[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAAmzW4OOe9+NHZ5CxL-e=Gf8rd4MwtM-C2+L14uWQBc6zoXsWA@mail.gmail.com>
Date: Fri, 3 Jul 2020 09:54:23 +0900
From: Joonsoo Kim <js1304@...il.com>
To: Vlastimil Babka <vbabka@...e.cz>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
Linux Memory Management List <linux-mm@...ck.org>,
LKML <linux-kernel@...r.kernel.org>,
Johannes Weiner <hannes@...xchg.org>,
Michal Hocko <mhocko@...nel.org>,
Hugh Dickins <hughd@...gle.com>,
Minchan Kim <minchan@...nel.org>,
Mel Gorman <mgorman@...hsingularity.net>, kernel-team@....com,
Joonsoo Kim <iamjoonsoo.kim@....com>,
Matthew Wilcox <willy@...radead.org>
Subject: Re: [PATCH v6 6/6] mm/vmscan: restore active/inactive ratio for
anonymous LRU
2020년 7월 2일 (목) 오후 10:45, Vlastimil Babka <vbabka@...e.cz>님이 작성:
>
> On 6/17/20 7:26 AM, js1304@...il.com wrote:
> > From: Joonsoo Kim <iamjoonsoo.kim@....com>
> >
> > Now, workingset detection is implemented for anonymous LRU.
> > We don't have to worry about the misfound for workingset due to
> > the ratio of active/inactive. Let's restore the ratio.
>
> How about:
>
> Now that workingset detection is implemented for anonymous LRU, we don't need
> large inactive list to allow detecting frequently accessed pages before they are
> reclaimed, anymore. This effectively reverts the temporary measure put in by
> commit "mm/vmscan: make active/inactive ratio as 1:1 for anon lru".
Much better!. I will use the comment you suggested. Thanks.
> > Acked-by: Johannes Weiner <hannes@...xchg.org>
> > Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@....com>
>
> Acked-by: Vlastimil Babka <vbabka@...e.cz>
>
> Thanks!
> I still hope Matthew can review updated patch 4/6 (I'm not really familiar with
> proper xarray handling), and Johannes patch 5/6.
Okay, I hope so, too. :)
> And then we just need a nice Documentation file describing how reclaim really
> works after all the recent changes :)
Agreed.
Thanks.
Powered by blists - more mailing lists