Received-SPF: pass (google.com: domain of linux-kernel+bounces-50653-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Precedence: bulk
MIME-Version: 1.0
References: <20240201-b4-zswap-invalidate-entry-v1-0-56ed496b6e55@bytedance.com>
 <20240201-b4-zswap-invalidate-entry-v1-5-56ed496b6e55@bytedance.com>
 <20240201181240.GE321148@cmpxchg.org> <d5455b43-aa22-4931-a6b3-062128f4d30f@bytedance.com>
In-Reply-To: <d5455b43-aa22-4931-a6b3-062128f4d30f@bytedance.com>
From: Yosry Ahmed <yosryahmed@google.com>
Date: Fri, 2 Feb 2024 14:15:19 -0800
Message-ID: <CAJD7tkb-GZriP6+HdgbkvcGTAAO=YZmGtQ1=AAhJkQJj_CmoYQ@mail.gmail.com>
Subject: Re: [PATCH 5/6] mm/zswap: only support zswap_exclusive_loads_enabled
To: Chengming Zhou <zhouchengming@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>, Nhat Pham <nphamcs@gmail.com>, 
	Andrew Morton <akpm@linux-foundation.org>, linux-kernel@vger.kernel.org, 
	linux-mm@kvack.org
Content-Type: text/plain; charset="UTF-8"

> I just A/B test kernel building in tmpfs directory, memory.max=2GB.
> (zswap writeback enabled and shrinker_enabled, one 50GB swapfile)
>
> From the below results, exclusive mode has fewer scan and refault.
>
>                               zswap-invalidate-entry        zswap-invalidate-entry-exclusive
> real                          63.80                         63.01
> user                          1063.83                       1061.32
> sys                           290.31                        266.15
>                               zswap-invalidate-entry        zswap-invalidate-entry-exclusive
> workingset_refault_anon       2383084.40                    1976397.40
> workingset_refault_file       44134.00                      45689.40
> workingset_activate_anon      837878.00                     728441.20
> workingset_activate_file      4710.00                       4085.20
> workingset_restore_anon       732622.60                     639428.40
> workingset_restore_file       1007.00                       926.80
> workingset_nodereclaim        0.00                          0.00
> pgscan                        14343003.40                   12409570.20
> pgscan_kswapd                 0.00                          0.00
> pgscan_direct                 14343003.40                   12409570.20
> pgscan_khugepaged             0.00                          0.00

I think the numbers look really good, and as I mentioned, we have been
doing this in production for many years now, so:

Acked-by: Yosry Ahmed <yosryahmed@google.com>