Date: Thu, 10 Nov 2016 12:04:23 +0000
From: Mark Rutland <mark.rutland@arm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: kan.liang@intel.com, mingo@redhat.com, linux-kernel@vger.kernel.org,
        acme@kernel.org, tglx@linutronix.de,
        alexander.shishkin@linux.intel.com, vince@deater.net,
        eranian@google.com, andi@firstfloor.org
Subject: Re: [PATCH] perf/core: introduce context per CPU event list
Message-ID: <20161110120423.GC4418@leverpostej>
References: <1478718286-12824-1-git-send-email-kan.liang@intel.com>
 <20161110083355.GO3568@worktop.programming.kicks-ass.net>
 <20161110110516.GA4418@leverpostej>
 <20161110113704.GU3142@twins.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20161110113704.GU3142@twins.programming.kicks-ass.net>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2104
Lines: 45

On Thu, Nov 10, 2016 at 12:37:05PM +0100, Peter Zijlstra wrote:
> On Thu, Nov 10, 2016 at 11:05:17AM +0000, Mark Rutland wrote:
> > On Thu, Nov 10, 2016 at 09:33:55AM +0100, Peter Zijlstra wrote:
> > > Yes this is a problem, but no this cannot be done. We can't have per-cpu
> > > storage per task. That rapidly explodes.
> > > 
> > > Mark is looking at replacing this stuff with an rb-tree for big-little,
> > > that would also allow improving this I think.
> > 
> > Unfortunately I've not had the chance to look at that since returning
> > from Plumbers. Also, I was leaning towards the alternative approach we
> > discussed, with a perf_event_task_contexts container, as that also
> > solved some other issues with the way we used perf_event_context::pmu in
> > big.LITTLE systems.
> > 
> > Looking at the way perf_iterate_ctx is used, it seems that we're just
> > trying to iterate over the active events for a context (i.e. those
> > programmed into the HW at this point in time). Though I'm missing some
> > subtlety, since we check event->state < PERF_EVENT_STATE_INACTIVE.
> > 
> > We have a similar issue with perf_event_task_tick() needing to know the
> > relevant contexts, and for that we have the active_ctx_list. Can't we do
> > something similar and add an active_events_list to perf_event_context?
> 
> So the problem is finding which events are active when.

Sure.

If we only care about PERF_EVENT_STATE_ACTIVE, then I think we can
fairly easily maintain a perf_event_context::active_event_list at
event_sched_{in,out}() time (or somewhere close to that).

If we need PERF_EVENT_STATE_INACTIVE events, then that doesn't work,
since we can give up early and not schedule some eligible events.

> If we stick all events in an RB-tree sorted on: {pmu,cpu,runtime} we
> can, fairly easily, find the relevant subtree and limit the iteration.
> Esp. if we use a threaded tree.

That would cater for big.LITTLE, certainly, but I'm not sure I follow
how that helps to find active events -- you'll still have to iterate
through the whole PMU subtree to find which are active, no?

Thanks,
Mark.