Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754268AbbGPAce (ORCPT ); Wed, 15 Jul 2015 20:32:34 -0400 Received: from know-smtprelay-omc-7.server.virginmedia.net ([80.0.253.71]:32790 "EHLO know-smtprelay-omc-7.server.virginmedia.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754012AbbGPAcc (ORCPT ); Wed, 15 Jul 2015 20:32:32 -0400 X-Originating-IP: [81.106.150.188] X-Spam: 0 X-Authority: v=2.1 cv=JuUM15MC c=1 sm=1 tr=0 a=DGj713NdaxKrsjjgQne7PA==:117 a=DGj713NdaxKrsjjgQne7PA==:17 a=NLZqzBF-AAAA:8 a=yEdEr6MRgwAA:10 a=IkcTkHD0fZMA:10 a=zOBTXjUuO1YA:10 a=D35dV9kuNp-bsEUCEdIA:9 a=QEXdDO2ut3YA:10 Date: Thu, 16 Jul 2015 01:32:18 +0100 From: Ken Moffat To: Frederic Weisbecker Cc: LKML , Jeff Epler Subject: Re: CONFIG_NO_HZ_FULL restricts cpu usage to the equivalent of one in 4.2 Message-ID: <20150716003218.GA15221@milliways> References: <20150715162713.GA29360@milliways> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline X-Clacks-Overhead: GNU Terry Pratchett Content-Transfer-Encoding: 8bit In-Reply-To: User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1440 Lines: 37 On Wed, Jul 15, 2015 at 09:11:46PM +0200, Frederic Weisbecker wrote: > 2015-07-15 18:27 GMT+02:00 Ken Moffat : > > > > The config differences follow. Perhaps it is actually one of the > > subsequent choices that is the problem. And I guess it could still > > be a gcc-5.1 issue. > > > > --- config-4.2-initial 2015-07-15 16:25:12.548005751 +0100 > > +++ config-4.2-speed-ok 2015-07-15 17:00:50.919998703 +0100 > > @@ -104,11 +104,8 @@ > > CONFIG_TICK_ONESHOT=y > > CONFIG_NO_HZ_COMMON=y > > # CONFIG_HZ_PERIODIC is not set > > -# CONFIG_NO_HZ_IDLE is not set > > -CONFIG_NO_HZ_FULL=y > > -CONFIG_NO_HZ_FULL_ALL=y > > You had CONFIG_NO_HZ_FULL_ALL enabled? Because that would indeed > produce that effect since it isolates all CPUs but 0 off sched > domains. > > Which means that basically only CPU 0 runs user tasks unless you > forces these otherwise. Thanks. I'll put it down to a bad .config choice, although it was fine on early 4.1. While I was starting to bisect, I noticed that on the A10 everything was happening on CPU 0 - not sure if that was happening on the original box, but for the moment it sounds likely. ĸen -- This one goes up to eleven! -- 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/