From mboxrd@z Thu Jan  1 00:00:00 1970
From: Avi Kivity <avi@redhat.com>
Subject: Re: [PATCH 0/3] v2: KVM-userspace: add NUMA support for guests
Date: Tue, 09 Dec 2008 16:24:53 +0200
Message-ID: <493E7FB5.80606@redhat.com>
References: <49392CB6.9000000@amd.com> <49393A78.5030601@codemonkey.ws> <4939473D.6080606@amd.com> <49394BB3.9080509@codemonkey.ws> <493D95A9.1090307@andrep.de>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1;
	format=flowed
Content-Transfer-Encoding: QUOTED-PRINTABLE
Cc: Anthony Liguori <anthony@codemonkey.ws>, kvm@vger.kernel.org
To: =?ISO-8859-1?Q?Andr=E9_Przywara?= <osp@andrep.de>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx2.redhat.com ([66.187.237.31]:41116 "EHLO mx2.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1755950AbYLIOZE (ORCPT <rfc822;kvm@vger.kernel.org>);
	Tue, 9 Dec 2008 09:25:04 -0500
In-Reply-To: <493D95A9.1090307@andrep.de>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

Andr=E9 Przywara wrote:
>>> But I wouldn't load the admin with the burden of pinning, but let=20
>>> this be done by QEMU/KVM. Maybe one could introduce a way to tell=20
>>> QEMU/KVM to not pin the threads.
>> This is where things start to get ugly...
> Why? qemu-system-x86_64 -numa 2,pin:none and then use whatever method=
=20
> you prefer (taskset, monitor) to pin the VCPUs (or left them unpinned=
).

I agree that for e.g. -numa 2, no host binding should occur.  Pinning=20
memory or cpus to nodes should only occur if the user explicitly=20
requested it.  Otherwise we run the risk of breaking load balancing.

If the user chooses to pin, the responsibility is on them.  If not, we=20
should allow the host to do its thing.

> // similar to numactl --hardware, * means all nodes (no pinning)
>  > numa pin:0;3
> // static pinning: guest 0 -> host 0, guest 1 -> host 3
>  > numa pin:*;
> // guest node 0 -> all nodes, guest node 1: keep as it is
> // or maybe: numa pin:0-3;
>  > numa migrate:1;2

I suggest using exactly the same syntax as the command line option. =20
Qemu would compute the difference between the current configuration and=
=20
the desired configuration and migrate vcpus and memory as needed.

--=20
error compiling committee.c: too many arguments to function