[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87efbd1prm.fsf@toke.dk>
Date: Thu, 22 Nov 2018 09:26:53 +0100
From: Toke Høiland-Jørgensen <toke@...e.dk>
To: Saeed Mahameed <saeedm@...lanox.com>,
"pstaszewski\@itcare.pl" <pstaszewski@...are.pl>,
"netdev\@vger.kernel.org" <netdev@...r.kernel.org>,
"dsahern\@gmail.com" <dsahern@...il.com>
Cc: "davem\@davemloft.net" <davem@...emloft.net>,
"jasowang\@redhat.com" <jasowang@...hat.com>,
"brouer\@redhat.com" <brouer@...hat.com>,
"mst\@redhat.com" <mst@...hat.com>
Subject: Re: consistency for statistics with XDP mode
Saeed Mahameed <saeedm@...lanox.com> writes:
>> > I'd say it sounds reasonable to include XDP in the normal traffic
>> > counters, but having the detailed XDP-specific counters is quite
>> > useful
>> > as well... So can't we do both (for all drivers)?
>> >
>
> What are you thinking ?
> reporting XDP_DROP in interface dropped counter ?
> and XDP_TX/REDIRECT in the TX counter ?
> XDP_ABORTED in the err/drop counter ?
>
> how about having a special XDP command in the .ndo_bpf that would query
> the standardized XDP stats ?
Don't have any strong opinions on the mechanism; just pointing out that
the XDP-specific stats are useful to have separately as well :)
-Toke
Powered by blists - more mailing lists