[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <6ce19e4e-34ed-69c9-186d-03035d966ae1@gmail.com>
Date: Wed, 8 Feb 2017 22:12:24 +0530
From: Balbir Singh <bsingharora@...il.com>
To: Anshuman Khandual <khandual@...ux.vnet.ibm.com>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org
Cc: mhocko@...e.com, vbabka@...e.cz, mgorman@...e.de,
minchan@...nel.org, aneesh.kumar@...ux.vnet.ibm.com,
srikar@...ux.vnet.ibm.com, haren@...ux.vnet.ibm.com,
jglisse@...hat.com, dave.hansen@...el.com, dan.j.williams@...el.com
Subject: Re: [PATCH 0/3] Define coherent device memory node
On 02/08/2017 07:31 PM, Anshuman Khandual wrote:
> This three patches define CDM node with HugeTLB & Buddy allocation
> isolation. Please refer to the last RFC posting mentioned here for details.
> The series has been split for easier review process. The next part of the
> work like VM flags, auto NUMA and KSM interactions with tagged VMAs will
> follow later.
>
> https://lkml.org/lkml/2017/1/29/198
>
> Optional Buddy allocation isolation methods
>
> (1) GFP flag based (mm_cdm_v1_optional_gfp)
> (2) Zonelist rebuilding (mm_cdm_v1_optional_zonelist)
> (3) Cpuset (mm_cdm_v1_optional_cpusets)
>
> All of these optional methods as well as the posted nodemask (mm_cdm_v1)
> approach can be accessed from the following git tree.
>
Definitely much better looking, in general I like the approach and
would ack it. Lets stick to mm_cdm_v1 (this post) as a starting point
Balbir Singh.
Powered by blists - more mailing lists