Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:8 as permitted sender) client-ip=2620:137:e000::3:8;
MIME-Version: 1.0
References: <20231206-zswap-lock-optimize-v1-0-e25b059f9c3a@bytedance.com>
In-Reply-To: <20231206-zswap-lock-optimize-v1-0-e25b059f9c3a@bytedance.com>
From:   Nhat Pham <nphamcs@gmail.com>
Date:   Wed, 6 Dec 2023 09:24:31 -0800
Message-ID: <CAKEwX=NXcY3_GuKbh0=Ceg9wj=7u4y0NgmfSVEG3-+deY0jiWQ@mail.gmail.com>
Subject: Re: [PATCH 0/7] mm/zswap: optimize the scalability of zswap rb-tree
To:     Chengming Zhou <zhouchengming@bytedance.com>
Cc:     Vitaly Wool <vitaly.wool@konsulko.com>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Michal Hocko <mhocko@kernel.org>,
        Seth Jennings <sjenning@redhat.com>,
        Dan Streetman <ddstreet@ieee.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Yosry Ahmed <yosryahmed@google.com>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, Chris Li <chrisl@kernel.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

+ Chris Li

Chris, I vaguely remember from our last conversation that you have
some concurrent efforts to use xarray here right?

On Wed, Dec 6, 2023 at 1:46=E2=80=AFAM Chengming Zhou
<zhouchengming@bytedance.com> wrote:
>
> Hi everyone,
>
> This patch series is based on the linux-next 20231205, which depends on
> the "workload-specific and memory pressure-driven zswap writeback" series
> from Nhat Pham.
>
> When testing the zswap performance by using kernel build -j32 in a tmpfs
> directory, I found the scalability of zswap rb-tree is not good, which
> is protected by the only spinlock. That would cause heavy lock contention
> if multiple tasks zswap_store/load concurrently.
>
> So a simple solution is to split the only one zswap rb-tree into multiple
> rb-trees, each corresponds to SWAP_ADDRESS_SPACE_PAGES (64M). This idea i=
s
> from the commit 4b3ef9daa4fc ("mm/swap: split swap cache into 64MB trunks=
").
>
> Although this method can't solve the spinlock contention completely, it
> can mitigate much of that contention.
>
> Another problem when testing the zswap using our default zsmalloc is that
> zswap_load() and zswap_writeback_entry() have to malloc a temporary memor=
y
> to support !zpool_can_sleep_mapped().
>
> Optimize it by reusing the percpu crypto_acomp_ctx->dstmem, which is also
> used by zswap_store() and protected by the same percpu crypto_acomp_ctx->=
mutex.
>
> Thanks for review and comment!
>
> To: Andrew Morton <akpm@linux-foundation.org>
> To: Seth Jennings <sjenning@redhat.com>
> To: Dan Streetman <ddstreet@ieee.org>
> To: Vitaly Wool <vitaly.wool@konsulko.com>
> To: Nhat Pham <nphamcs@gmail.com>
> To: Johannes Weiner <hannes@cmpxchg.org>
> To: Yosry Ahmed <yosryahmed@google.com>
> To: Michal Hocko <mhocko@kernel.org>
> Cc: linux-kernel@vger.kernel.org
> Cc: linux-mm@kvack.org
> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
>
> ---
> Chengming Zhou (7):
>       mm/zswap: make sure each swapfile always have zswap rb-tree
>       mm/zswap: split zswap rb-tree
>       mm/zswap: reuse dstmem when decompress
>       mm/zswap: change dstmem size to one page
>       mm/zswap: refactor out __zswap_load()
>       mm/zswap: cleanup zswap_load()
>       mm/zswap: cleanup zswap_reclaim_entry()
>
>  include/linux/zswap.h |   4 +-
>  mm/swapfile.c         |  10 ++-
>  mm/zswap.c            | 233 +++++++++++++++++++++-----------------------=
------
>  3 files changed, 106 insertions(+), 141 deletions(-)
> ---
> base-commit: 0f5f12ac05f36f117e793656c3f560625e927f1b
> change-id: 20231206-zswap-lock-optimize-06f45683b02b
>
> Best regards,
> --
> Chengming Zhou <zhouchengming@bytedance.com>