Current idle time in kstat is based on jiffies and is coarse grained.
tick_sched.idle_sleeptime is making some attempt to keep track of
idle time in a fine grained manner. But, it is not handling
the time spent in interrupts fully.
Make tick_sched.idle_sleeptime accurate with respect to time spent on
handling interrupts and also add tick_sched.idle_lastupdate, which
keeps track of last time when idle_sleeptime was updated.
This statistics will be crucial for cpufreq-ondemand governor, which can shed
some conservative gaurd band that is uses today while setting the frequency.
The ondemand changes that uses the exact idle time is coming soon.
Signed-off-by: Venkatesh Pallipadi <[EMAIL PROTECTED]>
Index: linux-2.6.22/kernel/time/tick-sched.c
===================================================================
--- linux-2.6.22.orig/kernel/time/tick-sched.c
+++ linux-2.6.22/kernel/time/tick-sched.c
@@ -141,6 +141,43 @@ void tick_nohz_update_jiffies(void)
local_irq_restore(flags);
}
+void tick_nohz_stop_idle(int cpu)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+ if (ts->idle_active) {
+ ktime_t now, delta;
+ now = ktime_get();
+ delta = ktime_sub(now, ts->idle_entrytime);
+ ts->idle_lastupdate = now;
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+ ts->idle_active = 0;
+ }
+}
+
+static void tick_nohz_start_idle(int cpu)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t now, delta;
+
+ now = ktime_get();
+ if (ts->idle_active) {
+ delta = ktime_sub(now, ts->idle_entrytime);
+ ts->idle_lastupdate = now;
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+ }
+ ts->idle_entrytime = now;
+ ts->idle_active = 1;
+}
+
+u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+ *last_update_time = ktime_to_us(ts->idle_lastupdate);
+ return ktime_to_us(ts->idle_sleeptime);
+}
+
/**
* tick_nohz_stop_sched_tick - stop the idle tick from the idle task
*
@@ -152,13 +189,15 @@ void tick_nohz_stop_sched_tick(void)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
struct tick_sched *ts;
- ktime_t last_update, expires, now, delta;
+ ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
int cpu;
local_irq_save(flags);
cpu = smp_processor_id();
+ tick_nohz_start_idle(cpu);
+
ts = &per_cpu(tick_cpu_sched, cpu);
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
@@ -178,19 +217,7 @@ void tick_nohz_stop_sched_tick(void)
}
}
- now = ktime_get();
- /*
- * When called from irq_exit we need to account the idle sleep time
- * correctly.
- */
- if (ts->tick_stopped) {
- delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
- }
-
- ts->idle_entrytime = now;
ts->idle_calls++;
-
/* Read jiffies and the time when jiffies were updated last */
do {
seq = read_seqbegin(&xtime_lock);
@@ -320,23 +347,22 @@ void tick_nohz_restart_sched_tick(void)
int cpu = smp_processor_id();
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
unsigned long ticks;
- ktime_t now, delta;
+ ktime_t now;
+
+ local_irq_disable();
+ tick_nohz_stop_idle(cpu);
- if (!ts->tick_stopped)
+ if (!ts->tick_stopped) {
+ local_irq_enable();
return;
+ }
/* Update jiffies first */
- now = ktime_get();
-
- local_irq_disable();
select_nohz_load_balancer(0);
+ now = ktime_get();
tick_do_update_jiffies64(now);
cpu_clear(cpu, nohz_cpu_mask);
- /* Account the idle time */
- delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-
/*
* We stopped the tick in idle. Update process times would miss the
* time we slept as update_process_times does only a 1 tick
Index: linux-2.6.22/include/linux/tick.h
===================================================================
--- linux-2.6.22.orig/include/linux/tick.h
+++ linux-2.6.22/include/linux/tick.h
@@ -51,8 +51,10 @@ struct tick_sched {
unsigned long idle_jiffies;
unsigned long idle_calls;
unsigned long idle_sleeps;
+ int idle_active;
ktime_t idle_entrytime;
ktime_t idle_sleeptime;
+ ktime_t idle_lastupdate;
ktime_t sleep_length;
unsigned long last_jiffies;
unsigned long next_jiffies;
@@ -103,6 +105,8 @@ extern void tick_nohz_stop_sched_tick(vo
extern void tick_nohz_restart_sched_tick(void);
extern void tick_nohz_update_jiffies(void);
extern ktime_t tick_nohz_get_sleep_length(void);
+extern void tick_nohz_stop_idle(int cpu);
+extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
# else
static inline void tick_nohz_stop_sched_tick(void) { }
static inline void tick_nohz_restart_sched_tick(void) { }
@@ -113,6 +117,8 @@ static inline ktime_t tick_nohz_get_slee
return len;
}
+static inline void tick_nohz_stop_idle(int cpu) { }
+static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return 0; }
# endif /* !NO_HZ */
#endif
Index: linux-2.6.22/kernel/softirq.c
===================================================================
--- linux-2.6.22.orig/kernel/softirq.c
+++ linux-2.6.22/kernel/softirq.c
@@ -280,9 +280,14 @@ EXPORT_SYMBOL(do_softirq);
*/
void irq_enter(void)
{
+#ifdef CONFIG_NO_HZ
+ int cpu = smp_processor_id();
+ if (idle_cpu(cpu) && !in_interrupt())
+ tick_nohz_stop_idle(cpu);
+#endif
__irq_enter();
#ifdef CONFIG_NO_HZ
- if (idle_cpu(smp_processor_id()))
+ if (idle_cpu(cpu))
tick_nohz_update_jiffies();
#endif
}
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
