[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CANn89i+Xdo-=4daFxCsRr2w5Yai=cpL=19Uv+WmaNsxtaXS2+g@mail.gmail.com>
Date: Tue, 5 Mar 2024 16:33:24 +0100
From: Eric Dumazet <edumazet@...gle.com>
To: Jakub Kicinski <kuba@...nel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@...utronix.de>, Paolo Abeni <pabeni@...hat.com>, netdev@...r.kernel.org,
"David S. Miller" <davem@...emloft.net>, Jesper Dangaard Brouer <hawk@...nel.org>,
Thomas Gleixner <tglx@...utronix.de>, Wander Lairson Costa <wander@...hat.com>, Yan Zhai <yan@...udflare.com>
Subject: Re: [PATCH v3 net-next 2/4] net: Allow to use SMP threads for backlog NAPI.
On Tue, Mar 5, 2024 at 4:23 PM Jakub Kicinski <kuba@...nel.org> wrote:
>
> On Tue, 5 Mar 2024 11:35:30 +0100 Sebastian Andrzej Siewior wrote:
> > I had RH benchmarking this and based on their 25Gbe and 50Gbe NICs and
> > the results look good. If anything it looked a bit better with this on
> > the 50Gbe NICs but since those NICs have RSS…
>
> TBH if y'all tested this with iperf that's pretty meaningless.
> The concern is not as much throughput on an idle system as it
> is the fact that we involve scheduler with it's heuristics
> for every NAPI run.
> But I recognize that your access to production workloads may
> be limited and you did more than most, so 🤷️
(sorry for duplicate of this message, user error from my side, using HTML)
I was hoping to run tests on 200Gbit NIC, but current net-next tree
broke the idpf driver
(at least for the FW running on my NIC)
:/
Powered by blists - more mailing lists