From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754228AbbBZP6S (ORCPT ); Thu, 26 Feb 2015 10:58:18 -0500 Received: from smtprelay0017.hostedemail.com ([216.40.44.17]:37729 "EHLO smtprelay.hostedemail.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1753740AbbBZP6R (ORCPT ); Thu, 26 Feb 2015 10:58:17 -0500 X-Session-Marker: 6E657665747340676F6F646D69732E6F7267 X-Spam-Summary: 2,0,0,,d41d8cd98f00b204,rostedt@goodmis.org,:::::::::::::::::,RULES_HIT:41:355:379:541:599:800:960:973:988:989:1260:1277:1311:1313:1314:1345:1359:1437:1515:1516:1518:1534:1540:1593:1594:1711:1730:1747:1777:1792:2393:2553:2559:2562:2895:3138:3139:3140:3141:3142:3352:3622:3865:3867:3868:3870:3871:3872:3874:5007:6261:7875:7901:7903:10004:10400:10848:10967:11026:11232:11658:11914:12043:12517:12519:12740:13069:13255:13311:13357:14096:14097:21080,0,RBL:none,CacheIP:none,Bayesian:0.5,0.5,0.5,Netcheck:none,DomainCache:0,MSF:not bulk,SPF:fn,MSBL:0,DNSBL:none,Custom_rules:0:0:0 X-HE-Tag: work39_2ae7801110e07 X-Filterd-Recvd-Size: 2027 Date: Thu, 26 Feb 2015 10:58:13 -0500 From: Steven Rostedt To: LKML Cc: Ingo Molnar , Peter Zijlstra , Thomas Gleixner , Clark Williams , linux-rt-users , Mike Galbraith , "Paul E. McKenney" , =?UTF-8?B?SsO2cm4=?= Engel Subject: Re: [RFC][PATCH v3] sched/rt: Use IPI to trigger RT task push migration instead of pulling Message-ID: <20150226105813.2659c8ea@gandalf.local.home> In-Reply-To: <20150225222644.042841cc@gandalf.local.home> References: <20150225222644.042841cc@gandalf.local.home> X-Mailer: Claws Mail 3.11.1 (GTK+ 2.24.25; 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, 25 Feb 2015 22:26:44 -0500 Steven Rostedt wrote: > +static int find_next_push_cpu(struct rq *rq) > +{ > + struct rq *next_rq; > + int cpu; > + > + while (1) { > + cpu = rto_next_cpu(rq); > + if (cpu >= nr_cpu_ids) > + break; > + next_rq = cpu_rq(cpu); > + > + /* Make sure the next rq can push to this rq */ > + if (next_rq->rt.highest_prio.next < > + rq->rt.highest_prio.curr && > + next_rq->rt.highest_prio.next < > + rq->rt.highest_prio.next) OK, this second comparison is not needed. I was looking at the code in more detail, and see that the .curr is updated when a new task is enqueued, and it does not represent the task currently running, but the highest priority task that is on the rq. I'll be sending a v4 soon with this update. -- Steve > + break; > + } > + > + return cpu; > +}