[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <535E3673.8020606@linaro.org>
Date: Mon, 28 Apr 2014 13:07:31 +0200
From: Daniel Lezcano <daniel.lezcano@...aro.org>
To: Peter Zijlstra <peterz@...radead.org>
CC: "Rafael J. Wysocki" <rjw@...ysocki.net>,
Amit Kucheria <amit.kucheria@...aro.org>,
Ingo Molnar <mingo@...e.hu>,
Lists linaro-kernel <linaro-kernel@...ts.linaro.org>,
Linux PM list <linux-pm@...r.kernel.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 2/3] sched: idle: Add sched balance option
On 04/28/2014 12:28 PM, Peter Zijlstra wrote:
> On Mon, Apr 28, 2014 at 12:09:20PM +0200, Daniel Lezcano wrote:
>> I agree a numerical value is not flexible. But it sounds weird to put a
>> scheduler option in the sysfs and maybe more options will follow.
>>
>> I am wondering if we shouldn't create a new cgroup for 'energy' and put
>> everything in there. So we will have more flexibility for extension and we
>> will be able to create a group of tasks for performance and a group of tasks
>> for energy saving.
>>
>> Does it make sense ?
>
> The old knobs used to live here:
>
> -What: /sys/devices/system/cpu/sched_mc_power_savings
> - /sys/devices/system/cpu/sched_smt_power_savings
Ah right.
> Not entirely sure that's a fine place, but it has precedent.
I share your doubts about the right place.
I'm really wondering if the cgroup couldn't be a good solution:
Amit pointed the conflict about the power vs performance with some
applications. We want to have for example a game to run fast performance
and some other application to save power.
The cgroup will allow to:
* eg. create a couple of cgroup one for performance and the other one
for power and assign the different applications to one of these group
* tweak the options just for a group of processes. Depending of the
behavior of the task, the userspace can create and change some options
for a specific application for optimum performance or energy saving
* add more energy options in a place easy to extend
* use string based options
* alternatively use a single configuration for the entire system
* use the event based file to trigger event about power consumption
(threshold reached) and from there we can easily freeze the group of
processes consuming too much energy
The cgroup will provide a highly configurable mechanism based on tasks
and could use with some other cgroup subsys (eg. to force the tasks on a
set of cpus).
IMHO, the cgroup is a good place.
--
<http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs
Follow Linaro: <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists