[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180719140327.GB10988@techadventures.net>
Date: Thu, 19 Jul 2018 16:03:27 +0200
From: Oscar Salvador <osalvador@...hadventures.net>
To: Michal Hocko <mhocko@...nel.org>
Cc: akpm@...ux-foundation.org, pasha.tatashin@...cle.com,
vbabka@...e.cz, aaron.lu@...el.com, iamjoonsoo.kim@....com,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
Oscar Salvador <osalvador@...e.de>
Subject: Re: [PATCH v2 3/5] mm/page_alloc: Optimize free_area_init_core
On Thu, Jul 19, 2018 at 03:44:17PM +0200, Michal Hocko wrote:
> On Thu 19-07-18 15:27:38, osalvador@...hadventures.net wrote:
> > From: Oscar Salvador <osalvador@...e.de>
> >
> > In free_area_init_core we calculate the amount of managed pages
> > we are left with, by substracting the memmap pages and the pages
> > reserved for dma.
> > With the values left, we also account the total of kernel pages and
> > the total of pages.
> >
> > Since memmap pages are calculated from zone->spanned_pages,
> > let us only do these calculcations whenever zone->spanned_pages is greather
> > than 0.
>
> But why do we care? How do we test this? In other words, why is this
> worth merging?
Uhm, unless the values are going to be updated, why do we want to go through all
comparasions/checks?
I thought it was a nice thing to have the chance to skip that block unless we are going to
update the counters.
Again, if you think this only adds complexity and no good, I can drop it.
Thanks
--
Oscar Salvador
SUSE L3
Powered by blists - more mailing lists