Re: [RFC net-next] net: mvneta: align xdp stats naming scheme to mlx5 driver

From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 19 Feb 2020 00:19:36 +0100

On 2/18/20 11:23 PM, Toke Høiland-Jørgensen wrote:

quoted

Jakub Kicinski [off-list ref] writes:

quoted

On Tue, 18 Feb 2020 01:14:29 +0100 Lorenzo Bianconi wrote:

quoted

Introduce "rx" prefix in the name scheme for xdp counters
on rx path.
Differentiate between XDP_TX and ndo_xdp_xmit counters

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>

Sorry for coming in late.

I thought the ability to attach a BPF program to a fexit of another
BPF
program will put an end to these unnecessary statistics. IOW I
maintain
my position that there should be no ethtool stats for XDP.

As discussed before real life BPF progs will maintain their own stats
at the granularity of their choosing, so we're just wasting datapath
cycles.

+1

Bugs in bpf programs leading to lack of fundamental statistics.

I think that is absolutely the wrong tradeoff.

And if performance is a concern, we can have a knob to turn off
the xdp counter bumps.  This is something I totally support.