[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Yzwb8vgYhAvDJzK+@pc636>
Date: Tue, 4 Oct 2022 13:41:38 +0200
From: Uladzislau Rezki <urezki@...il.com>
To: paulmck@...nel.org,
"Joel Fernandes (Google)" <joel@...lfernandes.org>
Cc: rcu@...r.kernel.org, linux-kernel@...r.kernel.org,
rushikesh.s.kadam@...el.com, urezki@...il.com,
neeraj.iitr10@...il.com, frederic@...nel.org, paulmck@...nel.org,
rostedt@...dmis.org, youssefesmat@...gle.com, surenb@...gle.com
Subject: Re: [PATCH v7 02/11] rcu: Make call_rcu() lazy to save power
> trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check"));
> rcu_nocb_lock_irqsave(rdp, flags);
> lockdep_assert_held(&rdp->nocb_lock);
> bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
> - if (bypass_ncbs &&
> + lazy_ncbs = READ_ONCE(rdp->lazy_len);
> +
> + if (bypass_ncbs && (lazy_ncbs == bypass_ncbs) &&
> + (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush) ||
> + bypass_ncbs > 2 * qhimark)) {
Do you know why we want double "qhimark" threshold? It is not only this
place, there are several. I am asking because it is not expected by the
user.
--
Uladzsislau Rezki
Powered by blists - more mailing lists