All of lore.kernel.org
 help / color / mirror / Atom feed
From: Samuel Thibault <samuel.thibault@eu.citrix.com>
To: Chris <hap10@tycho.ncsc.mil>
Cc: Derek Murray <Derek.Murray@cl.cam.ac.uk>,
	ncmike@us.ibm.com, xen-devel@lists.xensource.com
Subject: Re: Re: Scheduling groups, credit scheduler support
Date: Fri, 14 Dec 2007 17:20:53 +0000	[thread overview]
Message-ID: <20071214172053.GN4296@implementation.uk.xensource.com> (raw)
In-Reply-To: <12ADC17A-A071-49EA-AB34-AEF9975DF47E@tycho.ncsc.mil>

Chris, le Tue 04 Dec 2007 14:32:11 -0500, a écrit :
> One way to avoid both concerns is to create and manage group-tracking  
> objects independently of domain-tracking objects.   In other words,  
> make groups a first-class object.  They could be referenced by  
> schedulers as well as any other parts of the VMM that want to make  
> use of group information.

Yes, some kind of non-schedulable entity which is just here to do what
Mike's masters do: concentrate scheduling credits.

About the userland interface, I can see two approaches:
- have people explicitely create groups and put domains in it. That can
  be hierarchical (putting groups into other groups)
- have groups created and destroyed implicitely, for instance
join(d1,d2) will make d1 and d2 part of the same group, which is created
if there weren't any previously, or the union of both groups if both
existed.

The second approach seems fun, but I'm not sure it might ever be useful
actually :)

Also, there is the question: can a domain belong to several groups?
Depending on the point of view, that may be useful or just not make
any sense.  One problem of belonging to several groups is that you
end up with a graph of domains, which may be tedious and potentially
non-polynomial to walk.

Samuel

  parent reply	other threads:[~2007-12-14 17:20 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-11-29 20:19 [PATCH] Scheduling groups, credit scheduler support Mike D. Day
2007-11-29 22:36 ` Chris B
2007-12-03 15:37   ` Chris
2007-12-03 17:59     ` Mike D. Day
2007-12-04 19:32       ` Chris
2007-12-04 23:04         ` Keir Fraser
2007-12-06 16:42           ` Chris
2007-12-14 17:20         ` Samuel Thibault [this message]
2007-12-18 16:04           ` Chris
2007-12-04 10:38 ` [PATCH] " Keir Fraser
2007-12-04 13:50   ` Mike D. Day
2007-12-04 23:06     ` Keir Fraser
2007-12-14 13:35       ` Mike D. Day
2007-12-14 13:50         ` Keir Fraser
2007-12-14 16:26         ` Samuel Thibault
2007-12-14 17:36           ` Samuel Thibault
2007-12-19 16:08             ` Samuel Thibault
2007-12-14 16:49     ` Samuel Thibault
2007-12-19 20:18       ` Mike D. Day
2007-12-05  1:34 ` does xen-linux for PV support the Linux Standards base , or not ? tgh
2007-12-05  3:49   ` Mark Williamson
2007-12-14 17:01 ` [PATCH] Scheduling groups, credit scheduler support Samuel Thibault
2007-12-17 16:57   ` Samuel Thibault
2007-12-18 11:50 ` Samuel Thibault

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=20071214172053.GN4296@implementation.uk.xensource.com \
    --to=samuel.thibault@eu.citrix.com \
    --cc=Derek.Murray@cl.cam.ac.uk \
    --cc=hap10@tycho.ncsc.mil \
    --cc=ncmike@us.ibm.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 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.