From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756168Ab3FQOBL (ORCPT ); Mon, 17 Jun 2013 10:01:11 -0400 Received: from cantor2.suse.de ([195.135.220.15]:43542 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754688Ab3FQOBK (ORCPT ); Mon, 17 Jun 2013 10:01:10 -0400 Date: Mon, 17 Jun 2013 16:01:08 +0200 From: Michal Hocko To: Andrew Morton , Johannes Weiner , KAMEZAWA Hiroyuki Cc: linux-mm@kvack.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, Ying Han , Hugh Dickins , Michel Lespinasse , Greg Thelen , Tejun Heo , Balbir Singh , Glauber Costa Subject: Re: [patch v4] Soft limit rework Message-ID: <20130617140108.GE5018@dhcp22.suse.cz> References: <1370254735-13012-1-git-send-email-mhocko@suse.cz> <20130611154353.GF31277@dhcp22.suse.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20130611154353.GF31277@dhcp22.suse.cz> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue 11-06-13 17:43:53, Michal Hocko wrote: > JFYI, I have rebased the series on top of the current mmotm tree to > catch up with Mel's changes in reclaim and other small things here and > there. To be sure that the things are still good I have started my tests > again which will take some time. And it took way more time than I would like but the current mmotm is broken and crashes/hangs and misbehaves in strange ways. At first I thought it is my -mm git tree that is broken but then when I started testing with linux-next I could see issues as well. I was able to reduce the space to slab shrinkers rework but bisection led to nothing reasonable. I will report those issues in a separate email when I collect all necessary information. In the meantime I will retest on top of my -mm tree without slab shrinkers patches applied. This should be OK for the soft reclaim work because memcg shrinkers are still not merged into mm tree and they shouldn't be affected by the soft reclaim as the reclaim is per shrink_zone now. -- Michal Hocko SUSE Labs