Re: [RFC] sched: CPU topology try

From: Morten Rasmussen <morten.rasmussen@arm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Dietmar Eggemann <Dietmar.Eggemann@arm.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"mingo@kernel.org" <mingo@kernel.org>,
	"pjt@google.com" <pjt@google.com>,
	"cmetcalf@tilera.com" <cmetcalf@tilera.com>,
	"tony.luck@intel.com" <tony.luck@intel.com>,
	"alex.shi@linaro.org" <alex.shi@linaro.org>,
	"preeti@linux.vnet.ibm.com" <preeti@linux.vnet.ibm.com>,
	"linaro-kernel@lists.linaro.org" <linaro-kernel@lists.linaro.org>,
	"rjw@sisk.pl" <rjw@sisk.pl>,
	"paulmck@linux.vnet.ibm.com" <paulmck@linux.vnet.ibm.com>,
	"corbet@lwn.net" <corbet@lwn.net>,
	"tglx@linutronix.de" <tglx@linutronix.de>,
	"len.brown@intel.com" <len.brown@intel.com>,
	"arjan@linux.intel.com" <arjan@linux.intel.com>,
	"amit.kucheria@linaro.org" <amit.kucheria@linaro.org>,
	"james.hogan@imgtec.com" <james.hogan@imgtec.com>,
	"schwidefsky@de.ibm.com" <schwidefsky@de.ibm.com>,
	"heiko.carstens@de.ibm.com" <heiko.carstens@de.ibm.com>
Subject: Re: [RFC] sched: CPU topology try
Date: Mon, 6 Jan 2014 17:15:30 +0000	[thread overview]
Message-ID: <20140106171530.GC2936@e103034-lin> (raw)
In-Reply-To: <20140106162813.GM31570@twins.programming.kicks-ass.net>

On Mon, Jan 06, 2014 at 04:28:13PM +0000, Peter Zijlstra wrote:
> On Mon, Dec 23, 2013 at 06:22:17PM +0100, Dietmar Eggemann wrote:
> > I'm not sure if the idea to create a dedicated sched_domain level for every
> > topology flag representing a specific functionality will scale. From the
> > perspective of energy-aware scheduling we need e.g. energy costs (P and C
> > state) which can only be populated towards the scheduler via an additional
> > sub-struct and additional function arch_sd_energy() like depicted in
> > Morten's email:
> > 
> > [2] lkml.org/lkml/2013/11/14/102
> 
> That lkml.org link is actually not working for me (blank page -- maybe
> lkml.org is on the blink again).
> 
> That said, I yet have to sit down and think about the P state stuff, but
> I was thinking we need some rudimentary domain support for that.
> 
> For instance, the big-little thingies seem share their P state per
> cluster, so we need a domain at that level to hang some state off of --
> which we actually have in this case. But we need to ensure we do have
> it -- somehow.

Is there any examples of frequency domains not matching the span of a
sched_domain?

I would have thought that we would have a matching sched_domain to hang
the P and C state information from for most systems. If not, we could
just add it.

I don't think it is safe to assume that big-little always has cluster
P-states. It is implementation dependent. But the most obvious
alternative would be to have per-cpu P-states in which case we would
also have a matching sched_domain.