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:   Thu, 3 Nov 2022 13:44:12 +0100
From:   Peter Zijlstra <peterz@infradead.org>
To:     Chen Yu <yu.c.chen@intel.com>
Cc:     Vincent Guittot <vincent.guittot@linaro.org>,
        Tim Chen <tim.c.chen@intel.com>,
        Mel Gorman <mgorman@techsingularity.net>,
        Juri Lelli <juri.lelli@redhat.com>,
        Rik van Riel <riel@surriel.com>,
        Aaron Lu <aaron.lu@intel.com>,
        Abel Wu <wuyun.abel@bytedance.com>,
        K Prateek Nayak <kprateek.nayak@amd.com>,
        Yicong Yang <yangyicong@hisilicon.com>,
        "Gautham R . Shenoy" <gautham.shenoy@amd.com>,
        Ingo Molnar <mingo@redhat.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Valentin Schneider <vschneid@redhat.com>,
        Hillf Danton <hdanton@sina.com>,
        Honglei Wang <wanghonglei@didichuxing.com>,
        Len Brown <len.brown@intel.com>,
        Chen Yu <yu.chen.surf@gmail.com>, linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH v2 1/2] sched/fair: Introduce short duration task
 check
Message-ID: <Y2O3nDrvcy+KuGg1@hirez.programming.kicks-ass.net>
References: <cover.1666531576.git.yu.c.chen@intel.com>
 <6b81eea9a8cafb7634f36586f1744b8d4ac49da5.1666531576.git.yu.c.chen@intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <6b81eea9a8cafb7634f36586f1744b8d4ac49da5.1666531576.git.yu.c.chen@intel.com>
Precedence: bulk

On Sun, Oct 23, 2022 at 11:32:31PM +0800, Chen Yu wrote:

> +	if (sched_feat(SIS_SHORT) && !prev->on_rq) {
> +		/*
> +		 * sum_exec_runtime has been updated in update_curr()
> +		 * because we reach here via dequeue.
> +		 */
> +		this_dur_avg = se->sum_exec_runtime - se->prev_sum_runtime_vol;
> +		/*
> +		 * Record the accumulated runtime when task voluntarily
> +		 * switches out. End of old duration period, a new period
> +		 * starts.
> +		 */
> +		se->prev_sum_runtime_vol = se->sum_exec_runtime;
> +
> +		last_dur_avg = se->dur_avg;
> +		delta = this_dur_avg - last_dur_avg;
> +		/* consider large change to avoid frequent update */
> +		if (abs(delta) >= sysctl_sched_min_granularity) {
> +			/*
> +			 * If it is the first time the task starts to
> +			 * record dur_avg, discard the initial value 0.
> +			 * Otherwise, calculate the EWMA.
> +			 */
> +			if (unlikely(!this_dur_avg))
> +				se->dur_avg = this_dur_avg;
> +			else
> +				update_avg(&se->dur_avg, this_dur_avg);
> +		}
> +	}

This seems excessively convoluted; what's wrong with something like:

	if (sched_feat(SIS_SHORT) && !prev->on_rq) {
		u64 this_dur = se->sum_exec_runtime - se->prev_sum_exec_runtime_vol;
		se->prev_sum_exec_runtime_vol = se->sum_exec_runtime;

		update_avg(&se->dur_avg, this_dur);
	}

All that other stuff just makes it unreadable and probably slower.