Re: [PATCH v4 4/4] mm: memcg: use non-unified stats flushing for userspace reads

From: Wei Xu <weixugc@google.com>
To: Michal Hocko <mhocko@suse.com>
Cc: "Yosry Ahmed" <yosryahmed@google.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Johannes Weiner" <hannes@cmpxchg.org>,
	"Roman Gushchin" <roman.gushchin@linux.dev>,
	"Shakeel Butt" <shakeelb@google.com>,
	"Muchun Song" <muchun.song@linux.dev>,
	"Ivan Babrou" <ivan@cloudflare.com>, "Tejun Heo" <tj@kernel.org>,
	"Michal Koutný" <mkoutny@suse.com>,
	"Waiman Long" <longman@redhat.com>,
	linux-mm@kvack.org, cgroups@vger.kernel.org,
	linux-kernel@vger.kernel.org, "Greg Thelen" <gthelen@google.com>
Subject: Re: [PATCH v4 4/4] mm: memcg: use non-unified stats flushing for userspace reads
Date: Mon, 11 Sep 2023 12:15:24 -0700	[thread overview]
Message-ID: <CAAPL-u8NndkB2zHRtF8pVBSTsz854YmUbx62G7bpw6BMJiLaiQ@mail.gmail.com> (raw)
In-Reply-To: <ZP8SDdjut9VEVpps@dhcp22.suse.cz>

On Mon, Sep 11, 2023 at 6:11 AM Michal Hocko <mhocko@suse.com> wrote:
>
> On Thu 07-09-23 17:52:12, Wei Xu wrote:
> [...]
> > I tested this patch on a machine with 384 CPUs using a microbenchmark
> > that spawns 10K threads, each reading its memory.stat every 100
> > milliseconds.
>
> This is rather extreme case but I wouldn't call it utterly insane
> though.
>
> > Most of memory.stat reads take 5ms-10ms in kernel, with
> > ~5% reads even exceeding 1 second.
>
> Just curious, what would numbers look like if the mutex is removed and
> those threads would be condending on the existing spinlock with lock
> dropping in place and removed. Would you be willing to give it a shot?

Without the mutex and with the spinlock only, the common read latency
of memory.stat is still 5ms-10ms in kernel. There are very few reads
(<0.003%) going above 10ms and none more than 1 second.

> --
> Michal Hocko
> SUSE Labs