[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200213173602.GQ14897@hirez.programming.kicks-ass.net>
Date: Thu, 13 Feb 2020 18:36:02 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Vincent Guittot <vincent.guittot@...aro.org>
Cc: mingo@...hat.com, juri.lelli@...hat.com, dietmar.eggemann@....com,
rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
linux-kernel@...r.kernel.org, pauld@...hat.com,
parth@...ux.ibm.com, valentin.schneider@....com
Subject: Re: [RFC 3/4] sched/fair: replace runnable load average by runnable
average
On Tue, Feb 11, 2020 at 06:46:50PM +0100, Vincent Guittot wrote:
> @@ -367,6 +367,14 @@ struct util_est {
> * For cfs_rq, it is the aggregated load_avg of all runnable and
> * blocked sched_entities.
> *
> + * [runnable_avg definition]
> + *
> + * runnable_avg = runnable%
* SCHED_CAPACITY_SCALE
right, just like we have for util_avg.
> + *
> + * where runnable% is the time ratio that a sched_entity is runnable.
> + * For cfs_rq, it is the aggregated runnable_avg of all runnable and
> + * blocked sched_entities.
Which is a verbatim repeat of the runnable% definition for load_avg,
right? Perhaps re-arrange the text such that we only have a single
definition for each symbol?
> + *
> * [util_avg definition]
> *
> * util_avg = running% * SCHED_CAPACITY_SCALE
Can you please split this patch in two? First remove everything
runnable_load_avg, and then introduce runnable_avg.
I didn't quickly spot anything off, and you're right that runnable vs
util is an interesting signal.
Powered by blists - more mailing lists