[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Y36PF972kOK3ADvx@cmpxchg.org>
Date: Wed, 23 Nov 2022 16:22:31 -0500
From: Johannes Weiner <hannes@...xchg.org>
To: Yu Zhao <yuzhao@...gle.com>
Cc: Ivan Babrou <ivan@...udflare.com>, Linux MM <linux-mm@...ck.org>,
Linux Kernel Network Developers <netdev@...r.kernel.org>,
linux-kernel <linux-kernel@...r.kernel.org>,
Michal Hocko <mhocko@...nel.org>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Shakeel Butt <shakeelb@...gle.com>,
Muchun Song <songmuchun@...edance.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Eric Dumazet <edumazet@...gle.com>,
"David S. Miller" <davem@...emloft.net>,
Hideaki YOSHIFUJI <yoshfuji@...ux-ipv6.org>,
David Ahern <dsahern@...nel.org>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>, cgroups@...r.kernel.org,
kernel-team <kernel-team@...udflare.com>
Subject: Re: Low TCP throughput due to vmpressure with swap enabled
On Tue, Nov 22, 2022 at 05:44:44PM -0700, Yu Zhao wrote:
> Hi Johannes,
>
> Do you think it makes sense to have the below for both the baseline and
> MGLRU or it's some behavior change that the baseline doesn't want to
> risk?
It looks good to me. Besides the new FMODE_NOREUSE, it's also a nice
cleanup on the rmap side!
It would just be good to keep the comment from folio_referenced_one() and
move it to the vma_has_locality() check in invalid_folio_referenced_vma().
Otherwise,
Acked-by: Johannes Weiner <hannes@...xchg.org>
Powered by blists - more mailing lists