[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CALvZod65Y-dSkH6a=ASTDTK2oGznTd7Yts1csttxoP0w9jaQUw@mail.gmail.com>
Date: Fri, 11 Aug 2023 19:33:54 -0700
From: Shakeel Butt <shakeelb@...gle.com>
To: Ivan Babrou <ivan@...udflare.com>
Cc: Waiman Long <longman@...hat.com>, cgroups@...r.kernel.org,
Linux MM <linux-mm@...ck.org>,
kernel-team <kernel-team@...udflare.com>,
Johannes Weiner <hannes@...xchg.org>,
Michal Hocko <mhocko@...nel.org>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Muchun Song <muchun.song@...ux.dev>,
Andrew Morton <akpm@...ux-foundation.org>,
linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: Expensive memory.stat + cpu.stat reads
Hi Ivan,
(sorry for late response as I was away)
On Fri, Aug 11, 2023 at 3:35 PM Ivan Babrou <ivan@...udflare.com> wrote:
[...]
> > > I spent some time looking into this and I think I landed on a fix:
> > >
> > > * https://github.com/bobrik/linux/commit/50b627811d54
> > >
> > > I'm not 100% sure if it's the right fix for the issue, but it reduces
> > > the runtime significantly.
In your patch, can you try to replace mem_cgroup_flush_stats() with
mem_cgroup_flush_stats_ratelimited() instead of cgroup_rstat_flush().
I wanted to see if you observe any stale stats issues.
Powered by blists - more mailing lists