From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752642AbdFTVc6 (ORCPT ); Tue, 20 Jun 2017 17:32:58 -0400 Received: from mx2.suse.de ([195.135.220.15]:39407 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751090AbdFTVc4 (ORCPT ); Tue, 20 Jun 2017 17:32:56 -0400 Date: Tue, 20 Jun 2017 23:32:48 +0200 From: "Luis R. Rodriguez" To: Boqun Feng Cc: "Luis R. Rodriguez" , peterz@infradead.org, paulmck@linux.vnet.ibm.com, oleg@redhat.com, josh@joshtriplett.org, rostedt@goodmis.org, mathieu.desnoyers@efficios.com, jiangshanlai@gmail.com, paul.gortmaker@windriver.com, ebiederm@xmission.com, dmitry.torokhov@gmail.com, linux-kernel@vger.kernel.org Subject: Re: [RFC v2 1/2] swait: add idle variants which don't contribute to load average Message-ID: <20170620213248.GZ21846@wotan.suse.de> References: <87zid92ns2.fsf@xmission.com> <20170615184820.22994-1-mcgrof@kernel.org> <20170615184820.22994-2-mcgrof@kernel.org> <20170616004732.oo2dfpri6p6qjq4s@tardis> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170616004732.oo2dfpri6p6qjq4s@tardis> User-Agent: Mutt/1.6.0 (2016-04-01) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Jun 16, 2017 at 08:47:32AM +0800, Boqun Feng wrote: > On Thu, Jun 15, 2017 at 11:48:19AM -0700, Luis R. Rodriguez wrote: > > There are cases where folks are using an interruptible swait when > > using kthreads. This is rather confusing given you'd expect > > interruptible waits to be -- interruptible, but kthreads are not > > interruptible ! The reason for such practice though is to avoid > > having these kthreads contribute to the system load average. > > > > When systems are idle some kthreads may spend a lot of time blocking if > > using swait_event_timeout(). This would contribute to the system load > > average. On systems without preemption this would mean the load average > > of an idle system is bumped to 2 instead of 0. On systems with PREEMPT=y > > this would mean the load average of an idle system is bumped to 3 > > instead of 0. > > > > This adds proper API using TASK_IDLE to make such goals explicit and > > avoid confusion. > > > > Suggested-by: "Eric W. Biederman" > > Signed-off-by: Luis R. Rodriguez > > --- > > include/linux/swait.h | 25 +++++++++++++++++++++++++ > > 1 file changed, 25 insertions(+) > > > > diff --git a/include/linux/swait.h b/include/linux/swait.h > > index 2c700694d50a..105c70e23286 100644 > > --- a/include/linux/swait.h > > +++ b/include/linux/swait.h > > @@ -194,4 +194,29 @@ do { \ > > __ret; \ > > }) > > > > +#define __swait_event_idle(wq, condition) \ > > + ___swait_event(wq, condition, TASK_IDLE, 0, schedule()) > > + > > +#define swait_event_idle(wq, condition) \ > > Better to have some comments before to describe the purpose of this API? > Something like: > > /** > * swait_event_idle - wait uninterruptibly without system load contribution > * @wq: the waitqueue to wait on > * @condition: a C expression for the event to wait for > * > * The process is put to sleep (TASK_IDLE) until the > * @condition evaluates to true or a signal is received. Except we get no signals. > * The @condition is checked each time the waitqueue @wq is woken up. > * > * This function is mostly used when a kthread waits some condition and > * doesn't want to contribute to system load > */ > > so is for swait_event_idle_timeout(). Will add for both calls and elaborate on the return value for the timeout case. Luis