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 S1752071AbbESCah (ORCPT <rfc822;w@1wt.eu>);
	Mon, 18 May 2015 22:30:37 -0400
Received: from mail-wi0-f179.google.com ([209.85.212.179]:35890 "EHLO
	mail-wi0-f179.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1751532AbbESCaf (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Mon, 18 May 2015 22:30:35 -0400
Message-ID: <1432002632.2508.33.camel@gmail.com>
Subject: Re: [PATCH 4/4] nohz: Set isolcpus when nohz_full is set
From: Mike Galbraith <umgwanakikbuti@gmail.com>
To: Rik van Riel <riel@redhat.com>
Cc: Sasha Levin <levinsasha928@gmail.com>,
        Frederic Weisbecker <fweisbec@gmail.com>,
        Ingo Molnar <mingo@kernel.org>, LKML <linux-kernel@vger.kernel.org>,
        Chris Metcalf <cmetcalf@ezchip.com>,
        "Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
        Peter Zijlstra <peterz@infradead.org>, Dave Jones <davej@redhat.com>,
        Thomas Gleixner <tglx@linutronix.de>, Oleg Nesterov <oleg@redhat.com>,
        "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>,
        Ingo Molnar <mingo@redhat.com>,
        Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 19 May 2015 04:30:32 +0200
In-Reply-To: <5559FC90.1000603@redhat.com>
References: <1430928266-24888-1-git-send-email-fweisbec@gmail.com>
	 <1430928266-24888-5-git-send-email-fweisbec@gmail.com>
	 <55579CE0.5060801@gmail.com> <1431840650.3222.78.camel@gmail.com>
	 <55594BC0.9070005@redhat.com> <1431919756.2518.51.camel@gmail.com>
	 <5559F216.8050007@redhat.com> <1431958931.2496.189.camel@gmail.com>
	 <5559FC90.1000603@redhat.com>
Content-Type: text/plain; charset="UTF-8"
X-Mailer: Evolution 3.12.11 
Mime-Version: 1.0
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, 2015-05-18 at 10:52 -0400, Rik van Riel wrote:

> For real time KVM, it is desirable to run the VCPU threads on
> isolated CPUs as real time tasks.
> 
> Meanwhile, the emulator threads can run as normal tasks anywhere
> on the system.
> 
> This means the /machine cpuset, which all guests live under,
> needs to contain all the system's CPUs, both isolated and
> non-isolated, otherwise it will be unable to have the VCPU
> threads on isolated CPUs and the emulator threads on other
> CPUs.

Ok, I know next to nothing about virtualization only because I failed at
maintaining the desired absolute zero, but...

Why do you use isolcpus for this?  This KVM setup sounds very similar to
what I do for real realtime.  I use a shield script to set up an
exclusive isolated set and a system set and move the mundane world into
the system set.  Inject realtime proggy into its exclusive home, it
creates/pins worker bees, done.  Why the cpuset isolcpus hybrid?

When you say emulator threads can run anywhere, it sounds like that
includes the isolated set, but even so, nothing prevents injecting
whatever (the kernel permits) into whichever set.

	-Mike