Re: power-efficient scheduling design

From: Arjan van de Ven <arjan@linux.intel.com>
To: David Lang <david@lang.hm>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>,
	Preeti U Murthy <preeti@linux.vnet.ibm.com>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Ingo Molnar <mingo@kernel.org>,
	Morten Rasmussen <Morten.Rasmussen@arm.com>,
	"alex.shi@intel.com" <alex.shi@intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Mike Galbraith <efault@gmx.de>, "pjt@google.com" <pjt@google.com>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	linaro-kernel <linaro-kernel@lists.linaro.org>,
	"len.brown@intel.com" <len.brown@intel.com>,
	"corbet@lwn.net" <corbet@lwn.net>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Linux PM list <linux-pm@vger.kernel.org>
Subject: Re: power-efficient scheduling design
Date: Tue, 11 Jun 2013 18:48:58 -0700	[thread overview]
Message-ID: <51B7D38A.7050204@linux.intel.com> (raw)
In-Reply-To: <alpine.DEB.2.02.1306111722470.24968@nftneq.ynat.uz>

On 6/11/2013 5:27 PM, David Lang wrote:
>
> Nobody is saying that this sort of thing should be in the fastpath of the scheduler.
>
> But if the scheduler has a table that tells it the possible states, and the cost to get from the current state to each of these states (and to get back and/or wake up to
> full power), then the scheduler can make the decision on what to do, invoke a routine to make the change (and in the meantime, not be fighting the change by trying to
> schedule processes on a core that's about to be powered off), and then when the change happens, the scheduler will have a new version of the table of possible states and costs
>
> This isn't in the fastpath, it's in the rebalancing logic.

the reality is much more complex unfortunately.
C and P states hang together tightly, and even C state on
one core impacts other cores' performance, just like P state selection
on one core impacts other cores.

(at least for x86, we should really stop talking as if the OS picks the "frequency",
that's just not the case anymore)