All of lore.kernel.org
 help / color / mirror / Atom feed
From: Paul Jackson <pj@sgi.com>
To: "Paul Menage" <menage@google.com>
Cc: sekharan@us.ibm.com, npiggin@suse.de,
	ckrm-tech@lists.sourceforge.net, linux-kernel@vger.kernel.org,
	rohitseth@google.com, devel@openvz.org, clameter@sgi.com
Subject: Re: [ckrm-tech] [patch00/05]: Containers(V2)- Introduction
Date: Wed, 20 Sep 2006 13:49:03 -0700	[thread overview]
Message-ID: <20060920134903.fbd9fea8.pj@sgi.com> (raw)
In-Reply-To: <6599ad830609201225k3d38afe2gea7adc2fa8067e0@mail.google.com>

Paul M wrote:
> Even if the resource control portions aren't totally compatible,
> having two separate process container abstractions in the kernel is
> sub-optimal

At heart, CKRM (ne Resource Groups) are (well, have been until now)
different than cpusets.

Cpusets answers the question 'where', and Resource Groups 'how much'.

The fundamental motivation behind cpusets was to be able to enforce
job isolation.  A job can get dedicated use of specified resources,
-even- if it means those resources are severely underutilized by that
job.

The fundamental motivation (Chandra or others correct me if I'm wrong)
of Resource Groups is to improve capacity utilization while limiting
starvation due to greedy, competing users for the same resources.

Cpusets seeks maximum isolation.  Resource Groups seeks maximum
capacity utilization while preserving guaranteed levels of quality
of service.

Cpusets are that wall between you and the neighbor you might not
trust.  Resource groups are a large family of modest wealth sitting
down to share a meal.

It seems that cpusets can mimic memory resource groups.  I don't
see how cpusets could mimic other resource groups.  But maybe I'm
just being a dimm bulb.

-- 
                  I won't rest till it's the best ...
                  Programmer, Linux Scalability
                  Paul Jackson <pj@sgi.com> 1.925.600.0401

  parent reply	other threads:[~2006-09-20 20:49 UTC|newest]

Thread overview: 150+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-09-20  2:16 [patch00/05]: Containers(V2)- Introduction Rohit Seth
2006-09-20  5:39 ` Nick Piggin
2006-09-20 16:26   ` Christoph Lameter
2006-09-20 16:26     ` Christoph Lameter
2006-09-20 16:56     ` Nick Piggin
2006-09-20 16:56       ` Nick Piggin
2006-09-20 17:08       ` Christoph Lameter
2006-09-20 17:08         ` Christoph Lameter
2006-09-20 17:19         ` Nick Piggin
2006-09-20 17:19           ` Nick Piggin
2006-09-20 17:30           ` Christoph Lameter
2006-09-20 17:30             ` Christoph Lameter
2006-09-20 18:03             ` Nick Piggin
2006-09-20 18:03               ` Nick Piggin
2006-09-20 17:40       ` Alan Cox
2006-09-20 17:40         ` Alan Cox
2006-09-20 16:27   ` Rohit Seth
2006-09-20 16:27     ` Rohit Seth
     [not found]   ` <1158751720.8970.67.camel@twins>
     [not found]     ` <4511626B.9000106@yahoo.com.au>
     [not found]       ` <1158767787.3278.103.camel@taijtu>
2006-09-20 17:00         ` Nick Piggin
2006-09-20 17:00           ` Nick Piggin
2006-09-20 17:23           ` [ckrm-tech] " Paul Menage
2006-09-20 17:23             ` Paul Menage
2006-09-20 17:36           ` Alan Cox
2006-09-20 17:36             ` Alan Cox
2006-09-20 17:30             ` Nick Piggin
2006-09-20 17:30               ` Nick Piggin
2006-09-20 17:50           ` Rohit Seth
2006-09-20 17:50             ` Rohit Seth
2006-09-20 17:52             ` Christoph Lameter
2006-09-20 17:52               ` Christoph Lameter
2006-09-20 18:06               ` Peter Zijlstra
2006-09-20 18:06                 ` Peter Zijlstra
2006-09-20 18:14                 ` Rohit Seth
2006-09-20 18:14                   ` Rohit Seth
2006-09-20 18:27                   ` Peter Zijlstra
2006-09-20 18:27                     ` Peter Zijlstra
2006-09-20 18:33                     ` [ckrm-tech] " Paul Menage
2006-09-20 18:33                       ` Paul Menage
2006-09-20 18:38                     ` Rohit Seth
2006-09-20 18:38                       ` Rohit Seth
2006-09-20 19:48                 ` Paul Jackson
2006-09-20 19:48                   ` Paul Jackson
2006-09-20 19:48                 ` Christoph Lameter
2006-09-20 19:48                   ` Christoph Lameter
2006-09-20 19:51                   ` [ckrm-tech] " Paul Menage
2006-09-20 19:51                     ` Paul Menage
2006-09-20 18:37             ` Peter Zijlstra
2006-09-20 18:37               ` Peter Zijlstra
2006-09-20 18:57               ` Rohit Seth
2006-09-20 18:57                 ` Rohit Seth
2006-09-20 13:06 ` [Devel] " Cedric Le Goater
2006-09-20 16:45   ` Rohit Seth
2006-09-20 16:25 ` Christoph Lameter
2006-09-20 16:44   ` Nick Piggin
2006-09-20 16:48     ` Christoph Lameter
2006-09-20 17:07       ` Nick Piggin
2006-09-20 17:12         ` Christoph Lameter
2006-09-20 22:27           ` Paul Jackson
2006-09-20 22:59             ` Christoph Lameter
2006-09-20 17:26   ` Rohit Seth
2006-09-20 17:37     ` [ckrm-tech] " Paul Menage
2006-09-20 17:38     ` Christoph Lameter
2006-09-20 17:42       ` [ckrm-tech] " Paul Menage
2006-09-20 18:07       ` Rohit Seth
2006-09-20 19:51         ` Christoph Lameter
2006-09-20 20:06         ` Paul Jackson
2006-09-20 22:58         ` Paul Jackson
2006-09-20 23:02           ` Christoph Lameter
2006-09-20 23:33             ` Rohit Seth
2006-09-20 23:36               ` Christoph Lameter
2006-09-20 23:39                 ` Rohit Seth
2006-09-20 23:51                   ` Christoph Lameter
2006-09-21  0:05                     ` Paul Jackson
2006-09-21  0:09                       ` [ckrm-tech] " Paul Menage
2006-09-20 23:26           ` Rohit Seth
2006-09-20 23:31             ` Christoph Lameter
2006-09-21  0:51               ` [Lhms-devel] " KAMEZAWA Hiroyuki
2006-09-21  1:33                 ` KAMEZAWA Hiroyuki
2006-09-21  1:36                   ` [ckrm-tech] " Paul Menage
2006-09-20 22:51     ` Paul Jackson
2006-09-20 23:01       ` Christoph Lameter
2006-09-20 23:22       ` Rohit Seth
2006-09-20 23:45         ` Paul Jackson
2006-09-20 17:34   ` Alan Cox
2006-09-20 17:15     ` Christoph Lameter
2006-09-20 17:48       ` Alan Cox
2006-09-20 17:35         ` Christoph Lameter
2006-09-20 23:29         ` Paul Jackson
2006-09-20 23:18       ` Paul Jackson
2006-09-20 17:30     ` [ckrm-tech] " Paul Menage
2006-09-20 23:37       ` Paul Jackson
2006-09-20 23:53         ` Paul Menage
2006-09-21  0:07           ` Paul Jackson
2006-09-21  0:10             ` Paul Menage
2006-09-21  0:17               ` Paul Jackson
2006-09-20 18:34   ` Chandra Seetharaman
2006-09-20 18:43     ` Paul Menage
2006-09-20 18:54       ` Chandra Seetharaman
2006-09-20 19:25         ` Paul Menage
2006-09-20 19:35           ` Chandra Seetharaman
2006-09-20 19:57             ` Paul Menage
2006-09-21  0:30               ` Chandra Seetharaman
2006-09-21  0:33                 ` Paul Jackson
2006-09-21  0:50                   ` Chandra Seetharaman
2006-09-21  0:34                 ` Paul Menage
2006-09-20 20:49           ` Paul Jackson [this message]
2006-09-20 20:51             ` Paul Menage
2006-09-20 21:04               ` Paul Jackson
     [not found]                 ` <6599ad830609201605s2fc1ccbdse31e3e60a50d56bc@mail.google.com>
2006-09-20 23:54                   ` Paul Jackson
2006-09-20 23:57                     ` Paul Menage
2006-09-21  0:09                       ` Paul Jackson
2006-09-21  1:25                   ` Chandra Seetharaman
2006-09-21  0:45             ` Chandra Seetharaman
2006-09-21  0:51               ` Paul Jackson
2006-09-20 19:55         ` Christoph Lameter
2006-09-20 20:27         ` Paul Jackson
2006-09-21 17:02           ` Srivatsa Vaddagiri
2006-09-21 19:29             ` Paul Jackson
2006-09-20 20:11       ` Paul Jackson
2006-09-20 20:17         ` Paul Menage
2006-09-20 19:52     ` Christoph Lameter
2006-09-21  0:31       ` Chandra Seetharaman
2006-09-21  0:36         ` Paul Jackson
2006-09-21  0:42           ` Paul Menage
2006-09-21  1:45             ` Chandra Seetharaman
2006-09-21  1:52               ` Paul Menage
2006-09-21 20:06                 ` Chandra Seetharaman
2006-09-21 20:10                   ` Paul Menage
2006-09-21 21:44                     ` Chandra Seetharaman
2006-09-21 22:09                       ` Paul Menage
2006-09-22  0:06                         ` Chandra Seetharaman
2006-09-22  0:13                           ` Paul Menage
2006-09-22  0:55                             ` Chandra Seetharaman
2006-09-22  0:24                           ` Paul Jackson
2006-09-22  0:57                             ` Chandra Seetharaman
2006-09-22  1:11                               ` Paul Jackson
2006-09-21 21:59                     ` Paul Jackson
2006-09-21 22:07                       ` Paul Menage
2006-09-21 22:48                         ` Paul Jackson
2006-09-20 19:09   ` Chandra Seetharaman
2006-09-27 19:50 ` Chandra Seetharaman
2006-09-27 21:28   ` Rohit Seth
2006-09-27 22:24     ` Chandra Seetharaman
2006-09-28  8:01       ` Balbir Singh
2006-09-28 18:31         ` Rohit Seth
2006-09-28 21:53           ` Balbir Singh
2006-09-29  0:22             ` Rohit Seth
2006-09-28 18:12       ` Rohit Seth
2006-09-28 20:23         ` Chandra Seetharaman
2006-09-28 21:38           ` Rohit Seth

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=20060920134903.fbd9fea8.pj@sgi.com \
    --to=pj@sgi.com \
    --cc=ckrm-tech@lists.sourceforge.net \
    --cc=clameter@sgi.com \
    --cc=devel@openvz.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=menage@google.com \
    --cc=npiggin@suse.de \
    --cc=rohitseth@google.com \
    --cc=sekharan@us.ibm.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.