[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAAofZF4h65MTAgEuK5+EfE5SocFE3FfGWAcrLv=6fvZrgFtAWQ@mail.gmail.com>
Date: Tue, 30 Dec 2025 11:25:04 +0100
From: Marco Crivellari <marco.crivellari@...e.com>
To: Steven Rostedt <rostedt@...dmis.org>
Cc: linux-kernel@...r.kernel.org, linux-trace-kernel@...r.kernel.org,
Tejun Heo <tj@...nel.org>, Lai Jiangshan <jiangshanlai@...il.com>,
Frederic Weisbecker <frederic@...nel.org>, Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Michal Hocko <mhocko@...e.com>, Masami Hiramatsu <mhiramat@...nel.org>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Subject: Re: [PATCH] tracing: Replace use of system_wq with system_percpu_wq
Hi Steven,
On Wed, Dec 24, 2025 at 9:43 PM Steven Rostedt <rostedt@...dmis.org> wrote:
> [...]
> > @@ -1375,7 +1375,7 @@ static void free_filter_list_tasks(struct rcu_head *rhp)
> > struct filter_head *filter_list = container_of(rhp, struct filter_head, rcu);
> >
> > INIT_RCU_WORK(&filter_list->rwork, free_filter_list_work);
> > - queue_rcu_work(system_wq, &filter_list->rwork);
> > + queue_rcu_work(system_percpu_wq, &filter_list->rwork);
>
> This is just garbage collection and has no need to be done on the CPU it
> was queued on. I guess this can use system_dfl_wq?
I will check and I will send a new version with the unbound wq.
Thanks!
--
Marco Crivellari
L3 Support Engineer
Powered by blists - more mailing lists