From mboxrd@z Thu Jan 1 00:00:00 1970 From: Toke =?utf-8?Q?H=C3=B8iland-J=C3=B8rgensen?= Subject: Re: consistency for statistics with XDP mode Date: Thu, 22 Nov 2018 18:00:33 +0100 Message-ID: <87r2fdm4i6.fsf@toke.dk> References: <1d9a6548-4d1d-6624-e808-6ab0460a8655@gmail.com> <874lca2kvv.fsf@toke.dk> <651ddca3-91e0-5ad6-6afe-46aaa4bd24c9@itcare.pl> <636c1a4b9010eab5d461c13c7544a1d9e9f9ff3f.camel@mellanox.com> <87efbd1prm.fsf@toke.dk> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Cc: "davem\@davemloft.net" , "jasowang\@redhat.com" , "brouer\@redhat.com" , "mst\@redhat.com" To: David Ahern , Saeed Mahameed , "pstaszewski\@itcare.pl" , "netdev\@vger.kernel.org" Return-path: Received: from mail.toke.dk ([52.28.52.200]:60847 "EHLO mail.toke.dk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2388150AbeKWDkv (ORCPT ); Thu, 22 Nov 2018 22:40:51 -0500 In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: David Ahern writes: > On 11/22/18 1:26 AM, Toke H=C3=B8iland-J=C3=B8rgensen wrote: >> Saeed Mahameed writes: >>=20 >>>>> 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 ?=20 >>> 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 ? >>=20 >> Don't have any strong opinions on the mechanism; just pointing out that >> the XDP-specific stats are useful to have separately as well :) >> > > I would like to see basic packets, bytes, and dropped counters tracked > for Rx and Tx via the standard netdev counters for all devices. This is > for ease in accounting as well as speed and simplicity for bumping > counters for virtual devices from bpf helpers. > > From there, the XDP ones can be in the driver private stats as they are > currently but with some consistency across drivers for redirects, drops, > any thing else. > > So not a radical departure from where we are today, just getting the > agreement for consistency and driver owners to make the changes. Sounds good to me :) -Toke