From: Andre Przywara <andre.przywara@amd.com>
To: Dulloor <dulloor@gmail.com>
Cc: "xen-devel@lists.xensource.com" <xen-devel@lists.xensource.com>,
Keir Fraser <keir.fraser@eu.citrix.com>
Subject: Re: [vNUMA v2][PATCH 2/8] public interface
Date: Wed, 4 Aug 2010 09:01:26 +0200 [thread overview]
Message-ID: <4C591046.4070201@amd.com> (raw)
In-Reply-To: <AANLkTikD0fAnwyjjh+dZx4B_8AbnTUy-=dSosV7b+FO8@mail.gmail.com>
Dulloor wrote:
> On Tue, Aug 3, 2010 at 10:27 PM, Keir Fraser <keir.fraser@eu.citrix.com> wrote:
>> On 03/08/2010 22:55, "Andre Przywara" <andre.przywara@amd.com> wrote:
>>
>>>> As such, the purpose of vnode-to-mnode translation is for the enlightened
>>>> guests to know where their underlying memory comes from, so that
>>>> over-provisioning features
>>>> like ballooning are given a chance to maintain this distribution.
>>> I was afraid you were saying that ;-) I haven't thought about this in
>>> detail, but maybe we can make an exception for Dom0 only, because this
>>> is the most prominent and frequent user of ballooning. But I really
>>> think that DomUs should not know about or deal with host NUMA nodes.
>> So long as it gets renamed to 'node_id' in the info structure I'm okay with
>> it. That doesn't preclude simply setting that field to 0...nr_vnodes-1 and
>> doing translation in the hypervisor, but also leaves us a bit of
>> flexibility.
> Yes, I like this idea. Will do that.
Ack, that sounds good. So we have virtual nodes, virtual physical nodes
and machine nodes.
Andre.
--
Andre Przywara
AMD-OSRC (Dresden)
Tel: x29712
next prev parent reply other threads:[~2010-08-04 7:01 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1BEA8649F0C00540AB2811D7922ECB6C9338B4CC@orsmsx507.amr.corp.intel.com>
2010-07-02 23:54 ` [XEN][vNUMA][PATCH 3/9] public interface Dulloor
2010-07-05 7:39 ` Keir Fraser
2010-07-05 8:52 ` Dulloor
2010-07-05 10:23 ` Keir Fraser
2010-07-06 5:57 ` Dulloor
2010-07-06 12:57 ` Keir Fraser
2010-07-06 17:52 ` Dulloor
2010-08-01 22:02 ` [vNUMA v2][PATCH 2/8] " Dulloor
2010-08-03 12:40 ` Andre Przywara
2010-08-03 15:24 ` Dulloor
2010-08-03 13:37 ` Andre Przywara
2010-08-03 14:10 ` Keir Fraser
2010-08-03 15:43 ` Dulloor
2010-08-03 15:52 ` Keir Fraser
2010-08-03 17:24 ` Dulloor
2010-08-03 19:52 ` Keir Fraser
2010-08-03 20:32 ` Dulloor
2010-08-03 21:55 ` Andre Przywara
2010-08-04 5:27 ` Keir Fraser
2010-08-04 5:48 ` Dulloor
2010-08-04 7:01 ` Andre Przywara [this message]
2010-08-04 8:45 ` Keir Fraser
2010-08-04 13:34 ` Dan Magenheimer
2010-08-03 21:35 ` Andre Przywara
2010-08-03 15:54 ` Keir Fraser
2010-08-03 15:32 ` Dulloor
2010-08-03 21:21 ` Andre Przywara
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4C591046.4070201@amd.com \
--to=andre.przywara@amd.com \
--cc=dulloor@gmail.com \
--cc=keir.fraser@eu.citrix.com \
--cc=xen-devel@lists.xensource.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).