lkml.org 
[lkml]   [2019]   [Feb]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCHv4 10/13] node: Add memory caching attributes
From
Date

Le 11/02/2019 à 16:23, Keith Busch a écrit :
> On Sun, Feb 10, 2019 at 09:19:58AM -0800, Jonathan Cameron wrote:
>> On Sat, 9 Feb 2019 09:20:53 +0100
>> Brice Goglin <Brice.Goglin@inria.fr> wrote:
>>
>>> Hello Keith
>>>
>>> Could we ever have a single side cache in front of two NUMA nodes ? I
>>> don't see a way to find that out in the current implementation. Would we
>>> have an "id" and/or "nodemap" bitmask in the sidecache structure ?
>> This is certainly a possible thing for hardware to do.
>>
>> ACPI IIRC doesn't provide any means of representing that - your best
>> option is to represent it as two different entries, one for each of the
>> memory nodes. Interesting question of whether you would then claim
>> they were half as big each, or the full size. Of course, there are
>> other possible ways to get this info beyond HMAT, so perhaps the interface
>> should allow it to be exposed if available?
> HMAT doesn't do this, but I want this interface abstracted enough from
> HMAT to express whatever is necessary.
>
> The CPU cache is the closest existing exported attributes to this,
> and they provide "shared_cpu_list". To that end, I can export a
> "shared_node_list", though previous reviews strongly disliked multi-value
> sysfs entries. :(
>
> Would shared-node symlinks capture the need, and more acceptable?


As a user-space guy reading these files/symlinks, I would prefer reading
a bitmask just like we do for CPU cache "cpumap" or CPU "siblings" files
(or sibling_list).

Reading a directory and looking for dentries matching "foo%d" is far
less convenient  in C. If all these files are inside a dedicated
subdirectory, it's better but still not as easy.

Brice


\
 
 \ /
  Last update: 2019-02-12 09:11    [W:0.065 / U:0.120 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site