[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20250805154604.680bde07@kernel.org>
Date: Tue, 5 Aug 2025 15:46:04 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Alexander Lobakin <aleksander.lobakin@...el.com>
Cc: <intel-wired-lan@...ts.osuosl.org>, Michal Kubiak
<michal.kubiak@...el.com>, Maciej Fijalkowski
<maciej.fijalkowski@...el.com>, Tony Nguyen <anthony.l.nguyen@...el.com>,
Przemek Kitszel <przemyslaw.kitszel@...el.com>, Andrew Lunn
<andrew+netdev@...n.ch>, "David S. Miller" <davem@...emloft.net>, Eric
Dumazet <edumazet@...gle.com>, "Paolo Abeni" <pabeni@...hat.com>, Alexei
Starovoitov <ast@...nel.org>, "Daniel Borkmann" <daniel@...earbox.net>,
Simon Horman <horms@...nel.org>,
<nxne.cnse.osdt.itp.upstreaming@...el.com>, <bpf@...r.kernel.org>,
<netdev@...r.kernel.org>, <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH iwl-next v3 16/18] idpf: add support for XDP on Rx
On Tue, 5 Aug 2025 18:09:40 +0200 Alexander Lobakin wrote:
> From: Jakub Kicinski <kuba@...nel.org>
> Date: Fri, 1 Aug 2025 15:33:43 -0700
>
> > On Wed, 30 Jul 2025 18:07:15 +0200 Alexander Lobakin wrote:
> >> Use __LIBETH_WORD_ACCESS to parse descriptors more efficiently when
> >> applicable. It really gives some good boosts and code size reduction
> >> on x86_64.
> >
> > Could you perhaps quantify the goodness of the boost with a number? :)
>
> Sure, only a matter of switching this definition and running the tests
> (and bloat-o-meter).
> Intel doesn't allow us to publish raw numbers (Gbps/Mpps), I hope the
> diff in percents (+ bloat-o-meter output) would be enough?
Yes, delta is perfect. Absolute numbers aren't very meaningful if you
don't specify all HW components and FW versions, and direction of wind
on the day, anyway :$
Powered by blists - more mailing lists