Received-SPF: pass (google.com: domain of linux-kernel+bounces-215048-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
From: Andi Kleen <ak@linux.intel.com>
To: Usama Arif <usamaarif642@gmail.com>
Cc: akpm@linux-foundation.org,  hannes@cmpxchg.org,  shakeel.butt@linux.dev,
  david@redhat.com,  ying.huang@intel.com,  hughd@google.com,
  willy@infradead.org,  yosryahmed@google.com,  nphamcs@gmail.com,
  chengming.zhou@linux.dev,  linux-mm@kvack.org,
  linux-kernel@vger.kernel.org,  kernel-team@meta.com
Subject: Re: [PATCH v5 1/2] mm: store zero pages to be swapped out in a bitmap
In-Reply-To: <20240614100902.3469724-2-usamaarif642@gmail.com> (Usama Arif's
	message of "Fri, 14 Jun 2024 11:07:05 +0100")
References: <20240614100902.3469724-1-usamaarif642@gmail.com>
	<20240614100902.3469724-2-usamaarif642@gmail.com>
Date: Fri, 14 Jun 2024 07:45:37 -0700
Message-ID: <87ed8zmvla.fsf@linux.intel.com>
User-Agent: Gnus/5.13 (Gnus v5.13)
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain

Usama Arif <usamaarif642@gmail.com> writes:

> Approximately 10-20% of pages to be swapped out are zero pages [1].
> Rather than reading/writing these pages to flash resulting
> in increased I/O and flash wear, a bitmap can be used to mark these
> pages as zero at write time, and the pages can be filled at
> read time if the bit corresponding to the page is set.
> With this patch, NVMe writes in Meta server fleet decreased
> by almost 10% with conventional swap setup (zswap disabled).
>
> [1] https://lore.kernel.org/all/20171018104832epcms5p1b2232e2236258de3d03d1344dde9fce0@epcms5p1/

But how much did the CPU time increase? Surely the new loop is not free?

-Andi