[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <069a5533-2689-6764-2ec5-9ef0a1351860@oracle.com>
Date: Tue, 30 Jan 2018 18:40:58 -0800
From: Mike Kravetz <mike.kravetz@...cle.com>
To: Anshuman Khandual <khandual@...ux.vnet.ibm.com>,
Michal Hocko <mhocko@...nel.org>
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org,
akpm@...ux-foundation.org
Subject: Re: [RFC] mm/migrate: Add new migration reason MR_HUGETLB
On 01/30/2018 06:25 PM, Anshuman Khandual wrote:
> On 01/30/2018 01:29 PM, Michal Hocko wrote:
>> On Tue 30-01-18 08:37:14, Anshuman Khandual wrote:
>>> alloc_contig_range() initiates compaction and eventual migration for
>>> the purpose of either CMA or HugeTLB allocation. At present, reason
>>> code remains the same MR_CMA for either of those cases. Lets add a
>>> new reason code which will differentiate the purpose of migration
>>> as HugeTLB allocation instead.
>> Why do we need it?
>
> The same reason why we have MR_CMA (maybe some other ones as well) at
> present, for reporting purpose through traces at the least. It just
> seemed like same reason code is being used for two different purpose
> of migration.
>
I was 'thinking' that we could potentially open up alloc_contig_range()
for more general purpose use. Users would not call alloc_contig_range
directly, but it would be wrapped in a more user friendly API. Or,
perhaps it gets modified and becomes something else. Still just thinking
as part of "how do we provide a more general purpose interface for
allocation of more than MAX_ORDER contiguous pages?".
Not sure that we should be adding to the current alloc_contig_range
interface until we decide it is something which will be useful long term.
--
Mike Kravetz
Powered by blists - more mailing lists