systems where cpufreq policies are
shared between multiple CPUs, because in those cases the policy
utilization is computed as the maximum of the CPU utilization values
over the whole policy and if that turns out to be low, reducing the
frequency for the policy most likely is a good idea anyway.  On
systems with one CPU per policy, however, it may affect performance
adversely and even lead to increased energy consumption in some cases.

On those systems it may be addressed by taking another utilization
metric into consideration, like whether or not the CPU whose
frequency is about to be reduced has been idle recently, because if
that's not the case, the CPU is likely to be busy in the near future
and its frequency should not be reduced.

To that end, use the counter of idle calls in the timekeeping code.
Namely, make the schedutil governor look at that counter for the
current CPU every time before its frequency is about to be reduced.
If the counter has not changed since the previous iteration of the
governor computations for that CPU, the CPU has been busy for all
that time and its frequency should not be decreased, so if the new
frequency would be lower than the one set previously, the governor
will skip the frequency update.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Joel Fernandes <joelaf@google.com>
2017-03-23 02:12:14 +01:00

297 lines
8.4 KiB
C
Raw Blame History

/*
* Tick related global functions
*/
#ifndef _LINUX_TICK_H
#define _LINUX_TICK_H
#include <linux/clockchips.h>
#include <linux/irqflags.h>
#include <linux/percpu.h>
#include <linux/context_tracking_state.h>
#include <linux/cpumask.h>
#include <linux/sched.h>
#ifdef CONFIG_GENERIC_CLOCKEVENTS
extern void __init tick_init(void);
/* Should be core only, but ARM BL switcher requires it */
extern void tick_suspend_local(void);
/* Should be core only, but XEN resume magic and ARM BL switcher require it */
extern void tick_resume_local(void);
extern void tick_handover_do_timer(void);
extern void tick_cleanup_dead_cpu(int cpu);
#else /* CONFIG_GENERIC_CLOCKEVENTS */
static inline void tick_init(void) { }
static inline void tick_suspend_local(void) { }
static inline void tick_resume_local(void) { }
static inline void tick_handover_do_timer(void) { }
static inline void tick_cleanup_dead_cpu(int cpu) { }
#endif /* !CONFIG_GENERIC_CLOCKEVENTS */
#if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_SUSPEND)
extern void tick_freeze(void);
extern void tick_unfreeze(void);
#else
static inline void tick_freeze(void) { }
static inline void tick_unfreeze(void) { }
#endif
#ifdef CONFIG_TICK_ONESHOT
extern void tick_irq_enter(void);
# ifndef arch_needs_cpu
# define arch_needs_cpu() (0)
# endif
# else
static inline void tick_irq_enter(void) { }
#endif
#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
extern void hotplug_cpu__broadcast_tick_pull(int dead_cpu);
#else
static inline void hotplug_cpu__broadcast_tick_pull(int dead_cpu) { }
#endif
enum tick_broadcast_mode {
TICK_BROADCAST_OFF,
TICK_BROADCAST_ON,
TICK_BROADCAST_FORCE,
};
enum tick_broadcast_state {
TICK_BROADCAST_EXIT,
TICK_BROADCAST_ENTER,
};
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
extern void tick_broadcast_control(enum tick_broadcast_mode mode);
#else
static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { }
#endif /* BROADCAST */
#ifdef CONFIG_GENERIC_CLOCKEVENTS
extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state);
#else
static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
{
return 0;
}
#endif
static inline void tick_broadcast_enable(void)
{
tick_broadcast_control(TICK_BROADCAST_ON);
}
static inline void tick_broadcast_disable(void)
{
tick_broadcast_control(TICK_BROADCAST_OFF);
}
static inline void tick_broadcast_force(void)
{
tick_broadcast_control(TICK_BROADCAST_FORCE);
}
static inline int tick_broadcast_enter(void)
{
return tick_broadcast_oneshot_control(TICK_BROADCAST_ENTER);
}
static inline void tick_broadcast_exit(void)
{
tick_broadcast_oneshot_control(TICK_BROADCAST_EXIT);
}
enum tick_dep_bits {
TICK_DEP_BIT_POSIX_TIMER = 0,
TICK_DEP_BIT_PERF_EVENTS = 1,
TICK_DEP_BIT_SCHED = 2,
TICK_DEP_BIT_CLOCK_UNSTABLE = 3
};
#define TICK_DEP_MASK_NONE 0
#define TICK_DEP_MASK_POSIX_TIMER (1 << TICK_DEP_BIT_POSIX_TIMER)
#define TICK_DEP_MASK_PERF_EVENTS (1 << TICK_DEP_BIT_PERF_EVENTS)
#define TICK_DEP_MASK_SCHED (1 << TICK_DEP_BIT_SCHED)
#define TICK_DEP_MASK_CLOCK_UNSTABLE (1 << TICK_DEP_BIT_CLOCK_UNSTABLE)
#ifdef CONFIG_NO_HZ_COMMON
extern bool tick_nohz_enabled;
extern int tick_nohz_tick_stopped(void);
extern void tick_nohz_idle_enter(void);
extern void tick_nohz_idle_exit(void);
extern void tick_nohz_irq_exit(void);
extern ktime_t tick_nohz_get_sleep_length(void);
extern unsigned long tick_nohz_get_idle_calls(void);
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
#else /* !CONFIG_NO_HZ_COMMON */
#define tick_nohz_enabled (0)
static inline int tick_nohz_tick_stopped(void) { return 0; }
static inline void tick_nohz_idle_enter(void) { }
static inline void tick_nohz_idle_exit(void) { }
static inline ktime_t tick_nohz_get_sleep_length(void)
{
return NSEC_PER_SEC / HZ;
}
static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
#endif /* !CONFIG_NO_HZ_COMMON */
#ifdef CONFIG_NO_HZ_FULL
extern bool tick_nohz_full_running;
extern cpumask_var_t tick_nohz_full_mask;
extern cpumask_var_t housekeeping_mask;
static inline bool tick_nohz_full_enabled(void)
{
if (!context_tracking_is_enabled())
return false;
return tick_nohz_full_running;
}
static inline bool tick_nohz_full_cpu(int cpu)
{
if (!tick_nohz_full_enabled())
return false;
return cpumask_test_cpu(cpu, tick_nohz_full_mask);
}
static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask)
{
if (tick_nohz_full_enabled())
cpumask_or(mask, mask, tick_nohz_full_mask);
}
static inline int housekeeping_any_cpu(void)
{
return cpumask_any_and(housekeeping_mask, cpu_online_mask);
}
extern void tick_nohz_dep_set(enum tick_dep_bits bit);
extern void tick_nohz_dep_clear(enum tick_dep_bits bit);
extern void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit);
extern void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit);
extern void tick_nohz_dep_set_task(struct task_struct *tsk,
enum tick_dep_bits bit);
extern void tick_nohz_dep_clear_task(struct task_struct *tsk,
enum tick_dep_bits bit);
extern void tick_nohz_dep_set_signal(struct signal_struct *signal,
enum tick_dep_bits bit);
extern void tick_nohz_dep_clear_signal(struct signal_struct *signal,
enum tick_dep_bits bit);
/*
* The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases
* on top of static keys.
*/
static inline void tick_dep_set(enum tick_dep_bits bit)
{
if (tick_nohz_full_enabled())
tick_nohz_dep_set(bit);
}
static inline void tick_dep_clear(enum tick_dep_bits bit)
{
if (tick_nohz_full_enabled())
tick_nohz_dep_clear(bit);
}
static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit)
{
if (tick_nohz_full_cpu(cpu))
tick_nohz_dep_set_cpu(cpu, bit);
}
static inline void tick_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
{
if (tick_nohz_full_cpu(cpu))
tick_nohz_dep_clear_cpu(cpu, bit);
}
static inline void tick_dep_set_task(struct task_struct *tsk,
enum tick_dep_bits bit)
{
if (tick_nohz_full_enabled())
tick_nohz_dep_set_task(tsk, bit);
}
static inline void tick_dep_clear_task(struct task_struct *tsk,
enum tick_dep_bits bit)
{
if (tick_nohz_full_enabled())
tick_nohz_dep_clear_task(tsk, bit);
}
static inline void tick_dep_set_signal(struct signal_struct *signal,
enum tick_dep_bits bit)
{
if (tick_nohz_full_enabled())
tick_nohz_dep_set_signal(signal, bit);
}
static inline void tick_dep_clear_signal(struct signal_struct *signal,
enum tick_dep_bits bit)
{
if (tick_nohz_full_enabled())
tick_nohz_dep_clear_signal(signal, bit);
}
extern void tick_nohz_full_kick_cpu(int cpu);
extern void __tick_nohz_task_switch(void);
#else
static inline int housekeeping_any_cpu(void)
{
return smp_processor_id();
}
static inline bool tick_nohz_full_enabled(void) { return false; }
static inline bool tick_nohz_full_cpu(int cpu) { return false; }
static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { }
static inline void tick_dep_set(enum tick_dep_bits bit) { }
static inline void tick_dep_clear(enum tick_dep_bits bit) { }
static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) { }
static inline void tick_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { }
static inline void tick_dep_set_task(struct task_struct *tsk,
enum tick_dep_bits bit) { }
static inline void tick_dep_clear_task(struct task_struct *tsk,
enum tick_dep_bits bit) { }
static inline void tick_dep_set_signal(struct signal_struct *signal,
enum tick_dep_bits bit) { }
static inline void tick_dep_clear_signal(struct signal_struct *signal,
enum tick_dep_bits bit) { }
static inline void tick_nohz_full_kick_cpu(int cpu) { }
static inline void __tick_nohz_task_switch(void) { }
#endif
static inline const struct cpumask *housekeeping_cpumask(void)
{
#ifdef CONFIG_NO_HZ_FULL
if (tick_nohz_full_enabled())
return housekeeping_mask;
#endif
return cpu_possible_mask;
}
static inline bool is_housekeeping_cpu(int cpu)
{
#ifdef CONFIG_NO_HZ_FULL
if (tick_nohz_full_enabled())
return cpumask_test_cpu(cpu, housekeeping_mask);
#endif
return true;
}
static inline void housekeeping_affine(struct task_struct *t)
{
#ifdef CONFIG_NO_HZ_FULL
if (tick_nohz_full_enabled())
set_cpus_allowed_ptr(t, housekeeping_mask);
#endif
}
static inline void tick_nohz_task_switch(void)
{
if (tick_nohz_full_enabled())
__tick_nohz_task_switch();
}
#endif
Reference in New Issue View Git Blame Copy Permalink