[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <0c0480f3-6793-4d3e-bdbe-c503d50a0c02@nvidia.com>
Date: Mon, 17 Mar 2025 22:53:10 +0100
From: Joel Fernandes <joelagnelf@...dia.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: linux-kernel@...r.kernel.org, Andrea Righi <arighi@...dia.com>,
Tejun Heo <tj@...nel.org>, Ingo Molnar <mingo@...hat.com>,
Juri Lelli <juri.lelli@...hat.com>,
Vincent Guittot <vincent.guittot@...aro.org>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Steven Rostedt <rostedt@...dmis.org>, Ben Segall <bsegall@...gle.com>,
Mel Gorman <mgorman@...e.de>, Valentin Schneider <vschneid@...hat.com>,
David Vernet <void@...ifault.com>, Changwoo Min <changwoo@...lia.com>,
Luigi De Matteis <ldematteis123@...il.com>, paulmck@...nel.org,
boqun.feng@...il.com
Subject: Re: [PATCH RFC 3/8] sched/ext: Add a DL server for sched_ext tasks
Hello, Peter,
I replied to other parts of your email in another thread so I am just replying
to this part:
On 3/17/2025 11:31 AM, Peter Zijlstra wrote:
>
> Also; I gotta ask, why is nvidia looking at ext ?
There are some complex CPU topologies which perform poorly with the existing
FAIR scheduler as reported by people (I have not seen the data though so there's
that).
There are also workloads where it is beneficial to schedule on cores which have
the data in their cache and are submitting work to GPGPU, which makes the GPGPU
operations faster.
thanks,
- Joel
Powered by blists - more mailing lists