[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CANn89iLgWc6vZZo0tD0XVg0zY-T-eUjKj4r=O_B3QARjFB755Q@mail.gmail.com>
Date: Tue, 10 Dec 2024 17:12:37 +0100
From: Eric Dumazet <edumazet@...gle.com>
To: Frederik Deweerdt <deweerdt.lkml@...il.com>
Cc: netdev@...r.kernel.org, "David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>, Simon Horman <horms@...nel.org>,
Kuniyuki Iwashima <kuniyu@...zon.com>, Michal Luczaj <mhal@...x.co>, David Howells <dhowells@...hat.com>,
linux-kernel@...r.kernel.org, xiyou.wangcong@...il.com,
David.Laight@...lab.com, jdamato@...tly.com, stable@...r.kernel.org
Subject: Re: [PATCH v2 net] splice: do not checksum AF_UNIX sockets
On Tue, Dec 10, 2024 at 6:06 AM Frederik Deweerdt
<deweerdt.lkml@...il.com> wrote:
>
> When `skb_splice_from_iter` was introduced, it inadvertently added
> checksumming for AF_UNIX sockets. This resulted in significant
> slowdowns, for example when using sendfile over unix sockets.
>
> Using the test code in [1] in my test setup (2G single core qemu),
> the client receives a 1000M file in:
> - without the patch: 1482ms (+/- 36ms)
> - with the patch: 652.5ms (+/- 22.9ms)
>
> This commit addresses the issue by marking checksumming as unnecessary in
> `unix_stream_sendmsg`
>
> Cc: stable@...r.kernel.org
> Signed-off-by: Frederik Deweerdt <deweerdt.lkml@...il.com>
> Fixes: 2e910b95329c ("net: Add a function to splice pages into an skbuff for MSG_SPLICE_PAGES")
> ---
Reviewed-by: Eric Dumazet <edumazet@...gle.com>
Powered by blists - more mailing lists