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. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753282Ab1IGBKh (ORCPT ); Tue, 6 Sep 2011 21:10:37 -0400 Received: from mx2.parallels.com ([64.131.90.16]:39467 "EHLO mx2.parallels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751399Ab1IGBKa (ORCPT ); Tue, 6 Sep 2011 21:10:30 -0400 Message-ID: <4E66C45A.8060706@parallels.com> Date: Tue, 6 Sep 2011 22:09:46 -0300 From: Glauber Costa User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:6.0) Gecko/20110816 Thunderbird/6.0 MIME-Version: 1.0 To: Paul Menage CC: , , , , , "David S. Miller" , Hiroyouki Kamezawa , "Eric W. Biederman" Subject: Re: [PATCH] per-cgroup tcp buffer limitation References: <1315276556-10970-1-git-send-email-glommer@parallels.com> In-Reply-To: Content-Type: text/plain; charset="ISO-8859-1"; format=flowed Content-Transfer-Encoding: 7bit X-Originating-IP: [201.82.132.238] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@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. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail6.bemta8.messagelabs.com (mail6.bemta8.messagelabs.com [216.82.243.55]) by kanga.kvack.org (Postfix) with ESMTP id 6BE726B016B for ; Tue, 6 Sep 2011 21:10:36 -0400 (EDT) Message-ID: <4E66C45A.8060706@parallels.com> Date: Tue, 6 Sep 2011 22:09:46 -0300 From: Glauber Costa MIME-Version: 1.0 Subject: Re: [PATCH] per-cgroup tcp buffer limitation References: <1315276556-10970-1-git-send-email-glommer@parallels.com> In-Reply-To: Content-Type: text/plain; charset="ISO-8859-1"; format=flowed Content-Transfer-Encoding: 7bit Sender: owner-linux-mm@kvack.org List-ID: 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" 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. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: email@kvack.org