[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201110152429.GA5283@ranger.igk.intel.com>
Date: Tue, 10 Nov 2020 16:24:29 +0100
From: Maciej Fijalkowski <maciej.fijalkowski@...el.com>
To: Jesper Dangaard Brouer <brouer@...hat.com>
Cc: Hangbin Liu <liuhangbin@...il.com>, bpf@...r.kernel.org,
netdev@...r.kernel.org, Daniel Borkmann <daniel@...earbox.net>,
John Fastabend <john.fastabend@...il.com>,
Toke Høiland-Jørgensen <toke@...hat.com>,
Tariq Toukan <tariqt@...lanox.com>,
Jakub Kicinski <kuba@...nel.org>
Subject: Re: [PATCH bpf-next] samples/bpf: add xdp_redirect_map with xdp_prog
support
On Tue, Nov 10, 2020 at 03:25:10PM +0100, Jesper Dangaard Brouer wrote:
> On Tue, 10 Nov 2020 20:46:39 +0800
> Hangbin Liu <liuhangbin@...il.com> wrote:
>
> > This patch add running xdp program on egress interface support for
> > xdp_redirect_map sample. The new prog will change the IP ttl based
> > on egress ifindex.
> >
> > Signed-off-by: Hangbin Liu <liuhangbin@...il.com>
> > ---
> > samples/bpf/xdp_redirect_map_kern.c | 74 ++++++++++++++++++++++++++++-
> > samples/bpf/xdp_redirect_map_user.c | 21 ++++----
>
> Hmmm... I don't think is it a good idea to modify xdp_redirect_map this way.
>
> The xdp_redirect_map is used for comparative benchmarking and
> mentioned+used in scientific articles. As far as I can see, this
> change will default slowdown xdp_redirect_map performance, right?
+1
User should be able to trigger attachment of this xdp egress prog by
himself. I don't like having it as a mandatory thing on this sample.
>
> --
> Best regards,
> Jesper Dangaard Brouer
> MSc.CS, Principal Kernel Engineer at Red Hat
> LinkedIn: http://www.linkedin.com/in/brouer
>
Powered by blists - more mailing lists