Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Wed, 18 Apr 2018 17:19:28 +0800
From:   Leo Yan <leo.yan@linaro.org>
To:     Quentin Perret <quentin.perret@arm.com>
Cc:     Dietmar Eggemann <dietmar.eggemann@arm.com>,
        linux-kernel@vger.kernel.org,
        Peter Zijlstra <peterz@infradead.org>,
        Thara Gopinath <thara.gopinath@linaro.org>,
        linux-pm@vger.kernel.org,
        Morten Rasmussen <morten.rasmussen@arm.com>,
        Chris Redpath <chris.redpath@arm.com>,
        Patrick Bellasi <patrick.bellasi@arm.com>,
        Valentin Schneider <valentin.schneider@arm.com>,
        "Rafael J . Wysocki" <rjw@rjwysocki.net>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Viresh Kumar <viresh.kumar@linaro.org>,
        Todd Kjos <tkjos@google.com>,
        Joel Fernandes <joelaf@google.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        Steve Muckle <smuckle@google.com>,
        Eduardo Valentin <edubezval@gmail.com>
Subject: Re: [RFC PATCH v2 4/6] sched/fair: Introduce an energy estimation
 helper function
Message-ID: <20180418091928.GA15682@leoy-ThinkPad-X240s>
References: <20180406153607.17815-1-dietmar.eggemann@arm.com>
 <20180406153607.17815-5-dietmar.eggemann@arm.com>
 <20180417152213.GC18509@leoy-ThinkPad-X240s>
 <20180418081339.GB3943@e108498-lin.cambridge.arm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20180418081339.GB3943@e108498-lin.cambridge.arm.com>
User-Agent: Mutt/1.5.24 (2015-08-30)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, Apr 18, 2018 at 09:13:39AM +0100, Quentin Perret wrote:
> On Tuesday 17 Apr 2018 at 23:22:13 (+0800), Leo Yan wrote:
> > On Fri, Apr 06, 2018 at 04:36:05PM +0100, Dietmar Eggemann wrote:
> > > From: Quentin Perret <quentin.perret@arm.com>
> > > 
> > > In preparation for the definition of an energy-aware wakeup path, a
> > > helper function is provided to estimate the consequence on system energy
> > > when a specific task wakes-up on a specific CPU. compute_energy()
> > > estimates the OPPs to be reached by all frequency domains and estimates
> > > the consumption of each online CPU according to its energy model and its
> > > percentage of busy time.
> > > 
> > > Cc: Ingo Molnar <mingo@redhat.com>
> > > Cc: Peter Zijlstra <peterz@infradead.org>
> > > Signed-off-by: Quentin Perret <quentin.perret@arm.com>
> > > Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
> > > ---
> > >  include/linux/sched/energy.h | 20 +++++++++++++
> > >  kernel/sched/fair.c          | 68 ++++++++++++++++++++++++++++++++++++++++++++
> > >  kernel/sched/sched.h         |  2 +-
> > >  3 files changed, 89 insertions(+), 1 deletion(-)
> > > 
> > > diff --git a/include/linux/sched/energy.h b/include/linux/sched/energy.h
> > > index 941071eec013..b4110b145228 100644
> > > --- a/include/linux/sched/energy.h
> > > +++ b/include/linux/sched/energy.h
> > > @@ -27,6 +27,24 @@ static inline bool sched_energy_enabled(void)
> > >  	return static_branch_unlikely(&sched_energy_present);
> > >  }
> > >  
> > > +static inline
> > > +struct capacity_state *find_cap_state(int cpu, unsigned long util)
> > > +{
> > > +	struct sched_energy_model *em = *per_cpu_ptr(energy_model, cpu);
> > > +	struct capacity_state *cs = NULL;
> > > +	int i;
> > > +
> > > +	util += util >> 2;
> > > +
> > > +	for (i = 0; i < em->nr_cap_states; i++) {
> > > +		cs = &em->cap_states[i];
> > > +		if (cs->cap >= util)
> > > +			break;
> > > +	}
> > > +
> > > +	return cs;
> > 
> > 'cs' is possible to return NULL.
> 
> Only if em-nr_cap_states==0, and that shouldn't be possible if
> sched_energy_present==True, so this code should be safe :-)

You are right. Thanks for explanation.

> > > +}
> > > +
> > >  static inline struct cpumask *freq_domain_span(struct freq_domain *fd)
> > >  {
> > >  	return &fd->span;
> > > @@ -42,6 +60,8 @@ struct freq_domain;
> > >  static inline bool sched_energy_enabled(void) { return false; }
> > >  static inline struct cpumask
> > >  *freq_domain_span(struct freq_domain *fd) { return NULL; }
> > > +static inline struct capacity_state
> > > +*find_cap_state(int cpu, unsigned long util) { return NULL; }
> > >  static inline void init_sched_energy(void) { }
> > >  #define for_each_freq_domain(fdom) for (; fdom; fdom = NULL)
> > >  #endif
> > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > > index 6960e5ef3c14..8cb9fb04fff2 100644
> > > --- a/kernel/sched/fair.c
> > > +++ b/kernel/sched/fair.c
> > > @@ -6633,6 +6633,74 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
> > >  }
> > >  
> > >  /*
> > > + * Returns the util of "cpu" if "p" wakes up on "dst_cpu".
> > > + */
> > > +static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
> > > +{
> > > +	unsigned long util, util_est;
> > > +	struct cfs_rq *cfs_rq;
> > > +
> > > +	/* Task is where it should be, or has no impact on cpu */
> > > +	if ((task_cpu(p) == dst_cpu) || (cpu != task_cpu(p) && cpu != dst_cpu))
> > > +		return cpu_util(cpu);
> > > +
> > > +	cfs_rq = &cpu_rq(cpu)->cfs;
> > > +	util = READ_ONCE(cfs_rq->avg.util_avg);
> > > +
> > > +	if (dst_cpu == cpu)
> > > +		util += task_util(p);
> > > +	else
> > > +		util = max_t(long, util - task_util(p), 0);
> > 
> > I tried to understand the logic at here, below code is more clear for
> > myself:
> > 
> >         int prev_cpu = task_cpu(p);
> > 
> >         cfs_rq = &cpu_rq(cpu)->cfs;
> >         util = READ_ONCE(cfs_rq->avg.util_avg);
> > 
> >         /* Bail out if src and dst CPUs are the same one */
> >         if (prev_cpu == cpu && dst_cpu == cpu)
> >                 return util;
> > 
> >         /* Remove task utilization for src CPU */
> >         if (cpu == prev_cpu)
> >                 util = max_t(long, util - task_util(p), 0);
> > 
> >         /* Add task utilization for dst CPU */
> >         if (dst_cpu == cpu)
> >                 util += task_util(p);
> > 
> > BTW, CPU utilization is decayed value and task_util() is not decayed
> > value, so 'util - task_util(p)' calculates a smaller value than the
> > prev CPU pure utilization, right?
> 
> task_util() is the raw PELT signal, without UTIL_EST, so I think it's
> fine to do `util - task_util()`.
> 
> > 
> > Another question is can we reuse the function cpu_util_wake() and
> > just compenstate task util for dst cpu?
> 
> Well it's not that simple. cpu_util_wake() will give you the max between
> the util_avg and the util_est value, so which task_util() should you add
> to it ? The util_avg or the uti_est value ?

If feature 'UTIL_EST' is enabled, then add task's util_est; otherwise
add task util_avg value.

I think cpu_util_wake() has similiar logic with here, it merely returns
CPU level util; but here needs to accumulate CPU level util + task level
util.  So seems to me, the logic is:

  cpu_util_wake() + task_util_wake()

> Here we are trying to predict what will be the cpu_util signal in the
> future, so the only always-correct implementation of this function has
> to predict what will be the CPU util_avg and util_est signals in
> parallel and take the max of the two.

I totally agree with this, just want to check if can reuse existed code,
so we can have more consistent logic accrossing scheduler.

> > > +	if (sched_feat(UTIL_EST)) {
> > > +		util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued);
> > > +		if (dst_cpu == cpu)
> > > +			util_est += _task_util_est(p);
> > > +		else
> > > +			util_est = max_t(long, util_est - _task_util_est(p), 0);
> > > +		util = max(util, util_est);
> > > +	}
> > > +
> > > +	return min_t(unsigned long, util, capacity_orig_of(cpu));
> > > +}
> > > +
> > > +/*
> > > + * Estimates the system level energy assuming that p wakes-up on dst_cpu.
> > > + *
> > > + * compute_energy() is safe to call only if an energy model is available for
> > > + * the platform, which is when sched_energy_enabled() is true.
> > > + */
> > > +static unsigned long compute_energy(struct task_struct *p, int dst_cpu)
> > > +{
> > > +	unsigned long util, max_util, sum_util;
> > > +	struct capacity_state *cs;
> > > +	unsigned long energy = 0;
> > > +	struct freq_domain *fd;
> > > +	int cpu;
> > > +
> > > +	for_each_freq_domain(fd) {
> > > +		max_util = sum_util = 0;
> > > +		for_each_cpu_and(cpu, freq_domain_span(fd), cpu_online_mask) {
> > > +			util = cpu_util_next(cpu, p, dst_cpu);
> > > +			util += cpu_util_dl(cpu_rq(cpu));
> > > +			max_util = max(util, max_util);
> > > +			sum_util += util;
> > > +		}
> > > +
> > > +		/*
> > > +		 * Here we assume that the capacity states of CPUs belonging to
> > > +		 * the same frequency domains are shared. Hence, we look at the
> > > +		 * capacity state of the first CPU and re-use it for all.
> > > +		 */
> > > +		cpu = cpumask_first(freq_domain_span(fd));
> > > +		cs = find_cap_state(cpu, max_util);
> > > +		energy += cs->power * sum_util / cs->cap;
> > > +	}
> > 
> > This means all CPUs will be iterated for calculation, the complexity is
> > O(n)...
> > 
> > > +	return energy;
> > > +}
> > > +
> > > +/*
> > >   * select_task_rq_fair: Select target runqueue for the waking task in domains
> > >   * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
> > >   * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
> > > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> > > index 5d552c0d7109..6eb38f41d5d9 100644
> > > --- a/kernel/sched/sched.h
> > > +++ b/kernel/sched/sched.h
> > > @@ -2156,7 +2156,7 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
> > >  # define arch_scale_freq_invariant()	false
> > >  #endif
> > >  
> > > -#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
> > > +#ifdef CONFIG_SMP
> > >  static inline unsigned long cpu_util_dl(struct rq *rq)
> > >  {
> > >  	return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
> > > -- 
> > > 2.11.0
> > >