All of lore.kernel.org
 help / color / mirror / Atom feed
From: Yuyang Du <yuyang.du@intel.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Dirk Brandewie <dirk.brandewie@gmail.com>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>,
	Morten Rasmussen <morten.rasmussen@arm.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-pm@vger.kernel.org" <linux-pm@vger.kernel.org>,
	"mingo@kernel.org" <mingo@kernel.org>,
	"vincent.guittot@linaro.org" <vincent.guittot@linaro.org>,
	"daniel.lezcano@linaro.org" <daniel.lezcano@linaro.org>,
	"preeti@linux.vnet.ibm.com" <preeti@linux.vnet.ibm.com>,
	Dietmar Eggemann <Dietmar.Eggemann@arm.com>,
	len.brown@intel.com, jacob.jun.pan@linux.intel.com
Subject: Re: [RFC PATCH 06/16] arm: topology: Define TC2 sched energy and provide it to scheduler
Date: Wed, 11 Jun 2014 02:35:05 +0800	[thread overview]
Message-ID: <20140610183505.GC5487@intel.com> (raw)
In-Reply-To: <20140610101622.GB6758@twins.programming.kicks-ass.net>

On Tue, Jun 10, 2014 at 12:16:22PM +0200, Peter Zijlstra wrote:
> What other target would you optimize for? The purpose here is to build
> an energy aware scheduler, one that schedules tasks so that the total
> amount of energy, for the given amount of work, is minimal.
> 
> So we can't measure in Watt, since if we forced the CPU into the lowest
> P-state (or even C-state for that matter) work would simply not
> complete. So we need a complete energy term.
> 
> Now. IPC is instructions/cycle, Watt is Joule/second, so IPC/Watt is
> 
> instructions   second
> ------------ * ------ ~ instructions / joule
>   cycle        joule
> 
> Seeing how both cycles and seconds are time units.
> 
> So for any given amount of instructions, the work needs to be done, we
> want the minimal amount of energy consumed, and IPC/Watt is the natural
> metric to measure this over an entire workload.

Ok, I understand. Whether we take IPC/watt as an input metric in scheduler or
as a goal for scheduler, we definitely need to try both.

Thanks, Peter.

Yuyang

  parent reply	other threads:[~2014-06-11  2:39 UTC|newest]

Thread overview: 71+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-05-23 18:16 [RFC PATCH 00/16] sched: Energy cost model for energy-aware scheduling Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 01/16] sched: Documentation for scheduler energy cost model Morten Rasmussen
2014-06-05  8:49   ` Vincent Guittot
2014-06-05 11:35     ` Morten Rasmussen
2014-06-05 15:02       ` Vincent Guittot
2014-05-23 18:16 ` [RFC PATCH 02/16] sched: Introduce CONFIG_SCHED_ENERGY Morten Rasmussen
2014-06-08  6:03   ` Henrik Austad
2014-06-09 10:20     ` Morten Rasmussen
2014-06-10  9:39       ` Peter Zijlstra
2014-06-10 10:06         ` Morten Rasmussen
2014-06-10 10:23           ` Peter Zijlstra
2014-06-10 11:17             ` Henrik Austad
2014-06-10 12:19               ` Peter Zijlstra
2014-06-10 11:24             ` Morten Rasmussen
2014-06-10 12:24               ` Peter Zijlstra
2014-06-10 14:41                 ` Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 03/16] sched: Introduce sd energy data structures Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 04/16] sched: Allocate and initialize sched energy Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 05/16] sched: Add sd energy procfs interface Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 06/16] arm: topology: Define TC2 sched energy and provide it to scheduler Morten Rasmussen
2014-05-30 12:04   ` Peter Zijlstra
2014-06-02 14:15     ` Morten Rasmussen
2014-06-03 11:41       ` Peter Zijlstra
2014-06-04 13:49         ` Morten Rasmussen
2014-06-03 11:44   ` Peter Zijlstra
2014-06-04 15:42     ` Morten Rasmussen
2014-06-04 16:16       ` Peter Zijlstra
2014-06-06 13:15         ` Morten Rasmussen
2014-06-06 13:43           ` Peter Zijlstra
2014-06-06 14:29             ` Morten Rasmussen
2014-06-12 15:05               ` Vince Weaver
2014-06-03 11:50   ` Peter Zijlstra
2014-06-04 16:02     ` Morten Rasmussen
2014-06-04 17:27       ` Peter Zijlstra
2014-06-04 21:56         ` Rafael J. Wysocki
2014-06-05  6:52           ` Peter Zijlstra
2014-06-05 15:03             ` Dirk Brandewie
2014-06-05 20:29               ` Yuyang Du
2014-06-06  8:05                 ` Peter Zijlstra
2014-06-06  0:35                   ` Yuyang Du
2014-06-06 10:50                     ` Peter Zijlstra
2014-06-06 12:13                       ` Ingo Molnar
2014-06-06 12:27                         ` Ingo Molnar
2014-06-06 14:11                           ` Morten Rasmussen
2014-06-07  2:33                           ` Nicolas Pitre
2014-06-09  8:27                             ` Morten Rasmussen
2014-06-09 13:22                               ` Nicolas Pitre
2014-06-11 11:02                                 ` Eduardo Valentin
2014-06-11 11:42                                   ` Morten Rasmussen
2014-06-11 11:43                                     ` Eduardo Valentin
2014-06-11 13:37                                       ` Morten Rasmussen
2014-06-07 23:53                         ` Yuyang Du
2014-06-07 23:26                       ` Yuyang Du
2014-06-09  8:59                         ` Morten Rasmussen
2014-06-09  2:15                           ` Yuyang Du
2014-06-10 10:16                         ` Peter Zijlstra
2014-06-10 17:01                           ` Nicolas Pitre
2014-06-10 18:35                           ` Yuyang Du [this message]
2014-06-06 16:27                     ` Jacob Pan
2014-06-06 13:03         ` Morten Rasmussen
2014-06-07  2:52         ` Nicolas Pitre
2014-05-23 18:16 ` [RFC PATCH 07/16] sched: Introduce system-wide sched_energy Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 08/16] sched: Introduce SD_SHARE_CAP_STATES sched_domain flag Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 09/16] sched, cpufreq: Introduce current cpu compute capacity into scheduler Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 10/16] sched, cpufreq: Current compute capacity hack for ARM TC2 Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 11/16] sched: Energy model functions Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 12/16] sched: Task wakeup tracking Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 13/16] sched: Take task wakeups into account in energy estimates Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 14/16] sched: Use energy model in select_idle_sibling Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 15/16] sched: Use energy to guide wakeup task placement Morten Rasmussen
2014-05-23 18:16 ` [RFC PATCH 16/16] sched: Disable wake_affine to broaden the scope of wakeup target cpus Morten Rasmussen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20140610183505.GC5487@intel.com \
    --to=yuyang.du@intel.com \
    --cc=Dietmar.Eggemann@arm.com \
    --cc=daniel.lezcano@linaro.org \
    --cc=dirk.brandewie@gmail.com \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=morten.rasmussen@arm.com \
    --cc=peterz@infradead.org \
    --cc=preeti@linux.vnet.ibm.com \
    --cc=rjw@rjwysocki.net \
    --cc=vincent.guittot@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.