Re: [PATCH net 3/3] net: fec: increase the size of tx ring and update thresholds of tx ring

[Andrew Lunn <andrew@lunn.ch>]

> Sorry, the Vybrid platform is not currently maintained by us, and Vybrid is also not
> included in our usual Yocto SDK RC version.

Your Yocto SDK version does not matter. We are talking about mainline
here... You are maintaining the mainline driver, and submitting
patches to extend the mainline driver.

> Even I find a Vybrid board, I think it
> probably cann't run with the latest kernel image, because the latest kernel image
> does not match with the old Yocto SDK, and new Yocto SDK does not support Vybrid
> platform. I also asked my colleague in test team who is in charge of ethernet testing,
> she hadn't even heard of Vybrid platform.

Well 6.5-rc1 does run on Vybrid, i have a number of boards with
it. You will also find that many inflight entertainment systems have a
box under each row of seats in a aeroplane with a Vybrid controlling a
Marvell switch. Take a look at arch/arm/boot/dts/vf610-zii-* You will
also find a number of DTS files for imx5i, imx6, imx7 used for ZII
products which are back of the seat displays, and make heavy use of
networking with the FEC.

So i have in interest in the FEC for all these platforms.

> > And a bigger burst means more latency. Read about Buffer bloat.
> > 
> Perhaps, but not necessarily. For example, in some cases that some burst packets
> maybe stay in Qdisc instead of hardware queue if ring size is small.

Which is what you want, so high priority packets can jump to the head
of the queue.

> > While you have iperf running saturating the link, try a ping as well. How does
> > ping latency change with more TX buffers?
> > 
> Per your suggestions, I tested on i.MX8ULP, i.MX8MM and i.MX93 platforms. The
> results do not appear to be very different.

Thanks for the benchmark numbers. They look O.K.

       Andrew