From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753436AbeDPT7u (ORCPT ); Mon, 16 Apr 2018 15:59:50 -0400 Received: from mx2.suse.de ([195.135.220.15]:55045 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752934AbeDPT7t (ORCPT ); Mon, 16 Apr 2018 15:59:49 -0400 Subject: Re: [PATCH 3/3] dcache: account external names as indirectly reclaimable memory To: Michal Hocko Cc: Johannes Weiner , Minchan Kim , Roman Gushchin , linux-mm@kvack.org, Andrew Morton , Alexander Viro , linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@fb.com, lsf-pc@lists.linux-foundation.org References: <20180305133743.12746-1-guro@fb.com> <20180305133743.12746-5-guro@fb.com> <20180413133519.GA213834@rodete-laptop-imager.corp.google.com> <20180413135923.GT17484@dhcp22.suse.cz> <13f1f5b5-f3f8-956c-145a-4641fb996048@suse.cz> <20180413142821.GW17484@dhcp22.suse.cz> <20180413143716.GA5378@cmpxchg.org> <20180416114144.GK17484@dhcp22.suse.cz> <1475594b-c1ad-9625-7aeb-ad8ad385b793@suse.cz> <20180416122747.GM17484@dhcp22.suse.cz> From: Vlastimil Babka Message-ID: Date: Mon, 16 Apr 2018 21:57:50 +0200 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.6.0 MIME-Version: 1.0 In-Reply-To: <20180416122747.GM17484@dhcp22.suse.cz> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 04/16/2018 02:27 PM, Michal Hocko wrote: > On Mon 16-04-18 14:06:21, Vlastimil Babka wrote: >> >> For example the percpu (and other) array caches... >> >>> maybe it will turn out that such a large >>> portion of the chache would need to duplicate the state that a >>> completely new cache would be more reasonable. >> >> I'm afraid that's the case, yes. >> >>> Is this worth exploring >>> at least? I mean something like this should help with the fragmentation >>> already AFAIU. Accounting would be just free on top. >> >> Yep. It could be also CONFIG_urable so smaller systems don't need to >> deal with the memory overhead of this. >> >> So do we put it on LSF/MM agenda? > > If you volunteer to lead the discussion, then I do not have any > objections. Sure, let's add the topic of SLAB_MINIMIZE_WASTE [1] as well. Something like "Supporting reclaimable kmalloc caches and large non-buddy-sized objects in slab allocators" ? [1] https://marc.info/?l=linux-mm&m=152156671614796&w=2