[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAF8kJuOcMDpqZV+9+QjK-hsoJLGhoBzBOczAc7+UMypVJresSw@mail.gmail.com>
Date: Sun, 26 Nov 2023 23:42:11 -0800
From: Chris Li <chrisl@...nel.org>
To: "Huang, Ying" <ying.huang@...el.com>
Cc: Michal Hocko <mhocko@...e.com>,
Yosry Ahmed <yosryahmed@...gle.com>,
Liu Shixin <liushixin2@...wei.com>,
Yu Zhao <yuzhao@...gle.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Sachin Sant <sachinp@...ux.ibm.com>,
Johannes Weiner <hannes@...xchg.org>,
Kefeng Wang <wangkefeng.wang@...wei.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v10] mm: vmscan: try to reclaim swapcache pages if no swap space
Hi Ying,
On Sun, Nov 26, 2023 at 6:36 PM Huang, Ying <ying.huang@...el.com> wrote:
>
> Michal Hocko <mhocko@...e.com> writes:
>
> > On Thu 23-11-23 14:15:59, Huang, Ying wrote:
> >> Michal Hocko <mhocko@...e.com> writes:
> > [...]
> >> > Yes swapcache pages are indeed more complicated but most of the time
> >> > they just go away as well, no?
> >>
> >> When we swapin a page, we will put it in swapcache too. And the page
> >> can be in that state for long time if there is more than 50% free space
> >> in the swap device.
> >
> > True, but why is that a problem? If you encounter such a swapped in page
> > on the file LRU then the page should be referened and as such should be
> > activated, no?
>
> This just means that anonymous pages in file LRU aren't temporary or
> short-term. So we need to consider that. For example, the original
> method to balance between anonymous pages and file pages need to be
> re-designed. The anonymous pages are considered hotter than file pages
> in general.
I agree with Ying that anonymous pages typically have different page
access patterns than file pages, so we might want to treat them
differently to reclaim them effectively.
One random idea:
How about we put the anonymous page in a swap cache in a different LRU
than the rest of the anonymous pages. Then shrinking against those
pages in the swap cache would be more effective.Instead of having
[anon, file] LRU, now we have [anon not in swap cache, anon in swap
cache, file] LRU
Chris
Powered by blists - more mailing lists