lkml.org 
[lkml]   [2021]   [Nov]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: [RFC PATCH] mm: migrate: Add new node demotion strategy
Date
Dave Hansen <dave.hansen@intel.com> writes:

> On 11/4/21 7:51 PM, Huang, Ying wrote:
>>> Let's also try to do it with the existing node_demotion[] data
>>> structure before we go adding more.
>> To avoid cache ping-pong, I guess some kind of per-CPU data structure
>> may be more suitable for interleaving among multiple nodes.
>
> It would probably be better to just find something that's more
> read-heavy. Like, instead of keeping a strict round-robin, just
> randomly select one of the notes to which you can round-robin.
>
> That will scale naturally without having to worry about caching or fancy
> per-cpu data structures.

Yes. That sounds good. And per-CPU data structure is used inside
random API too :-)

Best Regards,
Huang, Ying

\
 
 \ /
  Last update: 2021-11-08 03:13    [W:0.469 / U:0.076 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site