Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 27 Jun 2023 12:14:37 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Aaron Lu <aaron.lu@intel.com>
Cc:     Deng Pan <pan.deng@intel.com>, tim.c.chen@intel.com,
        vincent.guittot@linaro.org, linux-kernel@vger.kernel.org,
        tianyou.li@intel.com, yu.ma@intel.com, lipeng.zhu@intel.com,
        yu.c.chen@intel.com, Tim Chen <tim.c.chen@linux.intel.com>
Subject: Re: [PATCH v2] sched/task_group: Re-layout structure to reduce false
 sharing
Message-ID: <20230627101437.GY4253@hirez.programming.kicks-ass.net>
References: <20230621081425.420607-1-pan.deng@intel.com>
 <20230626054756.GA435374@ziqianlu-dell>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20230626054756.GA435374@ziqianlu-dell>
Precedence: bulk

On Mon, Jun 26, 2023 at 01:47:56PM +0800, Aaron Lu wrote:

> > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> > index ec7b3e0a2b20..4fbd4b3a4bdd 100644
> > --- a/kernel/sched/sched.h
> > +++ b/kernel/sched/sched.h
> > @@ -389,6 +389,19 @@ struct task_group {
> >  #endif
> >  #endif
> >  
> > +	struct rcu_head		rcu;
> > +	struct list_head	list;
> > +
> > +	struct list_head	siblings;
> > +	struct list_head	children;
> > +
> > +	/*
> > +	 * To reduce false sharing, current layout is optimized to make
> > +	 * sure load_avg is in a different cacheline from parent, rt_se
> > +	 * and rt_rq.
> > +	 */

That comment is misleading I think; you don't particularly care about
those fields more than any other active fields that would cause false
sharing.

> > +	struct task_group	*parent;
> > +
> 
> I wonder if we can simply do:
> 
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index ec7b3e0a2b20..31b73e8d9568 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -385,7 +385,9 @@ struct task_group {
>  	 * it in its own cacheline separated from the fields above which
>  	 * will also be accessed at each tick.
>  	 */
> -	atomic_long_t		load_avg ____cacheline_aligned;
> +	struct {
> +		atomic_long_t		load_avg;
> +	} ____cacheline_aligned_in_smp;
>  #endif
>  #endif
> 
> This way it can make sure there is no false sharing with load_avg no
> matter how the layout of this structure changes in the future.

This. Also, ISTR there was a series to split this atomic across nodes;
whatever happend to that, and can we still measure an improvement over
this with that approach?