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 S932380AbdJ3QbE (ORCPT <rfc822;w@1wt.eu>);
        Mon, 30 Oct 2017 12:31:04 -0400
Received: from resqmta-ch2-09v.sys.comcast.net ([69.252.207.41]:52310 "EHLO
        resqmta-ch2-09v.sys.comcast.net" rhost-flags-OK-OK-OK-OK)
        by vger.kernel.org with ESMTP id S1752417AbdJ3QbC (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 30 Oct 2017 12:31:02 -0400
Date: Mon, 30 Oct 2017 11:30:59 -0500 (CDT)
From: Christopher Lameter <cl@linux.com>
X-X-Sender: cl@nuc-kabylake
To: Peter Zijlstra <peterz@infradead.org>
cc: cmetcalf@mellanox.com, linux-kernel@vger.kernel.org,
        tglx@linutronix.de, torvalds@linux-foundation.org, hpa@zytor.com,
        riel@redhat.com, mingo@kernel.org, efault@gmx.de, frederic@kernel.org,
        kernellwp@gmail.com, paulmck@linux.vnet.ibm.com,
        lcapitulino@redhat.com, linux-tip-commits@vger.kernel.org
Subject: Re: [tip:sched/core] sched/isolation: Document the isolcpus= flags
In-Reply-To: <20171030161101.wprohopz5eg7snb4@hirez.programming.kicks-ass.net>
Message-ID: <alpine.DEB.2.20.1710301125060.1182@nuc-kabylake>
References: <1509072159-31808-13-git-send-email-frederic@kernel.org> <tip-98a06af93784a6ae541e9fc6292ef26177832543@git.kernel.org> <20171027135831.GZ3165@worktop.lehotels.local> <alpine.DEB.2.20.1710301045160.970@nuc-kabylake>
 <20171030161101.wprohopz5eg7snb4@hirez.programming.kicks-ass.net>
User-Agent: Alpine 2.20 (DEB 67 2015-01-07)
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
X-CMAE-Envelope: MS4wfDccl3rt5BlRQbZjHLoi5TRIOWuzkyHRfAylItL83alisGL43umMP5ZyFGtp24nqZt7prn/BXW0orCJjIPtr3IPzqogvefq+zrDXYOH6oiZcgf7W8oB/
 eCNRk7hXiYq81rmAe+uDfXsJTUboRVPAgrYyZn97L+vvMadene5B2+6IPnRgUR6p1r4rJO6mS/L19sjuZCK4zSGuuT4J39+y0f062xzjWGnYWeQLbH2fZ0YP
 yDMtQM31hfDbpyInjclfSApj9frBN2r2B7f6H7UHh3HedTaJ/sz31crt6ykXSk6juxIcoo4neGYprjN6EOH9uEF4WB4qIZACoKev0G0+6hJ406Srq8vS1MUo
 G+sJeHwPTyPIJgPoTeie3gCk/e/hAwTvdPduiiRxLVSi6jlQlXyLUaYevuBSVaz79GkQf4fiZhMa7AlevTkIA5czngePOICT9TIYW5U+e+iqVmF3PGz/I+KA
 Fn17kfBN8j9LvVZefZ0M+zwHEIOgVeqpp5N2HlrsWHPJXs+uNDDG54dFTsmphDSUfwVZEd6S3ovGXyvcLkEHF2EZsUOoT+Vs9VdlA/uAw34tjSm74mfRQywC
 EN4=
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, 30 Oct 2017, Peter Zijlstra wrote:

> > isolcpus is the *right* approach here because you are micromanaging the OS
> > and are putting dedicated pieces of software on each core.
>
> That is what you want, and cpusets should allow for that just fine.

Well yes a cpuset of one processor I guess.

> > A cgroup suggests that threads would be scheduled over multiple cores
> > which is *not* what you want.
>
> No, that suggestion is false. cpusets should allow you to isolate
> individual CPUs just fine.
>
> > cgroup has to do something with containers
>
> Sod containers. That's just modern group think. cpusets existed long
> before all that wankery and it should very well retain the original use
> cases.

Historically cpusets were not used for cpu isolation. They were used to
restrict applications threads to sets of cpus for performance reasons. And
we are here dealing with individual processors.

> That said, I know there's problems with cpusets, and those should be
> fixed. But that doesn't mean isolcpus is anything other than a vile
> hack.

Controlling the way an individual processor works would be best done with
some kind of configuration in sysfs. I.e. /sys/cpu/<xx>/no_sched or so.

In lieu of that I think isolcpus is definitely better than a cpuset and it
is the only way that traditionally processor handling of the OS has been
restricted.