From: Dario Faggioli <dario.faggioli@citrix.com>
To: Ian Campbell <Ian.Campbell@citrix.com>
Cc: Marcus Granado <Marcus.Granado@eu.citrix.com>,
Keir Fraser <keir@xen.org>, Jan Beulich <JBeulich@suse.com>,
Li Yechen <lccycc123@gmail.com>,
George Dunlap <george.dunlap@eu.citrix.com>,
Andrew Cooper <Andrew.Cooper3@citrix.com>,
Juergen Gross <juergen.gross@ts.fujitsu.com>,
Ian Jackson <Ian.Jackson@eu.citrix.com>,
xen-devel@lists.xen.org, Matt Wilson <msw@amazon.com>,
Justin Weaver <jtweaver@hawaii.edu>,
Elena Ufimtseva <ufimtseva@gmail.com>
Subject: Re: [PATCH v4 13/15] xl: enable getting and setting soft
Date: Tue, 3 Dec 2013 12:14:54 +0100 [thread overview]
Message-ID: <1386069294.5338.282.camel@Solace> (raw)
In-Reply-To: <1386068399.13256.4.camel@kazak.uk.xensource.com>
[-- Attachment #1.1: Type: text/plain, Size: 1918 bytes --]
On mar, 2013-12-03 at 10:59 +0000, Ian Campbell wrote:
> On Tue, 2013-12-03 at 11:27 +0100, Dario Faggioli wrote:
> > On mar, 2013-12-03 at 09:32 +0000, Ian Campbell wrote:
> > > Another option would be to take two affinities on the command line, the
> > > first being hard and the second soft with some special syntax ("-"?) for
> > > "leave it alone".
> > >
> > Mmm... I think I like this better. So, if we take the approach
> > implemented in this patch right now, and introduce something like that
> > later, here's what we'd get:
> >
> > 1. xl vcpu-pin 3 all 4-6 : hard affinity for all dom3 vcpus --> 4-6
>
> You mean soft don't you? And also hard -> all, not left alone.
>
Aha! :-) Actually, the 'all' here (and below) refers to "what dom3's
vcpu(s)"?
xl vcpu-pin <OPTIONS> <domain-id> <vcpu> <cpus>
So, no, I did mean hard and, more specifically, I included that example
because that is what is being used right now (and I mean _right_now_ so
before this series), and that we both agreed should continue working.
Now that you made me thinking about this, going this way we risk to have
something like:
xl vcpu-pin 3 all all all
which may not exactly look crystal-clear...
> > 2. xl vcpu-pin -s 3 all 3,5 : soft affinity for all dom3 vcpus --> 3,5
>
> I think if you give -s then you should expect only one cpumap, which
> would be the soft affinity map.
>
Same here. Another example could be:
xl vcpu-pin -s 3 0 3,5
which has indeed only one cpumap, "3,5", while the "0" means vcpu #0
doma domain 3.
> > Would that be ok?
>
> I like it.
>
So, is this still true? :-D
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:[~2013-12-03 11:14 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-11-22 18:56 [PATCH v4 00/15] Implement vcpu soft affinity for credit1 Dario Faggioli
2013-11-22 18:56 ` [PATCH v4 01/15] xl: match output of vcpu-list with pinning syntax Dario Faggioli
2013-11-22 18:56 ` [PATCH v4 02/15] libxl: sanitize error handling in libxl_get_max_{cpus, nodes} Dario Faggioli
2013-11-25 17:26 ` George Dunlap
2013-11-27 13:45 ` Ian Campbell
2013-12-02 18:21 ` Dario Faggioli
2013-12-03 9:41 ` Ian Campbell
2013-12-03 11:40 ` Dario Faggioli
2013-12-03 11:45 ` Ian Campbell
2013-12-03 12:06 ` Dario Faggioli
2013-12-03 17:40 ` Ian Jackson
2013-11-22 18:56 ` [PATCH v4 03/15] libxl: introduce libxl_get_nr_cpus() Dario Faggioli
2013-11-27 13:49 ` Ian Campbell
2013-12-03 17:48 ` Ian Jackson
2013-12-03 17:52 ` Dario Faggioli
2013-12-03 17:54 ` Ian Jackson
2013-12-03 18:09 ` George Dunlap
2013-12-03 18:17 ` Konrad Rzeszutek Wilk
2013-12-03 18:22 ` George Dunlap
2013-12-03 18:26 ` Dario Faggioli
2013-12-03 18:19 ` Dario Faggioli
2013-12-03 18:15 ` Dario Faggioli
2013-12-03 18:16 ` Ian Jackson
2013-11-22 18:57 ` [PATCH v4 04/15] xl: allow for node-wise specification of vcpu pinning Dario Faggioli
2013-11-22 18:57 ` [PATCH v4 05/15] xl: implement and enable dryrun mode for `xl vcpu-pin' Dario Faggioli
2013-11-22 18:57 ` [PATCH v4 06/15] xl: test script for the cpumap parser (for vCPU pinning) Dario Faggioli
2013-11-22 18:57 ` [PATCH v4 07/15] xen: sched: rename v->cpu_affinity into v->cpu_hard_affinity Dario Faggioli
2013-11-22 18:57 ` [PATCH v4 08/15] xen: sched: introduce soft-affinity and use it instead d->node-affinity Dario Faggioli
2013-11-22 18:57 ` [PATCH v4 09/15] xen: derive NUMA node affinity from hard and soft CPU affinity Dario Faggioli
2013-11-22 18:57 ` [PATCH v4 10/15] xen: sched: DOMCTL_*vcpuaffinity works with hard and soft affinity Dario Faggioli
2013-11-27 13:11 ` Jan Beulich
2013-11-27 14:17 ` George Dunlap
2013-11-27 14:31 ` Dario Faggioli
2013-11-22 18:58 ` [PATCH v4 11/15] libxc: get and set soft and hard affinity Dario Faggioli
2013-11-22 18:58 ` [PATCH v4 12/15] libxl: get and set soft affinity Dario Faggioli
2013-11-25 17:52 ` George Dunlap
2013-11-27 14:45 ` Ian Campbell
2013-12-02 18:17 ` Dario Faggioli
2013-12-03 9:35 ` Ian Campbell
2013-11-22 18:58 ` [PATCH v4 13/15] xl: enable getting and setting soft Dario Faggioli
2013-11-27 14:57 ` Ian Campbell
2013-12-02 18:10 ` Dario Faggioli
2013-12-03 9:32 ` Ian Campbell
2013-12-03 10:27 ` Dario Faggioli
2013-12-03 10:59 ` Ian Campbell
2013-12-03 11:14 ` Dario Faggioli [this message]
2013-12-03 11:18 ` Ian Campbell
2013-11-22 18:58 ` [PATCH v4 14/15] xl: enable for specifying node-affinity in the config file Dario Faggioli
2013-11-27 15:53 ` Ian Campbell
2013-12-02 18:22 ` Dario Faggioli
2013-11-22 18:58 ` [PATCH v4 15/15] libxl: automatic NUMA placement affects soft affinity Dario Faggioli
2013-11-27 15:55 ` Ian Campbell
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=1386069294.5338.282.camel@Solace \
--to=dario.faggioli@citrix.com \
--cc=Andrew.Cooper3@citrix.com \
--cc=Ian.Campbell@citrix.com \
--cc=Ian.Jackson@eu.citrix.com \
--cc=JBeulich@suse.com \
--cc=Marcus.Granado@eu.citrix.com \
--cc=george.dunlap@eu.citrix.com \
--cc=jtweaver@hawaii.edu \
--cc=juergen.gross@ts.fujitsu.com \
--cc=keir@xen.org \
--cc=lccycc123@gmail.com \
--cc=msw@amazon.com \
--cc=ufimtseva@gmail.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).