From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752154Ab3FWXdq (ORCPT ); Sun, 23 Jun 2013 19:33:46 -0400 Received: from gate.crashing.org ([63.228.1.57]:57898 "EHLO gate.crashing.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751891Ab3FWXdp (ORCPT ); Sun, 23 Jun 2013 19:33:45 -0400 Message-ID: <1372030320.3944.114.camel@pasglop> Subject: Re: power-efficient scheduling design From: Benjamin Herrenschmidt To: Arjan van de Ven Cc: Catalin Marinas , Morten Rasmussen , David Lang , "len.brown@intel.com" , "alex.shi@intel.com" , "corbet@lwn.net" , "peterz@infradead.org" , Linus Torvalds , "efault@gmx.de" , "linux-kernel@vger.kernel.org" , "linaro-kernel@lists.linaro.org" , "preeti@linux.vnet.ibm.com" , Andrew Morton , "pjt@google.com" , Ingo Molnar Date: Mon, 24 Jun 2013 09:32:00 +1000 In-Reply-To: <51C4C6C8.1050008@linux.intel.com> References: <20130530134718.GB32728@e103034-lin> <20130531105204.GE30394@gmail.com> <20130614160522.GG32728@e103034-lin> <51C07ABC.2080704@linux.intel.com> <51C1D0BB.3040705@linux.intel.com> <20130619170042.GH5460@e103034-lin> <51C1E58D.9000408@linux.intel.com> <20130621085002.GJ5460@e103034-lin> <51C47377.2000208@linux.intel.com> <51C4C6C8.1050008@linux.intel.com> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.6.4-0ubuntu1 Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2013-06-21 at 14:34 -0700, Arjan van de Ven wrote: > On 6/21/2013 2:23 PM, Catalin Marinas wrote: > >> > >> oops sorry I misread your mail (lack of early coffee I suppose) > >> > >> I can see your point of having a thing for "did we ask for all the performance > >> we could ask for" prior to doing a load balance (although, for power efficiency, > >> if you have two tasks that could run in parallel, it's usually better to > >> run them in parallel... so likely we should balance anyway) > > > > Not necessarily, especially if parallel running implies powering up a > > full cluster just for one CPU (it depends on the hardware but for > > example a cluster may not be able to go in deeper sleep states unless > > all the CPUs in that cluster are idle). > > I guess it depends on the system Sort-of. We have something similar with threads on ppc. IE, the core can only really stop if all threads are. From a Linux persepctive it's a matter of how we define the scope of that 'cluster' Catalin is talking about. I'm sure you do too. Then there is the package, which adds MC etc... > the very first cpu needs to power on > * the core itself > * the "cluster" that you mention > * the memory controller > * the memory (out of self refresh) > > while the second cpu needs > * the core itself > * maybe a second cluster > > normally on Intel systems, the memory power delta is quite significant > which then means the efficiency of the second core is huge compared to > running things in sequence. What's your typical latency for bringing an MC back (and memory out of self refresh) ? IE. Basically bringing a package back up ? Cheers, Ben. > -- > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > Please read the FAQ at http://www.tux.org/lkml/