From mboxrd@z Thu Jan 1 00:00:00 1970 From: Lan Tianyu Subject: Re: [RFC PATCH V3 0/3] PM/CPU: Parallel enalbing nonboot cpus with resume devices Date: Thu, 09 Oct 2014 09:18:45 +0800 Message-ID: <5435E275.3030307@intel.com> References: <1411633925-9018-1-git-send-email-tianyu.lan@intel.com> <20141008205441.GJ4750@worktop.programming.kicks-ass.net> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from mga11.intel.com ([192.55.52.93]:18706 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752719AbaJIBXJ (ORCPT ); Wed, 8 Oct 2014 21:23:09 -0400 In-Reply-To: <20141008205441.GJ4750@worktop.programming.kicks-ass.net> Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: Peter Zijlstra Cc: mingo@kernel.org, rafael.j.wysocki@intel.com, toshi.kani@hp.com, akpm@linux-foundation.org, ktkhai@parallels.com, fabf@skynet.be, laijs@cn.fujitsu.com, srivatsa.bhat@linux.vnet.ibm.com, ego@linux.vnet.ibm.com, srivatsa@mit.edu, viresh.kumar@linaro.org, todd.e.brandt@linux.intel.com, tipbot@zytor.com, wangyun@linux.vnet.ibm.com, linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org, Thomas Gleixner On 2014=E5=B9=B410=E6=9C=8809=E6=97=A5 04:54, Peter Zijlstra wrote: > On Thu, Sep 25, 2014 at 04:32:02PM +0800, Lan Tianyu wrote: >> This patchset is to parallel enabling nonboot cpus with resuming dev= ices >> during system resume in order to accelerate S2RAM. From test result = on >> a 8 logical core Haswell machine, system resume time reduces from 34= 7ms >> to 217ms with this patchset. >> >> In the current world, all nonboot cpus are enabled serially during s= ystem >> resume. System resume sequence is that boot cpu enables nonboot cpu = one by >> one and then resume devices. Before resuming devices, there are few = tasks >> assigned to nonboot cpus after they are brought up. This wastes cpu = usage. >> >> This patchset is to allow boot cpu to go forward to resume devices a= fter >> bringing up one nonboot cpu and starting a thread. The thread will b= e in >> charge of bringing up other frozen cpus. The thread will be schedule= d to >> the first online cpu to run . This makes enabling cpu2~x parallel wi= th >> resuming devices. >=20 > So I feel we should really clean up hotplug before doing anything lik= e > this. Its a trainwreck and just piling more and more hacks ontop isn'= t > going to help any. >=20 Hi Peter: Sorry, I don't know the gap of hotplug clearly. Could you elaborate it= ? --=20 Best regards Tianyu Lan