Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751538AbWIUUGa (ORCPT ); Thu, 21 Sep 2006 16:06:30 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751539AbWIUUGa (ORCPT ); Thu, 21 Sep 2006 16:06:30 -0400 Received: from e31.co.us.ibm.com ([32.97.110.149]:43956 "EHLO e31.co.us.ibm.com") by vger.kernel.org with ESMTP id S1751538AbWIUUG3 (ORCPT ); Thu, 21 Sep 2006 16:06:29 -0400 Subject: Re: [ckrm-tech] [patch00/05]: Containers(V2)- Introduction From: Chandra Seetharaman Reply-To: sekharan@us.ibm.com To: Paul Menage Cc: Paul Jackson , npiggin@suse.de, ckrm-tech@lists.sourceforge.net, linux-kernel@vger.kernel.org, rohitseth@google.com, devel@openvz.org, clameter@sgi.com In-Reply-To: <6599ad830609201852k12cee6eey9086247c9bdec8b@mail.google.com> References: <1158718568.29000.44.camel@galaxy.corp.google.com> <1158777240.6536.89.camel@linuxchandra> <1158798715.6536.115.camel@linuxchandra> <20060920173638.370e774a.pj@sgi.com> <6599ad830609201742h71d112f4tae8fe390cb874c0b@mail.google.com> <1158803120.6536.139.camel@linuxchandra> <6599ad830609201852k12cee6eey9086247c9bdec8b@mail.google.com> Content-Type: text/plain Organization: IBM Date: Thu, 21 Sep 2006 13:06:26 -0700 Message-Id: <1158869186.6536.205.camel@linuxchandra> Mime-Version: 1.0 X-Mailer: Evolution 2.0.4 (2.0.4-7) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1980 Lines: 55 On Wed, 2006-09-20 at 18:52 -0700, Paul Menage wrote: > On 9/20/06, Chandra Seetharaman wrote: > > > > Interesting. So you could set up the fake node with "guarantee" and let > > it grow till "limit" ? > > Sure - that works great. (Theoretically you could do this all in > userspace - start by assigning "guarantee" nodes to a > container/cpuset and when it gets close to its memory limit assign > more nodes to it. But in practice userspace can't keep up with rapid > memory allocators. > I agree, especially when one of your main object is resource utilization. Think about the magnitude of this when you have to deal with 100s of containers. > > > > BTW, can you do these with fake nodes: > > - dynamic creation > > - dynamic removal > > - dynamic change of size > > The current fake numa support requires you to choose your node layout > at boot time - I've been working with 64 fake nodes of 128M each, > which gives a reasonable granularity for dividing a machine between > multiple different sized jobs. It still will not satisfy what OpenVZ/Container folks are looking for: 100s of containers. > > > > > Also, How could we account when a process moves from one node to > > another ? > > If you want to do that (the systems I'm working on don't really) you > could probably do it with the migrate_pages() syscall. It might not be > that efficient though. Totally agree, that will be very costly. > > Paul -- ---------------------------------------------------------------------- Chandra Seetharaman | Be careful what you choose.... - sekharan@us.ibm.com | .......you may get it. ---------------------------------------------------------------------- - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/