Received-SPF: pass (google.com: domain of linux-kernel+bounces-76077-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
To: Frederic Weisbecker <frederic@kernel.org>
Cc: linux-kernel@vger.kernel.org, Peter Zijlstra <peterz@infradead.org>,
 John Stultz <jstultz@google.com>, Thomas Gleixner <tglx@linutronix.de>,
 Eric Dumazet <edumazet@google.com>, "Rafael J . Wysocki"
 <rafael.j.wysocki@intel.com>, Arjan van de Ven <arjan@infradead.org>,
 "Paul E . McKenney" <paulmck@kernel.org>, Rik van Riel <riel@surriel.com>,
 Steven Rostedt <rostedt@goodmis.org>, Sebastian Siewior
 <bigeasy@linutronix.de>, Giovanni Gherdovich <ggherdovich@suse.cz>, Lukasz
 Luba <lukasz.luba@arm.com>, "Gautham R . Shenoy" <gautham.shenoy@amd.com>,
 Srinivas Pandruvada <srinivas.pandruvada@intel.com>, K Prateek Nayak
 <kprateek.nayak@amd.com>, Christian Loehle <christian.loehle@arm.com>
Subject: Re: [PATCH v11 18/20] timers: Implement the hierarchical pull model
In-Reply-To: <ZdZ87whmpul8xIBI@pavilion.home>
References: <20240221090548.36600-1-anna-maria@linutronix.de>
 <20240221090548.36600-19-anna-maria@linutronix.de>
 <ZdZ87whmpul8xIBI@pavilion.home>
Date: Thu, 22 Feb 2024 09:17:29 +0100
Message-ID: <87jzmwnc9y.fsf@somnus>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable

Frederic Weisbecker <frederic@kernel.org> writes:

> Le Wed, Feb 21, 2024 at 10:05:46AM +0100, Anna-Maria Behnsen a =C3=A9crit=
 :
>> Placing timers at enqueue time on a target CPU based on dubious heuristi=
cs
>> does not make any sense:
>>=20
>>  1) Most timer wheel timers are canceled or rearmed before they expire.
>>=20
>>  2) The heuristics to predict which CPU will be busy when the timer expi=
res
>>     are wrong by definition.
>>=20
>> So placing the timers at enqueue wastes precious cycles.
>>=20
>> The proper solution to this problem is to always queue the timers on the
>> local CPU and allow the non pinned timers to be pulled onto a busy CPU at
>> expiry time.
>>=20
>> Therefore split the timer storage into local pinned and global timers:
>> Local pinned timers are always expired on the CPU on which they have been
>> queued. Global timers can be expired on any CPU.
>>=20
>> As long as a CPU is busy it expires both local and global timers. When a
>> CPU goes idle it arms for the first expiring local timer. If the first
>> expiring pinned (local) timer is before the first expiring movable timer,
>> then no action is required because the CPU will wake up before the first
>> movable timer expires. If the first expiring movable timer is before the
>> first expiring pinned (local) timer, then this timer is queued into an i=
dle
>> timerqueue and eventually expired by another active CPU.
>>=20
>> To avoid global locking the timerqueues are implemented as a hierarchy. =
The
>> lowest level of the hierarchy holds the CPUs. The CPUs are associated to
>> groups of 8, which are separated per node. If more than one CPU group
>> exist, then a second level in the hierarchy collects the groups. Dependi=
ng
>> on the size of the system more than 2 levels are required. Each group ha=
s a
>> "migrator" which checks the timerqueue during the tick for remote expira=
ble
>> timers.
>>=20
>> If the last CPU in a group goes idle it reports the first expiring event=
 in
>> the group up to the next group(s) in the hierarchy. If the last CPU goes
>> idle it arms its timer for the first system wide expiring timer to ensure
>> that no timer event is missed.
>>=20
>> Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
>
> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
>
> Though I must confess I only had a shallow look at group creation (init_g=
roup,
> get_group, connect_child_parent, setup_groups, add_cpu, and tmigr_init). =
But for
> the rest, I'm running out of bad scenarios. Time for the rest of the worl=
d to
> find them!
>
> Thanks for the hard work!

Thank you for your support!

Did you saw the v11a for this patch? It is only a cleanup - it removes
an unused variable. Just asking, because Review was for plain v11 patch.

Thanks,
	Anna-Maria