Date: Mon, 3 Apr 2017 11:18:19 +0200
From: Michal Hocko <mhocko@kernel.org>
To: Wei Yang <richard.weiyang@gmail.com>
Cc: mgorman@techsingularity.net, jiang.liu@linux.intel.com,
        akpm@linux-foundation.org, tj@kernel.org, mingo@kernel.org,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC] calc_memmap_size() isn't accurate and one suggestion to
 improve
Message-ID: <20170403091818.GI24661@dhcp22.suse.cz>
References: <20170328011137.GA8655@WeideMacBook-Pro.local>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20170328011137.GA8655@WeideMacBook-Pro.local>
User-Agent: Mutt/1.5.23 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 832
Lines: 28

On Tue 28-03-17 09:11:37, Wei Yang wrote:
> Hi, masters,
> 
> # What I found
> 
> I found the function calc_memmap_size() may not be that accurate to get the
> pages for memmap.
> 
> The reason is:
> 
> > memmap is allocated on a node base,
> > while the calculation is on a zone base
> 
> This applies both to SPARSEMEM and FLATMEM.
> 
> For example, on my laptop with 6G memory, all the memmap space is allocated
> from ZONE_NORMAL.

Please try to be more specific. Why is this a problem? Are you trying to
fix some bad behavior or you want to make it more optimal?

I am sorry I didn't look closer into your proposal but I am quite busy
and other people are probably in a similar situation. If you want to get
a proper feedback please try to state the problem and be explicit if it
is user observable.
-- 
Michal Hocko
SUSE Labs