Received-SPF: pass (google.com: domain of linux-kernel+bounces-56624-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Precedence: bulk
MIME-Version: 1.0
References: <20240206010311.149103-1-jdamato@fastly.com> <7e338c2a-6091-4093-8ca2-bb3b2af3e79d@gmail.com>
 <20240206171159.GA11565@fastly.com> <44d321bf-88a0-4d6f-8572-dfbda088dd8f@nvidia.com>
 <20240206192314.GA11982@fastly.com> <b3c595d8-b30a-41ac-bb82-c1264678b3c4@nvidia.com>
 <20240207142529.GA12897@fastly.com>
In-Reply-To: <20240207142529.GA12897@fastly.com>
From: Dave Taht <dave.taht@gmail.com>
Date: Wed, 7 Feb 2024 09:31:33 -0500
Message-ID: <CAA93jw6_KMR_T6vs5S40n6OGeCdxbhikE7DCEAbN1N8_nFW_5g@mail.gmail.com>
Subject: Re: [PATCH net-next] eth: mlx5: link NAPI instances to queues and IRQs
To: Joe Damato <jdamato@fastly.com>
Cc: Gal Pressman <gal@nvidia.com>, Tariq Toukan <tariqt@nvidia.com>, 
	Tariq Toukan <ttoukan.linux@gmail.com>, linux-kernel@vger.kernel.org, 
	netdev@vger.kernel.org, rrameshbabu@nvidia.com, 
	Saeed Mahameed <saeedm@nvidia.com>, Leon Romanovsky <leon@kernel.org>, 
	"David S. Miller" <davem@davemloft.net>, Eric Dumazet <edumazet@google.com>, 
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>, 
	"open list:MELLANOX MLX5 core VPI driver" <linux-rdma@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Wed, Feb 7, 2024 at 9:26=E2=80=AFAM Joe Damato <jdamato@fastly.com> wrot=
e:
>
> On Wed, Feb 07, 2024 at 08:59:18AM +0200, Gal Pressman wrote:
> > On 06/02/2024 21:23, Joe Damato wrote:
> > >> The per queue coalesce series is going through internal code review,=
 and is
> > >> expected to also be ready in a matter of a few weeks.
> > >
> > > OK, great. Thanks for letting me know; we are definitely interested i=
n
> > > using this feature.
> >
> > Hi Joe,
> > Can you please share some details about your usecase for this feature?
>
> It was outlined in the cover letter for the RFC [1].
>
> But, briefly: we set a number of queues (say 16) via ethtool. We then
> create a series of n-tuple filters directing certain flows to queues 0-7
> via a custom RSS context. The remaining queues, 8-15 are for all other
> flows via the default RSS context.
>
> Queues 0-7 are used with busy polling from userland so we want those queu=
es
> to have a larger rx/tx-usecs rx/tx-frames than queues 8-15.

I am looking forward to trying this to chop some usec off of eBPF. I
am curious as to how low can you go...

> We implemented basic support for this in the RFC we sent to the mailing
> list.

thank you for re-citing this:

> [1]: https://lore.kernel.org/lkml/20230823223121.58676-1-dev@nalramli.com=
/

The big feature that I hope appears in some ethernet card someday the
ability to map (say 16k) LPMs to a hw queue, as opposed to a mere
tuple. It's the biggest overhead operation we have (presently in
vectoring data via ebpf) to libreqos for 10k+ ISP subscribers.

>


--=20
40 years of net history, a couple songs:
https://www.youtube.com/watch?v=3DD9RGX6QFm5E
Dave T=C3=A4ht CSO, LibreQos