OSDN Git Service

tick/nohz: Optimize nohz idle enter
authorGaurav Jindal <Gaurav.Jindal@spreadtrum.com>
Thu, 14 Jul 2016 12:04:20 +0000 (12:04 +0000)
committer0ranko0P <ranko0p@outlook.com>
Wed, 4 Dec 2019 13:45:14 +0000 (21:45 +0800)
tick_nohz_start_idle is called before checking whether the idle tick can be
stopped. If the tick cannot be stopped, calling tick_nohz_start_idle() is
pointless and just wasting CPU cycles.

Only invoke tick_nohz_start_idle() when can_stop_idle_tick() returns true. A
short one minute observation of the effect on ARM64 shows a reduction of calls
by 1.5% thus optimizing the idle entry sequence.

[tglx: Massaged changelog ]

Co-developed-by: Sanjeev Yadav<sanjeev.yadav@spreadtrum.com>
Signed-off-by: Gaurav Jindal<gaurav.jindal@spreadtrum.com>
Link: http://lkml.kernel.org/r/20160714120416.GB21099@gaurav.jindal@spreadtrum.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Francisco Franco <franciscofranco.1990@gmail.com>
Signed-off-by: kdrag0n <dragon@khronodragon.com>
kernel/time/tick-sched.c

index d675f8b..01b279e 100644 (file)
@@ -823,8 +823,6 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
        ktime_t now, expires;
        int cpu = smp_processor_id();
 
-       now = tick_nohz_start_idle(ts);
-
 #ifdef CONFIG_SMP
        if (check_pending_deferrable_timers(cpu))
                raise_softirq_irqoff(TIMER_SOFTIRQ);
@@ -833,6 +831,7 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
        if (can_stop_idle_tick(cpu, ts)) {
                int was_stopped = ts->tick_stopped;
 
+               now = tick_nohz_start_idle(ts);
                ts->idle_calls++;
 
                expires = tick_nohz_stop_sched_tick(ts, now, cpu);