linux-kernel - Re: [PATCH] sched/fair: Disable LB

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: Windows password security audit tool. GUI, reports in PDF.

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

Date:   Mon, 10 Sep 2018 16:12:05 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Dietmar Eggemann <dietmar.eggemann@....com>
Cc:     Ingo Molnar <mingo@...hat.com>,
        Fengguang Wu <fengguang.wu@...el.com>,
        Li Zhijian <zhijianx.li@...el.com>,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH] sched/fair: Disable LB_BIAS by default

On Thu, Aug 09, 2018 at 02:57:53PM +0100, Dietmar Eggemann wrote:
> LB_BIAS allows the adjustment on how conservative load should be
> balanced.

> It is very likely that LB_BIAS' influence on load balancing can be
> neglected (see test results below). This is further supported by:
> 
> (1) Weighted CPU load today is by itself a decayed average value (PELT)
>     (cfs_rq->avg->runnable_load_avg) and not the instantaneous load
>     (rq->load.weight) it was when LB_BIAS was introduced.
> 
> (2) Sd imbalance_pct is used for CPU_NEWLY_IDLE and CPU_NOT_IDLE (relate
>     to sd's newidle and busy idx) in find_busiest_group() when comparing
>     busiest and local avg load to make load balancing even more
>     conservative.
> 
> (3) The sd forkexec and newidle idx are always set to 0 so there is no
>     adjustment on how conservatively load balancing is done here.
> 
> (4) Affine wakeup based on weight (wake_affine_weight()) will not be
>     impacted since the sd wake idx is always set to 0.
> 
> Let's disable LB_BIAS by default for a few kernel releases to make sure
> that no workload and no scheduler topology is affected. The benefit of
> being able to remove the LB_BIAS dependency from source_load() and
> target_load() is that the entire rq->cpu_load[idx] code could be removed
> in this case.

Certainly worth a try; as I've written somewhere in a comment; it would
be very nice to get rid of that load tracking crud.

And it is trivial to revert if something does show up.

Ingo, what do you think?

> Signed-off-by: Dietmar Eggemann <dietmar.eggemann@....com>
> ---
>  kernel/sched/features.h | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/kernel/sched/features.h b/kernel/sched/features.h
> index 85ae8488039c..858589b83377 100644
> --- a/kernel/sched/features.h
> +++ b/kernel/sched/features.h
> @@ -39,7 +39,7 @@ SCHED_FEAT(WAKEUP_PREEMPTION, true)
>  
>  SCHED_FEAT(HRTICK, false)
>  SCHED_FEAT(DOUBLE_TICK, false)
> -SCHED_FEAT(LB_BIAS, true)
> +SCHED_FEAT(LB_BIAS, false)
>  
>  /*
>   * Decrement CPU capacity based on time not spent running tasks
> -- 
> 2.11.0
>