[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <147658a7-bf29-d2db-a4b6-f8638f973ba7@suse.cz>
Date: Wed, 21 Sep 2016 11:49:09 +0200
From: Vlastimil Babka <vbabka@...e.cz>
To: Dave Hansen <dave.hansen@...ux.intel.com>,
Mike Kravetz <mike.kravetz@...cle.com>,
Gerald Schaefer <gerald.schaefer@...ibm.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Naoya Horiguchi <n-horiguchi@...jp.nec.com>
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org,
Michal Hocko <mhocko@...e.cz>,
"Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
"Aneesh Kumar K . V" <aneesh.kumar@...ux.vnet.ibm.com>,
Martin Schwidefsky <schwidefsky@...ibm.com>,
Heiko Carstens <heiko.carstens@...ibm.com>,
Rui Teng <rui.teng@...ux.vnet.ibm.com>
Subject: Re: [PATCH 0/1] memory offline issues with hugepage size > memory
block size
On 09/20/2016 07:45 PM, Dave Hansen wrote:
> On 09/20/2016 10:37 AM, Mike Kravetz wrote:
>>
>> Their approach (I believe) would be to fail the offline operation in
>> this case. However, I could argue that failing the operation, or
>> dissolving the unused huge page containing the area to be offlined is
>> the right thing to do.
>
> I think the right thing to do is dissolve the whole huge page if even a
> part of it is offlined. The only question is what to do with the
> gigantic remnants.
Just free them into the buddy system? Or what are the alternatives?
Creating smaller huge pages (if supported)? That doesn't make much
sense. Offline it completely? That's probably not what the user requested.
Vlastimil
Powered by blists - more mailing lists