Received-SPF: pass (google.com: domain of linux-kernel+bounces-118042-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Precedence: bulk
MIME-Version: 1.0
References: <20240320-zswap-xarray-v8-1-dc08ee9f8744@kernel.org> <20240325133546.ffd728d1c309ba58eadb179c@linux-foundation.org>
In-Reply-To: <20240325133546.ffd728d1c309ba58eadb179c@linux-foundation.org>
From: Chris Li <chrisl@kernel.org>
Date: Mon, 25 Mar 2024 14:29:41 -0700
Message-ID: <CANeU7QkDuXeR8MzKvnPcN5odkpDQJ3bMW_nSRHbZGffPkiXW-Q@mail.gmail.com>
Subject: Re: [PATCH v8] zswap: replace RB tree with xarray
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, 
	Yosry Ahmed <yosryahmed@google.com>, Nhat Pham <nphamcs@gmail.com>, 
	Johannes Weiner <hannes@cmpxchg.org>, Chengming Zhou <zhouchengming@bytedance.com>, 
	Barry Song <v-songbaohua@oppo.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Mon, Mar 25, 2024 at 1:35=E2=80=AFPM Andrew Morton <akpm@linux-foundatio=
n.org> wrote:
>
> On Wed, 20 Mar 2024 12:31:38 -0700 Chris Li <chrisl@kernel.org> wrote:
>
> > Very deep RB tree requires rebalance at times. That
> > contributes to the zswap fault latencies. Xarray does not
> > need to perform tree rebalance. Replacing RB tree to xarray
> > can have some small performance gain.
> >
> > One small difference is that xarray insert might fail with
> > ENOMEM, while RB tree insert does not allocate additional
> > memory.
> >
> > The zswap_entry size will reduce a bit due to removing the
> > RB node, which has two pointers and a color field. Xarray
> > store the pointer in the xarray tree rather than the
> > zswap_entry. Every entry has one pointer from the xarray
> > tree. Overall, switching to xarray should save some memory,
> > if the swap entries are densely packed.
> >
> > Notice the zswap_rb_search and zswap_rb_insert always
> > followed by zswap_rb_erase. Use xa_erase and xa_store
> > directly. That saves one tree lookup as well.
> >
> > Remove zswap_invalidate_entry due to no need to call
> > zswap_rb_erase any more. Use zswap_free_entry instead.
> >
> > The "struct zswap_tree" has been replaced by "struct xarray".
> > The tree spin lock has transferred to the xarray lock.
> >
> > Run the kernel build testing 10 times for each version, averages:
> > (memory.max=3D2GB, zswap shrinker and writeback enabled,
> > one 50GB swapfile, 24 HT core, 32 jobs)
> >
>
> So this conflits with Johannes's "mm: zswap: fix data loss on
> SWP_SYNCHRONOUS_IO devices", right in the critical part of
> zswap_load().  Naive resolution of that conflict would have resulted in
> basically reverting Johannes's fix.
>
> That fix is cc:stable so we do want it to have a clean run in
> linux-next before sending it upstream.  So I'll drop this patch
> ("zswap: replace RB tree with xarray") for now.  Please redo it against
> latest mm-unstable and of course, be sure to preserve Johannes's fix,
> thanks.

Sure, I will wait for your mm-unstable update that contains Jonanne's
fix then re-submit a new version.

Chris