From: Dario Faggioli <dario.faggioli@citrix.com>
To: Ian Jackson <Ian.Jackson@eu.citrix.com>
Cc: Ian Campbell <Ian.Campbell@citrix.com>,
Andrew Cooper <andrew.cooper3@citrix.com>,
Juergen Gross <juergen.gross@ts.fujitsu.com>,
xen-devel <xen-devel@lists.xen.org>,
Jan Beulich <JBeulich@suse.com>,
Daniel De Graaf <dgdegra@tycho.nsa.gov>
Subject: Re: [PATCH 2/4] libxc: report how much memory a domain has on each NUMA node
Date: Tue, 11 Mar 2014 18:37:25 +0100 [thread overview]
Message-ID: <1394559445.17832.61.camel@Solace> (raw)
In-Reply-To: <21278.61493.651392.622482@mariner.uk.xensource.com>
[-- Attachment #1.1: Type: text/plain, Size: 1855 bytes --]
On mar, 2014-03-11 at 11:15 +0000, Ian Jackson wrote:
> Dario Faggioli writes ("Re: [Xen-devel] [PATCH 2/4] libxc: report how much memory a domain has on each NUMA node"):
> > If something changed, then yes you're screwed, but the bottom line, I
> > think is, if you think you may need the information broken down in
> > nodes, use XEN_DOMCTL_domain_numainfo, which gives you that and,
> > indirectly, also the total size.
>
> But it gives you for only one domain; whereas the domain list gives
> you all domains at once.
>
Right. Not sure what you're after (see below), but yes, it's probably at
least a more accurate snapshot of the system... I'll try to move this in
dominfo.
> We have had problems before with toolstack memory balancing and
> managemetn algorithms needing information which wasn't properly
> available. So I think I want to see an explanation how this would be
> used in an actual memory balancing/assignment algorith.
>
I'm not sure why you're asking this. For now, this is not going to be
used in any algorithm, it's pure information reporting.
Of course, the system administrator, or a toolstack at an higher level
than libxl, can use the info for making some decisions, but then full
consistency is up to then, I guess... mostly because I don't think there
is much we can do.
In the current NUMA placement implementation, in libxl, what we need to
know is how much memory is free on each node, rather than how much
memory each domain occupies there.
So, what is it that I should try to show you?
Thanks and Regards,
Dario
--
<<This happens because I choose it to happen!>> (Raistlin Majere)
-----------------------------------------------------------------
Dario Faggioli, Ph.D, http://about.me/dario.faggioli
Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK)
[-- Attachment #1.2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 198 bytes --]
[-- Attachment #2: Type: text/plain, Size: 126 bytes --]
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel
next prev parent reply other threads:[~2014-03-11 17:37 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-03-05 14:36 [PATCH 0/4] report how much memory a domain has on each NUMA node Dario Faggioli
2014-03-05 14:36 ` [PATCH 1/4] xen: " Dario Faggioli
2014-03-05 14:50 ` Juergen Gross
2014-03-05 16:31 ` Dario Faggioli
2014-03-05 16:49 ` Jan Beulich
2014-03-05 17:14 ` Dario Faggioli
2014-03-05 15:04 ` Jan Beulich
2014-03-05 16:13 ` Dario Faggioli
2014-03-05 16:44 ` Jan Beulich
2014-03-05 14:36 ` [PATCH 2/4] libxc: " Dario Faggioli
2014-03-05 15:05 ` Andrew Cooper
2014-03-05 15:40 ` Dario Faggioli
2014-03-10 16:39 ` Ian Jackson
2014-03-10 17:07 ` Dario Faggioli
2014-03-10 17:09 ` Andrew Cooper
2014-03-10 17:20 ` Ian Jackson
2014-03-10 17:35 ` Dario Faggioli
2014-03-11 11:15 ` Ian Jackson
2014-03-11 17:37 ` Dario Faggioli [this message]
2014-03-11 18:16 ` Ian Jackson
2014-03-11 19:04 ` Dario Faggioli
2014-03-13 11:54 ` George Dunlap
2014-03-05 14:36 ` [PATCH 3/4] libxl: " Dario Faggioli
2014-03-10 16:40 ` Ian Jackson
2014-03-10 17:28 ` Dario Faggioli
2014-03-13 17:26 ` Ian Jackson
2014-03-05 14:36 ` [PATCH 4/4] xl: " Dario Faggioli
2014-03-10 16:42 ` Ian Jackson
2014-03-10 17:09 ` Dario Faggioli
2014-03-05 14:40 ` [PATCH 0/4] " Juergen Gross
2014-03-05 14:44 ` Dario Faggioli
2014-03-10 16:37 ` Ian Jackson
2014-03-10 17:12 ` 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=1394559445.17832.61.camel@Solace \
--to=dario.faggioli@citrix.com \
--cc=Ian.Campbell@citrix.com \
--cc=Ian.Jackson@eu.citrix.com \
--cc=JBeulich@suse.com \
--cc=andrew.cooper3@citrix.com \
--cc=dgdegra@tycho.nsa.gov \
--cc=juergen.gross@ts.fujitsu.com \
--cc=xen-devel@lists.xen.org \
/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).