From mboxrd@z Thu Jan 1 00:00:00 1970 From: Vladimir Davydov Subject: Re: [patch] mm: memcontrol: support transparent huge pages under pressure Date: Tue, 23 Sep 2014 15:44:38 +0400 Message-ID: <20140923114438.GI18526@esperanza> References: <1411132840-16025-1-git-send-email-hannes@cmpxchg.org> <20140923082927.GG18526@esperanza> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Return-path: Content-Disposition: inline In-Reply-To: <20140923082927.GG18526@esperanza> Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: Content-Transfer-Encoding: 7bit To: Greg Thelen Cc: Johannes Weiner , linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, Michal Hocko , Dave Hansen , cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org On Tue, Sep 23, 2014 at 12:29:27PM +0400, Vladimir Davydov wrote: > On Mon, Sep 22, 2014 at 10:52:50PM -0700, Greg Thelen wrote: > > In this condition, if res usage is at limit then there's no point in > > swapping because memsw.usage is already maximal. Prior to this patch > > I think the kernel did the right thing, but not afterwards. > > > > Before this patch: > > if res.usage == res.limit, try_charge() indirectly calls > > try_to_free_mem_cgroup_pages(noswap=true) > > But this is wrong. If we fail to charge res, we should try to do swap > out along with page cache reclaim. Swap out won't affect memsw.usage, > but will diminish res.usage so that the allocation may succeed. Oops, I missed your point, sorry. If we hit the res.limit and memsw.limit=res.limit, we automatically hit memsw.limit too, so there's no point swapping out. Thanks, Vladimir