Date: Mon, 6 May 2013 12:19:36 +0200
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Paul Turner <pjt@google.com>
Cc: Alex Shi <alex.shi@intel.com>, Ingo Molnar <mingo@redhat.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Andrew Morton <akpm@linux-foundation.org>,
        Borislav Petkov <bp@alien8.de>, Namhyung Kim <namhyung@kernel.org>,
        Mike Galbraith <efault@gmx.de>,
        Morten Rasmussen <morten.rasmussen@arm.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Preeti U Murthy <preeti@linux.vnet.ibm.com>,
        Viresh Kumar <viresh.kumar@linaro.org>,
        LKML <linux-kernel@vger.kernel.org>, Mel Gorman <mgorman@suse.de>,
        Rik van Riel <riel@redhat.com>,
        Michael Wang <wangyun@linux.vnet.ibm.com>
Subject: Re: [PATCH v5 5/7] sched: compute runnable load avg in cpu_load and
 cpu_avg_load_per_task
Message-ID: <20130506101936.GE13861@dyad.programming.kicks-ass.net>
References: <1367804711-30308-1-git-send-email-alex.shi@intel.com>
 <1367804711-30308-6-git-send-email-alex.shi@intel.com>
 <CAPM31RLJe19FH+RYipwm4kwtzmFHoS2xGTx4iZ9+qwDJZ_pf3A@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CAPM31RLJe19FH+RYipwm4kwtzmFHoS2xGTx4iZ9+qwDJZ_pf3A@mail.gmail.com>
User-Agent: Mutt/1.5.21 (2012-12-30)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2230
Lines: 52

On Mon, May 06, 2013 at 01:46:19AM -0700, Paul Turner wrote:
> On Sun, May 5, 2013 at 6:45 PM, Alex Shi <alex.shi@intel.com> wrote:
> > @@ -2536,7 +2536,7 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
> >  void update_idle_cpu_load(struct rq *this_rq)
> >  {
> >         unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
> > -       unsigned long load = this_rq->load.weight;
> > +       unsigned long load = (unsigned long)this_rq->cfs.runnable_load_avg;
> 
> We should be minimizing:
>   Variance[ for all i ]{ cfs_rq[i]->runnable_load_avg +
> cfs_rq[i]->blocked_load_avg }
> 
> blocked_load_avg is the expected "to wake" contribution from tasks
> already assigned to this rq.
> 
> e.g. this could be:
>   load = this_rq->cfs.runnable_load_avg + this_rq->cfs.blocked_load_avg;
> 
> Although, in general I have a major concern with the current implementation:
> 
> The entire reason for stability with the bottom up averages is that
> when load migrates between cpus we are able to migrate it between the
> tracked sums.
> 
> Stuffing observed averages of these into the load_idxs loses that
> mobility; we will have to stall (as we do today for idx > 0) before we
> can recognize that a cpu's load has truly left it; this is a very
> similar problem to the need to stably track this for group shares
> computation.

Ah indeed. I overlooked that.

> To that end, I would rather see the load_idx disappear completely:
>  (a) We can calculate the imbalance purely from delta (runnable_avg +
> blocked_avg)
>  (b) It eliminates a bad tunable.

So I suspect (haven't gone back in history to verify) that load_idx mostly
comes from the fact that our balance passes happen more and more slowly the
bigger the domains get.

In that respect it makes sense to equate load_idx to sched_domain::level;
higher domains balance slower and would thus want a longer-term average to base
decisions on.

So what we would want is means to get sane longer term averages.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/