From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752586AbbDCTUn (ORCPT ); Fri, 3 Apr 2015 15:20:43 -0400 Received: from mail-am1on0057.outbound.protection.outlook.com ([157.56.112.57]:59147 "EHLO emea01-am1-obe.outbound.protection.outlook.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751923AbbDCTUm (ORCPT ); Fri, 3 Apr 2015 15:20:42 -0400 Message-ID: <551EE7F4.6070406@ezchip.com> Date: Fri, 3 Apr 2015 15:20:20 -0400 From: Chris Metcalf User-Agent: Mozilla/5.0 (X11; Linux i686 on x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.6.0 MIME-Version: 1.0 To: Frederic Weisbecker , Rik van Riel CC: "Peter Zijlstra (Intel)" , "Paul E. McKenney" , "Rafael J. Wysocki" , Martin Schwidefsky , Ingo Molnar , Subject: Re: [PATCH 2/2] nohz: make nohz_full imply isolcpus References: <1428078248-5425-1-git-send-email-cmetcalf@ezchip.com> <1428078248-5425-2-git-send-email-cmetcalf@ezchip.com> <20150403174258.GC13598@lerouge> In-Reply-To: <20150403174258.GC13598@lerouge> Content-Type: text/plain; charset="windows-1252"; format=flowed Content-Transfer-Encoding: 7bit X-Originating-IP: [12.216.194.146] X-ClientProxiedBy: CO2PR11CA0042.namprd11.prod.outlook.com (10.141.242.180) To AM2PR02MB0769.eurprd02.prod.outlook.com (25.163.146.154) Authentication-Results: vger.kernel.org; dkim=none (message not signed) header.d=none; X-Microsoft-Antispam: UriScan:;BCL:0;PCL:0;RULEID:;SRVR:AM2PR02MB0769;UriScan:;BCL:0;PCL:0;RULEID:;SRVR:AM2PR02MB0675; X-Microsoft-Antispam-PRVS: X-Forefront-Antispam-Report: BMV:1;SFV:NSPM;SFS:(10009020)(6009001)(6049001)(479174004)(41574002)(24454002)(51704005)(377454003)(50986999)(33656002)(62966003)(76176999)(42186005)(65816999)(575784001)(15975445007)(77096005)(2950100001)(36756003)(77156002)(92566002)(50466002)(87976001)(54356999)(86362001)(46102003)(19580395003)(80316001)(65956001)(40100003)(19580405001)(65806001)(122386002)(83506001)(47776003)(66066001)(18886065003);DIR:OUT;SFP:1101;SCL:1;SRVR:AM2PR02MB0769;H:[10.7.0.41];FPR:;SPF:None;MLV:sfv;LANG:en; X-Exchange-Antispam-Report-Test: UriScan:; X-Exchange-Antispam-Report-CFA-Test: BCL:0;PCL:0;RULEID:(601004)(5005006)(5002010);SRVR:AM2PR02MB0769;BCL:0;PCL:0;RULEID:;SRVR:AM2PR02MB0769; X-Forefront-PRVS: 05352A48BE X-MS-Exchange-CrossTenant-OriginalArrivalTime: 03 Apr 2015 19:20:36.2150 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-Transport-CrossTenantHeadersStamped: AM2PR02MB0769 X-OriginatorOrg: ezchip.com Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 04/03/2015 01:42 PM, Frederic Weisbecker wrote: > On Fri, Apr 03, 2015 at 12:24:08PM -0400, cmetcalf@ezchip.com wrote: >> From: Chris Metcalf >> >> It's not clear that nohz_full is useful without isolcpus also >> set, since otherwise the scheduler has to run periodically to >> try to determine whether to steal work from other cores. >> >> Signed-off-by: Chris Metcalf > I think Rick has a similar patch. I didn't see anything relevant in linux-next, though I did see cpu_isolated_map made into a public symbol in a recent commit by Rik. Rik, what's the change you're proposing that's similar to this one? Thanks! >> --- >> I am puzzled why this has not been done before, so I suspect >> there is some argument against it that I am missing, but I >> wasn't able to turn anything up by searching LKML. >> >> kernel/sched/core.c | 1 + >> 1 file changed, 1 insertion(+) >> >> diff --git a/kernel/sched/core.c b/kernel/sched/core.c >> index f0f831e8a345..275f12c608f2 100644 >> --- a/kernel/sched/core.c >> +++ b/kernel/sched/core.c >> @@ -6836,6 +6836,7 @@ static int init_sched_domains(const struct cpumask *cpu_map) >> doms_cur = alloc_sched_domains(ndoms_cur); >> if (!doms_cur) >> doms_cur = &fallback_doms; >> + tick_nohz_full_set_cpus(cpu_isolated_map); >> cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); >> err = build_sched_domains(doms_cur[0], NULL); >> register_sched_domain_sysctl(); >> -- >> 2.1.2 >> -- Chris Metcalf, EZChip Semiconductor http://www.ezchip.com