From mboxrd@z Thu Jan 1 00:00:00 1970 From: Glauber Costa Subject: Re: [PATCH] per-cgroup tcp buffer limitation Date: Tue, 6 Sep 2011 22:09:46 -0300 Message-ID: <4E66C45A.8060706@parallels.com> References: <1315276556-10970-1-git-send-email-glommer@parallels.com> Mime-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-1"; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: Sender: netdev-owner@vger.kernel.org To: Paul Menage Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, containers@lists.osdl.org, netdev@vger.kernel.org, xemul@parallels.com, "David S. Miller" , Hiroyouki Kamezawa , "Eric W. Biederman" List-Id: containers.vger.kernel.org On 09/06/2011 10:08 PM, Paul Menage wrote: > On Mon, Sep 5, 2011 at 7:35 PM, Glauber Costa wrote: >> This patch introduces per-cgroup tcp buffers limitation. This allows >> sysadmins to specify a maximum amount of kernel memory that >> tcp connections can use at any point in time. TCP is the main interest >> in this work, but extending it to other protocols would be easy. Hi Paul, > The general idea of limiting total socket buffer memory consumed by a > cgroup is a fine idea, but I think it needs to be integrated more > closely with the existing kernel memory cgroup tracking efforts, > especially if you're trying to use as generic a name as "kmem" for it. Can you be more specific? The generic part of kmem cgroup in this patch is quite simple. I think any other patchset would have a very easy time merging things into it. 90 % is sockets. > > I agree with Kamezawa's comments that you need a lot more documentation. Working on it right now.