Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753138AbdDKSP1 (ORCPT ); Tue, 11 Apr 2017 14:15:27 -0400 Received: from mx2.suse.de ([195.135.220.15]:43654 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753001AbdDKSP0 (ORCPT ); Tue, 11 Apr 2017 14:15:26 -0400 Date: Tue, 11 Apr 2017 20:15:20 +0200 From: Michal Hocko To: js1304@gmail.com Cc: Andrew Morton , Rik van Riel , Johannes Weiner , mgorman@techsingularity.net, Laura Abbott , Minchan Kim , Marek Szyprowski , Michal Nazarewicz , "Aneesh Kumar K . V" , Vlastimil Babka , Russell King , Will Deacon , linux-mm@kvack.org, linux-kernel@vger.kernel.org, kernel-team@lge.com, Joonsoo Kim Subject: Re: [PATCH v7 0/7] Introduce ZONE_CMA Message-ID: <20170411181519.GC21171@dhcp22.suse.cz> References: <1491880640-9944-1-git-send-email-iamjoonsoo.kim@lge.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1491880640-9944-1-git-send-email-iamjoonsoo.kim@lge.com> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 911 Lines: 20 Hi, I didn't get to read though patches yet but the cover letter didn't really help me to understand the basic concepts to have a good starting point before diving into implementation details. It contains a lot of history remarks which is not bad but IMHO too excessive here. I would appreciate the following information (some of that is already provided in the cover but could benefit from some rewording/text reorganization). - what is ZONE_CMA and how it is configured (from admin POV) - how does ZONE_CMA compare to other zones - who is allowed to allocate from this zone and what are the guarantees/requirements for successful allocation - how does the zone compare to a preallocate allocation pool - how is ZONE_CMA balanced/reclaimed due to internal memory pressure (from CMA users) - is this zone reclaimable for the global memory reclaim - why this was/is controversial -- Michal Hocko SUSE Labs