Received-SPF: pass (google.com: domain of linux-kernel+bounces-120022-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Precedence: bulk
MIME-Version: 1.0
References: <20240325235018.2028408-1-yosryahmed@google.com> <20240325235018.2028408-6-yosryahmed@google.com>
In-Reply-To: <20240325235018.2028408-6-yosryahmed@google.com>
From: Nhat Pham <nphamcs@gmail.com>
Date: Tue, 26 Mar 2024 15:01:18 -0700
Message-ID: <CAKEwX=N=mbaHFwqgMsc8Zb8tCLfSeowBEPyd1H2nOO2L8Qemgg@mail.gmail.com>
Subject: Re: [RFC PATCH 5/9] mm: zswap: remove zswap_same_filled_pages_enabled
To: Yosry Ahmed <yosryahmed@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>, Johannes Weiner <hannes@cmpxchg.org>, 
	Chengming Zhou <chengming.zhou@linux.dev>, linux-mm@kvack.org, linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Mon, Mar 25, 2024 at 4:50=E2=80=AFPM Yosry Ahmed <yosryahmed@google.com>=
 wrote:
>
> There is no logical reason to refuse storing same-filled pages more
> efficiently and opt for compression. Remove the userspace knob.
>

Agree. Absolutely no idea why we have this knob in the first place -
if you have cycles to compress, you probably have some extra cycles to
check same-filled page state? And that is the only cost I can think of
- it wins on probably all other aspects: memory usage,
"decompression", no need to write back these pages etc.

Any actual zswap user who has data or counter-use case should chime
in, but FWIW, my vote is:
Reviewed-by: Nhat Pham <nphamcs@gmail.com>