[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200706160815.GH3448022@tassilo.jf.intel.com>
Date: Mon, 6 Jul 2020 09:08:15 -0700
From: Andi Kleen <ak@...ux.intel.com>
To: Michal Hocko <mhocko@...nel.org>
Cc: Michal Suchánek <msuchanek@...e.de>,
David Hildenbrand <david@...hat.com>,
Gautham R Shenoy <ego@...ux.vnet.ibm.com>,
Srikar Dronamraju <srikar@...ux.vnet.ibm.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
Satheesh Rajendran <sathnaga@...ux.vnet.ibm.com>,
Mel Gorman <mgorman@...e.de>,
"Kirill A. Shutemov" <kirill@...temov.name>,
Andrew Morton <akpm@...ux-foundation.org>,
linuxppc-dev@...ts.ozlabs.org, Christopher Lameter <cl@...ux.com>,
Vlastimil Babka <vbabka@...e.cz>
Subject: Re: [PATCH v5 3/3] mm/page_alloc: Keep memoryless cpuless node 0
offline
> > What's the point of this indirection other than another way of avoiding
> > empty node 0?
>
> Honestly, I do not have any idea. I've traced it down to
> Author: Andi Kleen <ak@...e.de>
> Date: Tue Jan 11 15:35:48 2005 -0800
I don't remember all the details, and I can't even find the commit
(is it in linux-historic?).
But AFAIK there's no guarantee PXMs are small and continuous, so it
seemed better to have a clean zero based space.
Back then we had a lot of problems with buggy SRAT tables in BIOS,
so we really tried to avoid trusting the BIOS as much as possible.
-Andi
Powered by blists - more mailing lists