From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754862AbYDTIU3 (ORCPT ); Sun, 20 Apr 2008 04:20:29 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752047AbYDTIUO (ORCPT ); Sun, 20 Apr 2008 04:20:14 -0400 Received: from e28smtp02.in.ibm.com ([59.145.155.2]:35095 "EHLO e28smtp02.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752086AbYDTIUK (ORCPT ); Sun, 20 Apr 2008 04:20:10 -0400 Message-ID: <480AFBE5.1070702@linux.vnet.ibm.com> Date: Sun, 20 Apr 2008 13:46:37 +0530 From: Balbir Singh Reply-To: balbir@linux.vnet.ibm.com Organization: IBM User-Agent: Thunderbird 2.0.0.12 (X11/20080226) MIME-Version: 1.0 To: Paul Menage CC: Pavel Emelianov , YAMAMOTO Takashi , linux-kernel@vger.kernel.org, linux-mm@kvack.org, containers@lists.osdl.org, KAMEZAWA Hiroyuki Subject: Re: [RFC][-mm] Memory controller hierarchy support (v1) References: <20080419053551.10501.44302.sendpatchset@localhost.localdomain> <6599ad830804190849u31f13191m4dcca4e471493c2b@mail.gmail.com> In-Reply-To: <6599ad830804190849u31f13191m4dcca4e471493c2b@mail.gmail.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Paul Menage wrote: > On Fri, Apr 18, 2008 at 10:35 PM, Balbir Singh > wrote: >> 1. We need to hold cgroup_mutex while walking through the children >> in reclaim. We need to figure out the best way to do so. Should >> cgroups provide a helper function/macro for it? > > There's already a function, cgroup_lock(). But it would be nice to > avoid such a heavy locking here, particularly since memory allocations > can occur with cgroup_mutex held, which could lead to a nasty deadlock > if the allocation triggered reclaim. > Hmm.. probably.. > One of the things that I've been considering was to put the > parent/child/sibling hierarchy explicitly in cgroup_subsys_state. This > would give subsystems their own copy to refer to, and could use their > own internal locking to synchronize with callbacks from cgroups that > might change the hierarchy. Cpusets could make use of this too, since > it has to traverse hierarchies sometimes. > Very cool! I look forward to that infrastructure. I'll also look at the cpuset code and see how to traverse the hierarchy. >> 2. Do not allow children to have a limit greater than their parents. >> 3. Allow the user to select if hierarchial support is required > > My thoughts on this would be: > > 1) Never attach a first-level child's counter to its parent. As > Yamamoto points out, otherwise we end up with extra global operations > whenever any cgroup allocates or frees memory. Limiting the total > system memory used by all user processes doesn't seem to be something > that people are going to generally want to do, and if they really do > want to they can just create a non-root child and move the whole > system into that. > > The one big advantage that you currently get from having all > first-level children be attached to the root is that the reclaim logic > automatically scans other groups when it reaches the top-level - but I > think that can be provided as a special-case in the reclaim traversal, > avoiding the overhead of hitting the root cgroup that we have in this > patch. > I've been doing some thinking along these lines, I'll think more about this. > 2) Always attach other children's counters to their parents - if the > user didn't want a hierarchy, they could create a flat grouping rather > than nested groupings. > Yes, that's a TODO > Paul -- Warm Regards, Balbir Singh Linux Technology Center IBM, ISTL