From: Andre Przywara <andre.przywara@amd.com>
To: Jan Beulich <JBeulich@suse.com>
Cc: Anil Madhavapeddy <anil@recoil.org>,
Andrew Cooper <Andrew.Cooper3@citrix.com>,
xen-devel <xen-devel@lists.xen.org>,
Dario Faggioli <raistlin@linux.it>,
George Dunlap <dunlapg@gmail.com>,
Yang Z Zhang <yang.z.zhang@intel.com>
Subject: Re: NUMA TODO-list for xen-devel
Date: Fri, 3 Aug 2012 13:26:06 +0200 [thread overview]
Message-ID: <501BB54E.1050302@amd.com> (raw)
In-Reply-To: <501BC6B8020000780009277B@nat28.tlf.novell.com>
On 08/03/2012 12:40 PM, Jan Beulich wrote:
>>>> On 03.08.12 at 12:02, Andre Przywara <andre.przywara@amd.com> wrote:
>> On 08/01/2012 06:16 PM, Dario Faggioli wrote:
>>> Hi everyone,
>>>
>>> With automatic placement finally landing into xen-unstable, I stated
>>> thinking about what I could work on next, still in the field of
>>> improving Xen's NUMA support. Well, it turned out that running out of
>>> things to do is not an option! :-O
>>>
>>> In fact, I can think of quite a bit of open issues in that area, that I'm
>>> just braindumping here.
>>
>>> ...
>>>
>>> * automatic placement of Dom0, if possible (my current series is
>>> only affecting DomU)
>>
>> I think Dom0 NUMA awareness should be one of the top priorities. If I
>> boot my 8-node box with Xen, I end up with a NUMA-clueless Dom0 which
>> actually has memory from all 8 nodes and thinks it's memory is flat.
>> There are some tricks to confine it to node 0 (dom0_mem=<memory of
>> node0> dom0_vcpus=<cores in node0> dom0_vcpus_pin), but this requires
>> intimate knowledge of the systems parameters and is error-prone.
>
> How about "dom0_mem=node<n> dom0_vcpus=node<n>" as
> an extension to the current options?
Yes, that sounds like a good idea. And relatively easy to implement.
Maybe a list or a number of nodes (to make it more complicated ;-)
Regards,
Andre.
--
Andre Przywara
AMD-Operating System Research Center (OSRC), Dresden, Germany
next prev parent reply other threads:[~2012-08-03 11:26 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-08-01 16:16 NUMA TODO-list for xen-devel Dario Faggioli
2012-08-01 16:24 ` Dario Faggioli
2012-08-01 16:30 ` Andrew Cooper
2012-08-01 16:47 ` Dario Faggioli
2012-08-01 16:53 ` Andrew Cooper
2012-08-02 9:40 ` Jan Beulich
2012-08-02 13:21 ` Dario Faggioli
2012-08-01 16:32 ` Anil Madhavapeddy
2012-08-01 16:58 ` Dario Faggioli
2012-08-02 0:04 ` Malte Schwarzkopf
2012-08-07 23:53 ` Dario Faggioli
2012-08-02 1:04 ` Zhang, Yang Z
2012-08-07 22:56 ` Dario Faggioli
2012-08-02 9:43 ` Jan Beulich
2012-08-02 13:34 ` Dario Faggioli
2012-08-02 14:07 ` Jan Beulich
2012-08-02 16:36 ` George Dunlap
2012-08-03 9:23 ` Jan Beulich
2012-08-03 9:48 ` Andre Przywara
2012-08-03 10:03 ` Jan Beulich
2012-08-03 22:40 ` Dan Magenheimer
2012-08-03 11:00 ` George Dunlap
2012-08-03 22:34 ` Dan Magenheimer
2012-08-06 7:15 ` Jan Beulich
2012-08-06 16:28 ` Dan Magenheimer
2012-08-03 10:02 ` Andre Przywara
2012-08-03 10:40 ` Jan Beulich
2012-08-03 11:26 ` Andre Przywara [this message]
2012-08-03 11:38 ` Jan Beulich
2012-08-03 13:14 ` Dario Faggioli
2012-08-03 13:52 ` Jan Beulich
2012-08-03 22:42 ` Dan Magenheimer
2012-08-08 7:07 ` Dario Faggioli
2012-08-08 7:43 ` Dario Faggioli
2012-08-03 22:22 ` Dan Magenheimer
2012-08-07 23:49 ` Dario Faggioli
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=501BB54E.1050302@amd.com \
--to=andre.przywara@amd.com \
--cc=Andrew.Cooper3@citrix.com \
--cc=JBeulich@suse.com \
--cc=anil@recoil.org \
--cc=dunlapg@gmail.com \
--cc=raistlin@linux.it \
--cc=xen-devel@lists.xen.org \
--cc=yang.z.zhang@intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.