Re: [PATCH net-next 0/5] devlink rate police limiter

[Jakub Kicinski <kuba@kernel.org>]

On Thu, 7 Jul 2022 13:20:12 +0200 Jiri Pirko wrote:
> Wait. Lets draw the basic picture of "the wire":
> 
> --------------------------+                +--------------------------
> eswitch representor netdev|=====thewire====|function (vf/sf/whatever
> --------------------------+                +-------------------------
> 
> Now the rate setting Dima is talking about, it is the configuration of
> the "function" side. Setting the rate is limitting the "function" TX/RX
> Note that this function could be of any type - netdev, rdma, vdpa, nvme.

The patches add policing, are you saying we're gonna drop RDMA or NVMe
I/O?

> Configuring the TX/RX rate (including groupping) applies to all of
> these.

I don't understand why the "side of the wire" matters when the patches
target both Rx and Tx. Surely that covers both directions.

> Putting the configuration on the eswitch representor does not fit:
> 1) it is configuring the other side of the wire, the configuration
>    should be of the eswitch port. Configuring the other side is
>    confusing and misleading. For the purpose of configuring the
>    "function" side, we introduced "port function" object in devlink.
> 2) it is confuguring netdev/ethernet however the confuguration applies
>    to all queues of the function.

If you think it's technically superior to put it in devlink that's fine.
I'll repeat myself - what I'm asking for is convergence so that drivers
don't have  to implement 3 different ways of configuring this. We have
devlink rate for from-VF direction shaping, tc police for bi-dir
policing and obviously legacy NDOs. None of them translate between each
other so drivers and user space have to juggle interfaces.