[lkml]   [2018]   [Mar]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRE: [RFT][PATCH v7 5/8] cpuidle: Return nohz hint from cpuidle_select()
On 2018.03.21 23:25 Doug Smythies wrote:
> On 2018.03.21 15:15 Rafael J. Wysocki wrote:
>> On Wed, Mar 21, 2018 at 6:59 PM, Thomas Ilsche wrote:
>>> On 2018-03-21 15:36, Rafael J. Wysocki wrote:
>>>> So please disregard this one entirely and take the v7.2 replacement
>>>> instead of it:
>>>> The current versions (including the above) is in the git branch at
>>>> git:// \
>>>> idle-loop-v7.2
>>> With v7.2 (tested on SKL-SP from git) I see similar behavior in idle
>>> as with v5: several cores which just keep the sched tick enabled.
>>> Worse yet, some go only in C1 (not even C1E!?) despite sleeping the
>>> full sched tick.
>>> The resulting power consumption is ~105 W instead of ~ 70 W.
>>> I have briefly ran v7 and I believe it was also affected.

I am not seeing any issues at all with V7.

>> Then it looks like menu_select() stubbornly thinks that the idle
>> duration will be within the tick boundary on those cores.
>> That may be because the bumping up of the correction factor in
>> menu_reflect() is too conservative or it may be necessary to do
>> something radical to measured_us in menu_update() in case of a tick
>> wakeup combined with a large next_timer_us value.
>> For starters, please see if the attached patch (on top of the
>> idle-loop-v7.2 git branch) changes this behavior in any way.
> O.K. I am seeing some weirdness.
> On my system with both V7.2 and V7.2 plus this patch, I observe
> A spike in Idle State 1 residency every 34+ minutes. And slightly
> higher average idle power than before.
> (I might not have done V7 idle tests long enough).

I re-did the idle test on V7, and for longer.
It is great.
See line added to the idle graph for V7.2+:

> It can be seen in the frequency sweep I did earlier today, with V7.2:
> Despite the note on the graph that says it might be real, I don't think
> it is (I forgot to delete the note).
> With V7.2+ sometimes the event occurs at 17 minute intervals.
> Here is a idle graph (for reference: we have seen idle package power
> pretty steady at ~3.7 watts before).

Now shown on the new graph. Link above.


... Doug

 \ /
  Last update: 2018-03-22 16:42    [W:0.163 / U:0.380 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site