[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <8fcea325-ca5f-0abd-34e0-1ac7b092e2fb@gentwo.org>
Date: Mon, 8 Sep 2025 08:25:48 -0700 (PDT)
From: "Christoph Lameter (Ampere)" <cl@...two.org>
To: Frederic Weisbecker <frederic@...nel.org>
cc: Adam Li <adamli@...amperecomputing.com>, anna-maria@...utronix.de,
tglx@...utronix.de, mingo@...hat.com, peterz@...radead.org,
juri.lelli@...hat.com, vincent.guittot@...aro.org, vschneid@...hat.com,
dietmar.eggemann@....com, rostedt@...dmis.org, bsegall@...gle.com,
mgorman@...e.de, linux-kernel@...r.kernel.org, patches@...erecomputing.com
Subject: Re: [PATCH RESEND 1/2] tick/nohz: Fix wrong NOHZ idle CPU state
On Fri, 5 Sep 2025, Frederic Weisbecker wrote:
> isolcpus for domain isolation is indeed in the way for long term deprecation
> and the only replacement possible is cpuset, which overhead is only visible
> on partition creation and update.
>
> We could argue on the interface, the point is that nohz_full doesn't make sense
> without domain isolation.
Most use cases I see use nohz_full on all cpus and rely on the OS to
exempt the sheperd cpu.
Powered by blists - more mailing lists