[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CACKFLi=nD76sHPFALg8dzR6Oj2CDGsZqbjY1gS_9ZKdo-KJrHQ@mail.gmail.com>
Date: Sat, 1 Jul 2023 16:09:53 -0700
From: Michael Chan <michael.chan@...adcom.com>
To: Parav Pandit <parav@...dia.com>
Cc: aelior@...vell.com, skalluru@...vell.com, manishc@...vell.com,
netdev@...r.kernel.org, edumazet@...gle.com, davem@...emloft.net,
kuba@...nel.org, pabeni@...hat.com, dsahern@...nel.org
Subject: Re: [PATCH net-next] tcp: Make GRO completion function inline
On Sun, Jun 11, 2023 at 7:08 AM Parav Pandit <parav@...dia.com> wrote:
>
> At 100G link speed, with 1500 MTU, at 8.2 mpps, if device does GRO for
> 64K message size, currently it results in ~190k calls to
> tcp_gro_complete() in data path.
>
> Inline this small routine to avoid above number of function calls.
>
> Suggested-by: David Ahern <dsahern@...nel.org>
> Signed-off-by: Parav Pandit <parav@...dia.com>
>
> ---
> This patch is untested as I do not have the any of the 3 hw devices
> calling this routine.
>
> qede, bnxt and bnx2x maintainers,
>
> Can you please verify it with your devices if it reduces cpu
> utilization marginally or it stays same or has some side effects?
>
> ---
Sorry for the delay. It works fine on bnxt NICs running hardware GRO.
No noticeable changes in throughput or CPU utilization running simple
netperf. Thanks.
Tested-by: Michael Chan <michael.chan@...adcom.com>
Reviewed-by: Michael Chan <michael.chan@...adcom.com>
Download attachment "smime.p7s" of type "application/pkcs7-signature" (4209 bytes)
Powered by blists - more mailing lists