xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Dario Faggioli <dario.faggioli@citrix.com>
To: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>,
	Sisu Xi <xisisu@gmail.com>,
	Stefano Stabellini <stefano.stabellini@eu.citrix.com>,
	Ian Jackson <ian.jackson@eu.citrix.com>,
	"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>,
	Meng Xu <xumengpanda@gmail.com>, Meng Xu <mengxu@cis.upenn.edu>,
	Jan Beulich <JBeulich@suse.com>, Chao Wang <chaowang@wustl.edu>,
	Chong Li <lichong659@gmail.com>,
	Dagaen Golomb <dgolomb@seas.upenn.edu>
Subject: Re: [PATCH v1 1/4] xen: add real time scheduler rt
Date: Wed, 3 Sep 2014 16:59:51 +0200	[thread overview]
Message-ID: <1409756391.2673.68.camel@Solace.lan> (raw)
In-Reply-To: <CAFLBxZZb-xiZ81ne=02ucQ=OPXq0U3e4h-ZCzjBR8Nx6Mdeu+A@mail.gmail.com>


[-- Attachment #1.1: Type: text/plain, Size: 1703 bytes --]

On mer, 2014-09-03 at 15:20 +0100, George Dunlap wrote:
> So if I'm reading this right, you set the information for vcpus one
> vcpu at a time, but you want to read the whole lot out all at once?
> 
> I don't like the inconsistency.  It would be better if you did the
> same thing each direction:  Either pass in an array with info about
> the vcpus, or just read the vcpu information one-by-one.
> 
I agree. One by one (in both reading and writing direction) was what I
suggested, but others (I think it was Andrew) pointed out that, when
hypercall are involved, batching is always a good thing. And in fact
(although maybe not in hot paths) it's quite likely that one wants to
retrieve the parameters for all the vcpus (e.g., it is like that as far
as xl is concerned), so that's why, IIRC, Meng went for the batching
approach.

I also continue to think that, in the case of this scheduler, a good API
would include both calls to set and get one vcpu at a time *AND* calls
to set and get all of them.

I'm fine with this version only having one of the two alternatives (and
about adding the other one later), but I agree with George it should be
consistent.

If we like batching, then batching it is, but I think in that case we
need to think about one change the parameters of only one vcpu (perhaps
treat budget=0 && period=0 in the i-eth element of the array as 'don't
touch vcpu #i"?).

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: 181 bytes --]

[-- Attachment #2: Type: text/plain, Size: 126 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel

  parent reply	other threads:[~2014-09-03 14:59 UTC|newest]

Thread overview: 72+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-08-24 22:58 Introduce rt real-time scheduler for Xen Meng Xu
2014-08-24 22:58 ` [PATCH v1 1/4] xen: add real time scheduler rt Meng Xu
2014-08-26 14:27   ` Jan Beulich
2014-08-27  2:07     ` Meng Xu
2014-08-27  6:26       ` Jan Beulich
2014-08-27 14:28         ` Meng Xu
2014-08-27 15:04           ` Jan Beulich
2014-08-28 16:06             ` Meng Xu
2014-08-29  9:05               ` Jan Beulich
2014-08-29 19:35                 ` Meng Xu
2014-09-03 14:08                 ` George Dunlap
2014-09-03 14:24                   ` Meng Xu
2014-09-03 14:35                     ` Dario Faggioli
2014-09-03 13:40   ` George Dunlap
2014-09-03 14:11     ` Meng Xu
2014-09-03 14:15       ` George Dunlap
2014-09-03 14:35         ` Meng Xu
2014-09-05  9:46     ` Dario Faggioli
2014-09-03 14:20   ` George Dunlap
2014-09-03 14:45     ` Jan Beulich
2014-09-03 14:59     ` Dario Faggioli [this message]
2014-09-03 15:27       ` Meng Xu
2014-09-03 15:46         ` Dario Faggioli
2014-09-03 17:13           ` George Dunlap
2014-09-03 15:13     ` Meng Xu
2014-09-03 16:06       ` George Dunlap
2014-09-03 16:57         ` Dario Faggioli
2014-09-03 17:18           ` George Dunlap
2014-09-04  2:15             ` Meng Xu
2014-09-04 14:27             ` Dario Faggioli
2014-09-04 15:30               ` Meng Xu
2014-09-05  9:36                 ` Dario Faggioli
2014-09-05 15:06                   ` Meng Xu
2014-09-05 15:09                     ` Dario Faggioli
2014-09-04  2:11         ` Meng Xu
2014-09-04 11:00           ` Dario Faggioli
2014-09-04 13:03           ` George Dunlap
2014-09-04 14:00             ` Meng Xu
2014-09-05 17:17   ` Dario Faggioli
2014-09-07  3:56     ` Meng Xu
2014-09-08 10:33       ` Dario Faggioli
2014-09-09 13:43         ` Meng Xu
2014-08-24 22:58 ` [PATCH v1 2/4] libxc: add rt scheduler Meng Xu
2014-09-05 10:34   ` Dario Faggioli
2014-09-05 17:17     ` Meng Xu
2014-09-05 17:50       ` Dario Faggioli
2014-08-24 22:58 ` [PATCH v1 3/4] libxl: " Meng Xu
2014-08-25 13:17   ` Wei Liu
2014-08-25 15:55     ` Meng Xu
2014-08-26  9:51       ` Wei Liu
2014-09-03 15:33   ` George Dunlap
2014-09-03 20:52     ` Meng Xu
2014-09-04 14:27     ` George Dunlap
2014-09-04 14:45       ` Dario Faggioli
2014-09-04 14:47       ` Meng Xu
2014-09-04 14:51         ` George Dunlap
2014-09-04 15:07           ` Meng Xu
2014-09-04 15:44             ` Dario Faggioli
2014-09-04 15:55               ` George Dunlap
2014-09-04 16:12                 ` Meng Xu
2014-09-05  9:19                   ` Dario Faggioli
2014-09-04 15:25         ` Dario Faggioli
2014-09-05 10:21   ` Dario Faggioli
2014-09-05 15:45     ` Meng Xu
2014-09-05 17:41       ` Dario Faggioli
2014-08-24 22:58 ` [PATCH v1 4/4] xl: introduce " Meng Xu
2014-08-25 13:31   ` Wei Liu
2014-08-25 16:12     ` Meng Xu
2014-09-03 15:52   ` George Dunlap
2014-09-03 22:28     ` Meng Xu
2014-09-05  9:40       ` Dario Faggioli
2014-09-05 14:43         ` Meng Xu

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=1409756391.2673.68.camel@Solace.lan \
    --to=dario.faggioli@citrix.com \
    --cc=George.Dunlap@eu.citrix.com \
    --cc=JBeulich@suse.com \
    --cc=chaowang@wustl.edu \
    --cc=dgolomb@seas.upenn.edu \
    --cc=ian.campbell@citrix.com \
    --cc=ian.jackson@eu.citrix.com \
    --cc=lichong659@gmail.com \
    --cc=mengxu@cis.upenn.edu \
    --cc=stefano.stabellini@eu.citrix.com \
    --cc=xen-devel@lists.xen.org \
    --cc=xisisu@gmail.com \
    --cc=xumengpanda@gmail.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).