[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20231016071756.4ac5b865@kernel.org>
Date: Mon, 16 Oct 2023 07:17:56 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Cc: linux-kernel@...r.kernel.org, netdev@...r.kernel.org,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Paolo Abeni <pabeni@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
Come On Now <hawk@...nel.org>
Subject: Re: [PATCH net-next 0/2] net: Use SMP threads for backlog NAPI (or
optional).
On Mon, 16 Oct 2023 11:53:21 +0200 Sebastian Andrzej Siewior wrote:
> > Do we have reason to believe nobody uses RPS?
>
> Not sure what you relate to. I would assume that RPS is used in general
> on actual devices and not on loopback where backlog is used. But it is
> just an assumption.
> The performance drop, which I observed with RPS and stress-ng --udp, is
> within the same range with threads and IPIs (based on memory). I can
> re-run the test and provide actual numbers if you want.
I was asking about RPS because with your current series RPS processing
is forced into threads. IDK how well you can simulate the kind of
workload which requires RPS. I've seen it used mostly on proxyies
and gateways. For proxies Meta's experiments with threaded NAPI show
regressions across the board. So "force-threading" RPS will most likely
also cause regressions.
Powered by blists - more mailing lists