From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S932295AbbBZMpS (ORCPT <rfc822;w@1wt.eu>);
	Thu, 26 Feb 2015 07:45:18 -0500
Received: from cdptpa-outbound-snat.email.rr.com ([107.14.166.229]:8943 "EHLO
	cdptpa-oedge-vip.email.rr.com" rhost-flags-OK-OK-OK-FAIL)
	by vger.kernel.org with ESMTP id S932270AbbBZMpQ (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Thu, 26 Feb 2015 07:45:16 -0500
Date: Thu, 26 Feb 2015 07:46:09 -0500
From: Steven Rostedt <rostedt@goodmis.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: LKML <linux-kernel@vger.kernel.org>, Ingo Molnar <mingo@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Clark Williams <williams@redhat.com>,
        linux-rt-users <linux-rt-users@vger.kernel.org>,
        Mike Galbraith <umgwanakikbuti@gmail.com>,
        "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
        =?UTF-8?B?SsO2cm4=?= Engel <joern@purestorage.com>
Subject: Re: [RFC][PATCH v2] sched/rt: Use IPI to trigger RT task push
 migration instead of pulling
Message-ID: <20150226074609.27ccd39d@grimm.local.home>
In-Reply-To: <20150226074907.GQ21418@twins.programming.kicks-ass.net>
References: <20150224133946.3948c4b7@gandalf.local.home>
	<20150225103535.GJ5029@twins.programming.kicks-ass.net>
	<20150225105116.7fa03cc9@gandalf.local.home>
	<20150225171110.GO21418@twins.programming.kicks-ass.net>
	<20150225125015.6c5110ca@gandalf.local.home>
	<20150226074907.GQ21418@twins.programming.kicks-ass.net>
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
X-RR-Connecting-IP: 107.14.168.118:25
X-Cloudmark-Score: 0
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Thu, 26 Feb 2015 08:49:07 +0100
Peter Zijlstra <peterz@infradead.org> wrote:
 
> Yes, notice that we don't start iterating at the beginning; this in on
> purpose. If we start iterating at the beginning, _every_ cpu will again
> pile up on the first one.
> 
> By starting at the current cpu, each cpu will start iteration some place
> else and hopefully, with a big enough system, different CPUs end up on a
> different rto cpu.

Note, v3 doesn't start at the current CPU, it starts at the original
CPU again. As the start of every IPI comes from a different CPU, this
still keeps a restart from clobbering the same CPU.

-- Steve