[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240827021351.iq6i7zkwm32xili3@oppo.com>
Date: Tue, 27 Aug 2024 10:13:51 +0800
From: Hailong Liu <hailong.liu@...o.com>
To: Lokesh Gidra <lokeshgidra@...gle.com>
CC: Suren Baghdasaryan <surenb@...gle.com>, Nicolas Geoffray
<ngeoffray@...gle.com>, Barry Song <21cnbao@...il.com>, Michal Hocko
<mhocko@...e.com>, gaoxu <gaoxu2@...or.com>, Andrew Morton
<akpm@...ux-foundation.org>, "linux-mm@...ck.org" <linux-mm@...ck.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>, Shaohua Li
<shli@...com>, yipengxiang <yipengxiang@...or.com>, fengbaopeng
<fengbaopeng@...or.com>, Kalesh Singh <kaleshsingh@...gle.com>
Subject: Re: [PATCH v2] mm: add lazyfree folio to lru tail
On Mon, 26. Aug 09:37, Lokesh Gidra wrote:
>
> IMHO, within LRU_INACTIVE_FILE, MADV_FREE'ed pages should be
> prioritized for reclamation over file ones.
> >
> > Adding Lokesh.
> > Lokesh, could you please comment on the reasoning behind the above
> > mentioned change?
>
> Adding Nicolas as well, in case he wants to add something.
IMHO, lruvec_add_folio is enough. if lruvec_add_folio_tail why not use
MADV_DONTNEED instead? In MM the reclaim policy prefer to reclaim file cache, if
MADV_FREE'd pages directly add to the tail, they might be reclaimed instantly.
Also the benefit of workingset_refault_file cannot be convinced for me.
So we should know the reasons and the benefits of the changes. page faults or ?
> >
> > >
> > > >
> > > > --
> > > > Michal Hocko
> > > > SUSE Labs
> > > >
> > >
> > > Thanks
> > > Barry
>
--
Help you, Help me,
Hailong.
Powered by blists - more mailing lists