linux-kernel - Re: [PATCH v3] sched/freq: move call to cpufreq_update

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 14 Nov 2019 17:23:32 +0100
From:   Dietmar Eggemann <dietmar.eggemann@....com>
To:     Vincent Guittot <vincent.guittot@...aro.org>,
        linux-kernel@...r.kernel.org, mingo@...hat.com,
        peterz@...radead.org, juri.lelli@...hat.com, rostedt@...dmis.org,
        mgorman@...e.de, dsmythies@...us.net
Cc:     linux-pm@...r.kernel.org, torvalds@...ux-foundation.org,
        tglx@...utronix.de, sargun@...gun.me, tj@...nel.org,
        xiexiuqi@...wei.com, xiezhipeng1@...wei.com,
        srinivas.pandruvada@...ux.intel.com
Subject: Re: [PATCH v3] sched/freq: move call to cpufreq_update_util

On 13.11.19 21:21, Vincent Guittot wrote:
> update_cfs_rq_load_avg() calls cfs_rq_util_change() everytime pelt decays,
> which might be inefficient when cpufreq driver has rate limitation.
> 
> When a task is attached on a CPU, we have call path:
> 
> update_load_avg()
>   update_cfs_rq_load_avg()
>     cfs_rq_util_change -- > trig frequency update
>   attach_entity_load_avg()
>     cfs_rq_util_change -- > trig frequency update
> 
> The 1st frequency update will not take into account the utilization of the
> newly attached task and the 2nd one might be discard because of rate
> limitation of the cpufreq driver.
> 
> update_cfs_rq_load_avg() is only called by update_blocked_averages()
> and update_load_avg() so we can move the call to
> cfs_rq_util_change/cpufreq_update_util() into these 2 functions. It's also
> interesting to notice that update_load_avg() already calls directly
> cfs_rq_util_change() for !SMP case.
> 
> This changes will also ensure that cpufreq_update_util() is called even
> when there is no more CFS rq in the leaf_cfs_rq_list to update but only
> irq, rt or dl pelt signals.
> 
> Reported-by: Doug Smythies <dsmythies@...us.net>
> Fixes: 039ae8bcf7a5 ("sched/fair: Fix O(nr_cgroups) in the load balancing path")
> Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>

Reviewed-by: Dietmar Eggemann <dietmar.eggemann@....com>

> ---
> 
> changes for v3:
> - fix typo
> - test the decay of root cfs_rq even for !CONFIG_FAIR_GROUP_SCHED case

nit: s/!CONFIG_FAIR_GROUP_SCHED/CONFIG_FAIR_GROUP_SCHED

[...]

> @@ -7543,6 +7544,7 @@ static void update_blocked_averages(int cpu)
>  	const struct sched_class *curr_class;
>  	struct rq_flags rf;
>  	bool done = true;
> +	int decayed;
>  
>  	rq_lock_irqsave(rq, &rf);
>  	update_rq_clock(rq);
> @@ -7552,9 +7554,9 @@ static void update_blocked_averages(int cpu)
>  	 * that RT, DL and IRQ signals have been updated before updating CFS.
>  	 */

tip/sched/urgent's b90f7c9d2198 ("sched/pelt: Fix update of blocked PELT
ordering") adds this comment to both update_blocked_averages()
implementations. It mentions explicitly that update_cfs_rq_load_avg()
can call cpufreq_update_util(). Something this patch changes. Might be
good to update the comments with this patch as well.

[...]