[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <5ff0b3ed-b02c-e198-3b27-931bdcde502d@intel.com>
Date: Mon, 1 Feb 2021 09:49:44 -0800
From: Dave Hansen <dave.hansen@...el.com>
To: David Rientjes <rientjes@...gle.com>,
Dave Hansen <dave.hansen@...ux.intel.com>
Cc: linux-kernel@...r.kernel.org, linux-mm@...ck.org,
yang.shi@...ux.alibaba.com, ying.huang@...el.com,
dan.j.williams@...el.com, david@...hat.com, osalvador@...e.de
Subject: Re: [RFC][PATCH 04/13] mm/numa: node demotion data structure and
lookup
On 1/30/21 5:19 PM, David Rientjes wrote:
> On Mon, 25 Jan 2021, Dave Hansen wrote:
>
>> diff -puN mm/migrate.c~0006-node-Define-and-export-memory-migration-path mm/migrate.c
>> --- a/mm/migrate.c~0006-node-Define-and-export-memory-migration-path 2021-01-25 16:23:09.553866709 -0800
>> +++ b/mm/migrate.c 2021-01-25 16:23:09.558866709 -0800
>> @@ -1161,6 +1161,22 @@ out:
>> return rc;
>> }
>>
>> +static int node_demotion[MAX_NUMNODES] = {[0 ... MAX_NUMNODES - 1] = NUMA_NO_NODE};
>
> __read_mostly?
Yep, that's sane. I'll fix that up in the next revision.
Powered by blists - more mailing lists