linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH] tick/nohz: Make the idle_exittime update correctly
@ 2020-12-05  9:41 Yunfeng Ye
  2020-12-15 12:06 ` Yunfeng Ye
  2021-02-19 12:33 ` Frederic Weisbecker
  0 siblings, 2 replies; 7+ messages in thread
From: Yunfeng Ye @ 2020-12-05  9:41 UTC (permalink / raw)
  To: fweisbec, tglx, mingo, linux-kernel; +Cc: Shiyuan Hu, Hewenliang

The idle_exittime field of tick_sched is used to record the time when
the idle state was left. but currently the idle_exittime is updated in
the function tick_nohz_restart_sched_tick(), which is not always in idle
state when nohz_full is configured.

  tick_irq_exit
    tick_nohz_irq_exit
      tick_nohz_full_update_tick
        tick_nohz_restart_sched_tick
          ts->idle_exittime = now;

So move to tick_nohz_stop_idle() to make the idle_exittime update
correctly.

Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
---
 kernel/time/tick-sched.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 749ec2a583de..be2e5d772d50 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -591,6 +591,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
 {
 	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
 	ts->idle_active = 0;
+	ts->idle_exittime = now;

 	sched_clock_idle_wakeup_event();
 }
@@ -901,7 +902,6 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 	 * Cancel the scheduled timer and restore the tick
 	 */
 	ts->tick_stopped  = 0;
-	ts->idle_exittime = now;

 	tick_nohz_restart(ts, now);
 }
-- 
2.18.4

^ permalink raw reply related	[flat|nested] 7+ messages in thread

* [PATCH] tick/nohz: Make the idle_exittime update correctly
  2020-12-05  9:41 [PATCH] tick/nohz: Make the idle_exittime update correctly Yunfeng Ye
@ 2020-12-15 12:06 ` Yunfeng Ye
  2020-12-15 14:47   ` Frederic Weisbecker
  2021-02-19 12:33 ` Frederic Weisbecker
  1 sibling, 1 reply; 7+ messages in thread
From: Yunfeng Ye @ 2020-12-15 12:06 UTC (permalink / raw)
  To: fweisbec, tglx, mingo, linux-kernel; +Cc: Shiyuan Hu, Hewenliang

The idle_exittime field of tick_sched is used to record the time when
the idle state was left. but currently the idle_exittime is updated in
the function tick_nohz_restart_sched_tick(), which is not always in idle
state when nohz_full is configured.

  tick_irq_exit
    tick_nohz_irq_exit
      tick_nohz_full_update_tick
        tick_nohz_restart_sched_tick
          ts->idle_exittime = now;

So move to tick_nohz_stop_idle() to make the idle_exittime update
correctly.

Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
---
 kernel/time/tick-sched.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 749ec2a583de..be2e5d772d50 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -591,6 +591,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
 {
 	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
 	ts->idle_active = 0;
+	ts->idle_exittime = now;

 	sched_clock_idle_wakeup_event();
 }
@@ -901,7 +902,6 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 	 * Cancel the scheduled timer and restore the tick
 	 */
 	ts->tick_stopped  = 0;
-	ts->idle_exittime = now;

 	tick_nohz_restart(ts, now);
 }
-- 
2.18.4


^ permalink raw reply related	[flat|nested] 7+ messages in thread

* Re: [PATCH] tick/nohz: Make the idle_exittime update correctly
  2020-12-15 12:06 ` Yunfeng Ye
@ 2020-12-15 14:47   ` Frederic Weisbecker
  2020-12-17  6:51     ` Yunfeng Ye
  0 siblings, 1 reply; 7+ messages in thread
From: Frederic Weisbecker @ 2020-12-15 14:47 UTC (permalink / raw)
  To: Yunfeng Ye; +Cc: fweisbec, tglx, mingo, linux-kernel, Shiyuan Hu, Hewenliang

On Tue, Dec 15, 2020 at 08:06:34PM +0800, Yunfeng Ye wrote:
> The idle_exittime field of tick_sched is used to record the time when
> the idle state was left. but currently the idle_exittime is updated in
> the function tick_nohz_restart_sched_tick(), which is not always in idle
> state when nohz_full is configured.
> 
>   tick_irq_exit
>     tick_nohz_irq_exit
>       tick_nohz_full_update_tick
>         tick_nohz_restart_sched_tick
>           ts->idle_exittime = now;
> 
> So move to tick_nohz_stop_idle() to make the idle_exittime update
> correctly.
> 
> Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
> ---
>  kernel/time/tick-sched.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
> index 749ec2a583de..be2e5d772d50 100644
> --- a/kernel/time/tick-sched.c
> +++ b/kernel/time/tick-sched.c
> @@ -591,6 +591,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
>  {
>  	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
>  	ts->idle_active = 0;
> +	ts->idle_exittime = now;

This changes a bit the meaning of idle_exittime then since this is also called
from idle interrupt entry.

__tick_nohz_idle_restart_tick() would be a better place.

Thanks.

> 
>  	sched_clock_idle_wakeup_event();
>  }
> @@ -901,7 +902,6 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
>  	 * Cancel the scheduled timer and restore the tick
>  	 */
>  	ts->tick_stopped  = 0;
> -	ts->idle_exittime = now;
> 
>  	tick_nohz_restart(ts, now);
>  }
> -- 
> 2.18.4
> 

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH] tick/nohz: Make the idle_exittime update correctly
  2020-12-15 14:47   ` Frederic Weisbecker
@ 2020-12-17  6:51     ` Yunfeng Ye
  2020-12-17 13:59       ` Frederic Weisbecker
  0 siblings, 1 reply; 7+ messages in thread
From: Yunfeng Ye @ 2020-12-17  6:51 UTC (permalink / raw)
  To: Frederic Weisbecker
  Cc: fweisbec, tglx, mingo, linux-kernel, Shiyuan Hu, Hewenliang



On 2020/12/15 22:47, Frederic Weisbecker wrote:
> On Tue, Dec 15, 2020 at 08:06:34PM +0800, Yunfeng Ye wrote:
>> The idle_exittime field of tick_sched is used to record the time when
>> the idle state was left. but currently the idle_exittime is updated in
>> the function tick_nohz_restart_sched_tick(), which is not always in idle
>> state when nohz_full is configured.
>>
>>   tick_irq_exit
>>     tick_nohz_irq_exit
>>       tick_nohz_full_update_tick
>>         tick_nohz_restart_sched_tick
>>           ts->idle_exittime = now;
>>
>> So move to tick_nohz_stop_idle() to make the idle_exittime update
>> correctly.
>>
>> Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
>> ---
>>  kernel/time/tick-sched.c | 2 +-
>>  1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
>> index 749ec2a583de..be2e5d772d50 100644
>> --- a/kernel/time/tick-sched.c
>> +++ b/kernel/time/tick-sched.c
>> @@ -591,6 +591,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
>>  {
>>  	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
>>  	ts->idle_active = 0;
>> +	ts->idle_exittime = now;
> 
> This changes a bit the meaning of idle_exittime then since this is also called
> from idle interrupt entry.
> 
> __tick_nohz_idle_restart_tick() would be a better place.
> 
So is it necessary to modify the comment "@idle_exittime:      Time when the idle state was left" ?

On the other hand, if the patch "nohz: Update tick instead of restarting tick in tick_nohz_idle_exit()"
(https://www.spinics.net/lists/kernel/msg3747039.html ) applied, __tick_nohz_idle_restart_tick will not
be called always, So is it put here also a better place?

Thanks.

> Thanks.
> 
>>
>>  	sched_clock_idle_wakeup_event();
>>  }
>> @@ -901,7 +902,6 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
>>  	 * Cancel the scheduled timer and restore the tick
>>  	 */
>>  	ts->tick_stopped  = 0;
>> -	ts->idle_exittime = now;
>>
>>  	tick_nohz_restart(ts, now);
>>  }
>> -- 
>> 2.18.4
>>
> .
> 

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH] tick/nohz: Make the idle_exittime update correctly
  2020-12-17  6:51     ` Yunfeng Ye
@ 2020-12-17 13:59       ` Frederic Weisbecker
  2020-12-18  0:54         ` Yunfeng Ye
  0 siblings, 1 reply; 7+ messages in thread
From: Frederic Weisbecker @ 2020-12-17 13:59 UTC (permalink / raw)
  To: Yunfeng Ye; +Cc: fweisbec, tglx, mingo, linux-kernel, Shiyuan Hu, Hewenliang

On Thu, Dec 17, 2020 at 02:51:58PM +0800, Yunfeng Ye wrote:
> 
> 
> On 2020/12/15 22:47, Frederic Weisbecker wrote:
> > On Tue, Dec 15, 2020 at 08:06:34PM +0800, Yunfeng Ye wrote:
> >> The idle_exittime field of tick_sched is used to record the time when
> >> the idle state was left. but currently the idle_exittime is updated in
> >> the function tick_nohz_restart_sched_tick(), which is not always in idle
> >> state when nohz_full is configured.
> >>
> >>   tick_irq_exit
> >>     tick_nohz_irq_exit
> >>       tick_nohz_full_update_tick
> >>         tick_nohz_restart_sched_tick
> >>           ts->idle_exittime = now;
> >>
> >> So move to tick_nohz_stop_idle() to make the idle_exittime update
> >> correctly.
> >>
> >> Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
> >> ---
> >>  kernel/time/tick-sched.c | 2 +-
> >>  1 file changed, 1 insertion(+), 1 deletion(-)
> >>
> >> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
> >> index 749ec2a583de..be2e5d772d50 100644
> >> --- a/kernel/time/tick-sched.c
> >> +++ b/kernel/time/tick-sched.c
> >> @@ -591,6 +591,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
> >>  {
> >>  	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
> >>  	ts->idle_active = 0;
> >> +	ts->idle_exittime = now;
> > 
> > This changes a bit the meaning of idle_exittime then since this is also called
> > from idle interrupt entry.
> > 
> > __tick_nohz_idle_restart_tick() would be a better place.
> > 
> So is it necessary to modify the comment "@idle_exittime:      Time when the idle state was left" ?
> 
> On the other hand, if the patch "nohz: Update tick instead of restarting tick in tick_nohz_idle_exit()"
> (https://www.spinics.net/lists/kernel/msg3747039.html ) applied, __tick_nohz_idle_restart_tick will not
> be called always, So is it put here also a better place?

Right but I need to re-order some code before. That's ok, I'll integrate this
patch inside the changes.

Thanks.

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH] tick/nohz: Make the idle_exittime update correctly
  2020-12-17 13:59       ` Frederic Weisbecker
@ 2020-12-18  0:54         ` Yunfeng Ye
  0 siblings, 0 replies; 7+ messages in thread
From: Yunfeng Ye @ 2020-12-18  0:54 UTC (permalink / raw)
  To: Frederic Weisbecker
  Cc: fweisbec, tglx, mingo, linux-kernel, Shiyuan Hu, Hewenliang



On 2020/12/17 21:59, Frederic Weisbecker wrote:
> On Thu, Dec 17, 2020 at 02:51:58PM +0800, Yunfeng Ye wrote:
>>
>>
>> On 2020/12/15 22:47, Frederic Weisbecker wrote:
>>> On Tue, Dec 15, 2020 at 08:06:34PM +0800, Yunfeng Ye wrote:
>>>> The idle_exittime field of tick_sched is used to record the time when
>>>> the idle state was left. but currently the idle_exittime is updated in
>>>> the function tick_nohz_restart_sched_tick(), which is not always in idle
>>>> state when nohz_full is configured.
>>>>
>>>>   tick_irq_exit
>>>>     tick_nohz_irq_exit
>>>>       tick_nohz_full_update_tick
>>>>         tick_nohz_restart_sched_tick
>>>>           ts->idle_exittime = now;
>>>>
>>>> So move to tick_nohz_stop_idle() to make the idle_exittime update
>>>> correctly.
>>>>
>>>> Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
>>>> ---
>>>>  kernel/time/tick-sched.c | 2 +-
>>>>  1 file changed, 1 insertion(+), 1 deletion(-)
>>>>
>>>> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
>>>> index 749ec2a583de..be2e5d772d50 100644
>>>> --- a/kernel/time/tick-sched.c
>>>> +++ b/kernel/time/tick-sched.c
>>>> @@ -591,6 +591,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
>>>>  {
>>>>  	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
>>>>  	ts->idle_active = 0;
>>>> +	ts->idle_exittime = now;
>>>
>>> This changes a bit the meaning of idle_exittime then since this is also called
>>> from idle interrupt entry.
>>>
>>> __tick_nohz_idle_restart_tick() would be a better place.
>>>
>> So is it necessary to modify the comment "@idle_exittime:      Time when the idle state was left" ?
>>
>> On the other hand, if the patch "nohz: Update tick instead of restarting tick in tick_nohz_idle_exit()"
>> (https://www.spinics.net/lists/kernel/msg3747039.html ) applied, __tick_nohz_idle_restart_tick will not
>> be called always, So is it put here also a better place?
> 
> Right but I need to re-order some code before. That's ok, I'll integrate this
> patch inside the changes.
> 
Ok, thanks.

> Thanks.
> .
> 

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH] tick/nohz: Make the idle_exittime update correctly
  2020-12-05  9:41 [PATCH] tick/nohz: Make the idle_exittime update correctly Yunfeng Ye
  2020-12-15 12:06 ` Yunfeng Ye
@ 2021-02-19 12:33 ` Frederic Weisbecker
  1 sibling, 0 replies; 7+ messages in thread
From: Frederic Weisbecker @ 2021-02-19 12:33 UTC (permalink / raw)
  To: Yunfeng Ye; +Cc: fweisbec, tglx, mingo, linux-kernel, Shiyuan Hu, Hewenliang

On Sat, Dec 05, 2020 at 05:41:52PM +0800, Yunfeng Ye wrote:
> The idle_exittime field of tick_sched is used to record the time when
> the idle state was left. but currently the idle_exittime is updated in
> the function tick_nohz_restart_sched_tick(), which is not always in idle
> state when nohz_full is configured.
> 
>   tick_irq_exit
>     tick_nohz_irq_exit
>       tick_nohz_full_update_tick
>         tick_nohz_restart_sched_tick
>           ts->idle_exittime = now;
> 
> So move to tick_nohz_stop_idle() to make the idle_exittime update
> correctly.
> 
> Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
> ---
>  kernel/time/tick-sched.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
> index 749ec2a583de..be2e5d772d50 100644
> --- a/kernel/time/tick-sched.c
> +++ b/kernel/time/tick-sched.c
> @@ -591,6 +591,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
>  {
>  	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
>  	ts->idle_active = 0;
> +	ts->idle_exittime = now;
> 
>  	sched_clock_idle_wakeup_event();
>  }
> @@ -901,7 +902,6 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
>  	 * Cancel the scheduled timer and restore the tick
>  	 */
>  	ts->tick_stopped  = 0;
> -	ts->idle_exittime = now;
> 
>  	tick_nohz_restart(ts, now);
>  }

Hi,

I've edited and queued on top of latest changes, see below. I'll post it after
the merge window.

---
From: Yunfeng Ye <yeyunfeng@huawei.com>
Date: Wed, 10 Feb 2021 00:08:54 +0100
Subject: [PATCH] tick/nohz: Update idle_exittime on actual idle exit

The idle_exittime field of tick_sched is used to record the time when
the idle state was left. but currently the idle_exittime is updated in
the function tick_nohz_restart_sched_tick(), which is not always in idle
state when nohz_full is configured:

  tick_irq_exit
    tick_nohz_irq_exit
      tick_nohz_full_update_tick
        tick_nohz_restart_sched_tick
          ts->idle_exittime = now;

It's thus overwritten by mistake on nohz_full tick restart. Move the
update to the appropriate idle exit path instead.

Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 kernel/time/tick-sched.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 79796286a4ba..2907c762a8fe 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -918,8 +918,6 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 	 * Cancel the scheduled timer and restore the tick
 	 */
 	ts->tick_stopped  = 0;
-	ts->idle_exittime = now;
-
 	tick_nohz_restart(ts, now);
 }
 
@@ -1231,6 +1229,7 @@ static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now)
 	else
 		tick_nohz_restart_sched_tick(ts, now);
 
+	ts->idle_exittime = now;
 	tick_nohz_account_idle_ticks(ts);
 }
 
-- 
2.25.1



^ permalink raw reply related	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2021-02-19 12:33 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-12-05  9:41 [PATCH] tick/nohz: Make the idle_exittime update correctly Yunfeng Ye
2020-12-15 12:06 ` Yunfeng Ye
2020-12-15 14:47   ` Frederic Weisbecker
2020-12-17  6:51     ` Yunfeng Ye
2020-12-17 13:59       ` Frederic Weisbecker
2020-12-18  0:54         ` Yunfeng Ye
2021-02-19 12:33 ` Frederic Weisbecker

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).