[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20171123211837.0f5efa8b@xeon-e3>
Date: Thu, 23 Nov 2017 21:18:37 -0800
From: Stephen Hemminger <stephen@...workplumber.org>
To: Solio Sarabia <solio.sarabia@...el.com>
Cc: netdev@...r.kernel.org, davem@...eloft.net, kys@...rosoft.com,
shiny.sebastian@...el.com, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] net-sysfs: export gso_max_size attribute
On Wed, 22 Nov 2017 16:30:41 -0800
Solio Sarabia <solio.sarabia@...el.com> wrote:
> The netdevice gso_max_size is exposed to allow users fine-control on
> systems with multiple NICs with different GSO buffer sizes, and where
> the virtual devices like bridge and veth, need to be aware of the GSO
> size of the underlying devices.
>
> In a virtualized environment, setting the right GSO sizes for physical
> and virtual devices makes all TSO work to be on physical NIC, improving
> throughput and reducing CPU util. If virtual devices send buffers
> greater than what NIC supports, it forces host to do TSO for buffers
> exceeding the limit, increasing CPU utilization in host.
>
> Suggested-by: Shiny Sebastian <shiny.sebastian@...el.com>
> Signed-off-by: Solio Sarabia <solio.sarabia@...el.com>
> ---
> In one test scenario with Hyper-V host, Ubuntu 16.04 VM, with Docker
> inside VM, and NTttcp sending 40 Gbps from one container, setting the
> right gso_max_size values for all network devices in the chain, reduces
> CPU overhead about 3x (for the sender), since all TSO work is done by
> physical NIC.
>
> net/core/net-sysfs.c | 30 ++++++++++++++++++++++++++++++
> 1 file changed, 30 insertions(+)
You probably should expose gso_max_segs as well.
Powered by blists - more mailing lists