From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751873AbdCAOHv (ORCPT ); Wed, 1 Mar 2017 09:07:51 -0500 Received: from mail.kernel.org ([198.145.29.136]:54238 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751769AbdCAOHr (ORCPT ); Wed, 1 Mar 2017 09:07:47 -0500 Date: Wed, 1 Mar 2017 08:40:09 -0500 From: Steven Rostedt To: Peter Zijlstra Cc: LKML , Ingo Molnar , Thomas Gleixner , Andrew Morton , Clark Williams , Daniel Bristot de Oliveira Subject: Re: [PATCH v2] sched/rt: Add comments describing the RT IPI pull method Message-ID: <20170301084009.75f65b00@gandalf.local.home> In-Reply-To: <20170301094409.GB6515@twins.programming.kicks-ass.net> References: <20170228155030.30c69068@gandalf.local.home> <20170301094409.GB6515@twins.programming.kicks-ass.net> X-Mailer: Claws Mail 3.14.0 (GTK+ 2.24.31; x86_64-pc-linux-gnu) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 1 Mar 2017 10:44:09 +0100 Peter Zijlstra wrote: > On Tue, Feb 28, 2017 at 03:50:30PM -0500, Steven Rostedt wrote: > > + * The overloaded RT CPU, wher receiving an IPI, will try to push off its > > "wher" isn't in my dictionary, I'm thinking you mean: "when". Fixed that > for you. Heh, thanks. Hmm, I looked at all the highlighted words when I pulled in the patch into claws-mail. I'm surprised I missed that. > > > + * overloaded RT tasks and then send an IPI to the next CPU that has > > + * overloaded RT tasks. This stops when all CPUs with overloaded RT tasks > > + * have completed. Just because a CPU may have pushed off its own overloaded > > + * RT task does not mean it should stop sending the IPI around to other > > + * overloaded CPUs. There may be another RT task waiting to run on one of > > + * those CPUs that are of higher priority than the one that was just > > + * pushed. > > + * > > + * An optimization that could possibly be made is to make a CPU array similar > > + * to the cpupri array mask of all running RT tasks, but for the overloaded > > + * case, then the IPI could be sent to only the CPU with the highest priority > > + * RT task waiting, and that CPU could send off further IPIs to the CPU with > > + * the next highest waiting task. Since the overloaded case is much less likely > > + * to happen, the complexity of this implementation may not be worth it. > > + * Instead, just send an IPI around to all overloaded CPUs. > > Yeah, not sure, I'll leave it in though. OK, Thanks! -- Steve