Re: [PATCH net-next v3 02/23] docs: ethtool: document that rx_buf_len must control payload lengths

[Mina Almasry]

On Mon, Aug 18, 2025 at 6:56 AM Pavel Begunkov <asml.silence@xxxxxxxxx> wrote:
>
> From: Jakub Kicinski <kuba@xxxxxxxxxx>
>
> Document the semantics of the rx_buf_len ethtool ring param.
> Clarify its meaning in case of HDS, where driver may have
> two separate buffer pools.
>
> The various zero-copy TCP Rx schemes we have suffer from memory

nit: 'we have suffer' sounds weird, probably meant just 'suffer'.

> management overhead. Specifically applications aren't too impressed
> with the number of 4kB buffers they have to juggle. Zero-copy
> TCP makes most sense with larger memory transfers so using
> 16kB or 32kB buffers (with the help of HW-GRO) feels more
> natural.
>
> Signed-off-by: Jakub Kicinski <kuba@xxxxxxxxxx>
> Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>

Reviewed-by: Mina Almasry <almasrymina@xxxxxxxxxx>

-- 
Thanks,
Mina