[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <ZvcUyTUF11crCqwK@slm.duckdns.org>
Date: Fri, 27 Sep 2024 10:25:45 -1000
From: Tejun Heo <tj@...nel.org>
To: Zhang Qiao <zhangqiao22@...wei.com>
Cc: David Vernet <void@...ifault.com>, Ingo Molnar <mingo@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
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>,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] sched_ext: Remove redundant p->nr_cpus_allowed checker
On Thu, Sep 26, 2024 at 06:39:49PM +0800, Zhang Qiao wrote:
> select_rq_task() already checked that 'p->nr_cpus_allowed > 1',
> 'p->nr_cpus_allowed == 1' checker in scx_select_cpu_dfl() is redundant.
>
> Signed-off-by: Zhang Qiao <zhangqiao22@...wei.com>
Applied to sched_ext/for-6.12-fixes. I think we probably need a flag to tell
the BPF scheduler whether select_cpu has been called or not. Right now, most
schedulers assume that select_cpu() as called before enqueue() on wakeup
path but that's not true for CPU-affine tasks.
Thanks.
--
tejun
Powered by blists - more mailing lists