From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail144.messagelabs.com (mail144.messagelabs.com [216.82.254.51]) by kanga.kvack.org (Postfix) with ESMTP id D4A126B0011 for ; Thu, 12 May 2011 20:55:01 -0400 (EDT) Received: from hpaq6.eem.corp.google.com (hpaq6.eem.corp.google.com [172.25.149.6]) by smtp-out.google.com with ESMTP id p4D0swHl023723 for ; Thu, 12 May 2011 17:54:58 -0700 Received: from qwj8 (qwj8.prod.google.com [10.241.195.72]) by hpaq6.eem.corp.google.com with ESMTP id p4D0sSqO021589 (version=TLSv1/SSLv3 cipher=RC4-SHA bits=128 verify=NOT) for ; Thu, 12 May 2011 17:54:57 -0700 Received: by qwj8 with SMTP id 8so1730143qwj.18 for ; Thu, 12 May 2011 17:54:51 -0700 (PDT) MIME-Version: 1.0 In-Reply-To: <4DCC7E00.60102@redhat.com> References: <1305226032-21448-1-git-send-email-yinghan@google.com> <4DCC7E00.60102@redhat.com> Date: Thu, 12 May 2011 17:54:51 -0700 Message-ID: Subject: Re: [RFC PATCH 0/4] memcg: revisit soft_limit reclaim on contention From: Ying Han Content-Type: multipart/alternative; boundary=0016e64aefdad71a0604a31dc031 Sender: owner-linux-mm@kvack.org List-ID: To: Rik van Riel Cc: Johannes Weiner , KOSAKI Motohiro , Minchan Kim , Daisuke Nishimura , Balbir Singh , Tejun Heo , Pavel Emelyanov , KAMEZAWA Hiroyuki , Andrew Morton , Li Zefan , Mel Gorman , Christoph Lameter , Hugh Dickins , Michal Hocko , Dave Hansen , Zhu Yanhai , linux-mm@kvack.org, Michel Lespinasse --0016e64aefdad71a0604a31dc031 Content-Type: text/plain; charset=ISO-8859-1 On Thu, May 12, 2011 at 5:40 PM, Rik van Riel wrote: > On 05/12/2011 02:47 PM, Ying Han wrote: > > TODO: >> a) there was a question on how to do zone balancing w/o global LRU. This >> could be >> solved by building another cgroup list per-zone, where we also link >> cgroups under >> their soft_limit. We won't scan the list unless the first list being >> exhausted and >> the free pages is still under the high_wmark. >> > > b). one of the tricky part is to calculate the target nr_to_scan for each >> cgroup, >> especially combining the current heuristics with soft_limit exceeds. it >> depends how >> much weight we need to put on the second. One way is to make the ratio to >> be user >> configurable. >> > > Johannes addresses these in his patch series. That would be great, I am reading through his patch and apparently not getting there yet :) > > > Ying Han (4): >> Disable "organizing cgroups over soft limit in a RB-Tree" >> Organize memcgs over soft limit in round-robin. >> Implementation of soft_limit reclaim in round-robin. >> Add some debugging stats >> > > Looks like you also have some things Johannes doesn't have. > > It may be good for the two patch series you have to get > merged into one series, before stuff gets merged upstream. > > Yes, that is my motivation here to post the patch here :) --Ying > -- > All rights reversed > --0016e64aefdad71a0604a31dc031 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable

On Thu, May 12, 2011 at 5:40 PM, Rik van= Riel <riel@redhat.= com> wrote:
On 05/12/2011 02:47 PM, Ying Han wrote:

TODO:
a) there was a question on how to do zone balancing w/o global LRU. This co= uld be
solved by building another cgroup list per-zone, where we also link cgroups= under
their soft_limit. We won't scan the list unless the first list being ex= hausted and
the free pages is still under the high_wmark.

b). one of the tricky part is to calculate the target nr_to_scan for each c= group,
especially combining the current heuristics with soft_limit exceeds. it dep= ends how
much weight we need to put on the second. One way is to make the ratio to b= e user
configurable.

Johannes addresses these in his patch series.

That would be great, I am reading through his patch and apparently not g= etting there yet :)=A0


Ying Han (4):
=A0 Disable "organizing cgroups over soft limit in a RB-Tree" =A0 Organize memcgs over soft limit in round-robin.
=A0 Implementation of soft_limit reclaim in round-robin.
=A0 Add some debugging stats

Looks like you also have some things Johannes doesn't have.

It may be good for the two patch series you have to get
merged into one series, before stuff gets merged upstream.

Yes, that is my motivation here to post the pa= tch here :)

--Ying=A0
--
All rights reversed

--0016e64aefdad71a0604a31dc031-- -- 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