[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 08 Aug 2011 11:03:27 +0200
From: Peter Zijlstra <a.p.zijlstra@...llo.nl>
To: Lin Ming <ming.m.lin@...el.com>
Cc: Stephane Eranian <eranian@...gle.com>, Ingo Molnar <mingo@...e.hu>,
Andi Kleen <andi@...stfloor.org>,
Arnaldo Carvalho de Melo <acme@...stprotocols.net>,
linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v2 6/6] perf tool: Parse general/raw events from sysfs
On Mon, 2011-08-08 at 16:57 +0800, Lin Ming wrote:
> On Mon, 2011-08-08 at 16:48 +0800, Peter Zijlstra wrote:
> > On Mon, 2011-08-08 at 09:08 +0800, Lin Ming wrote:
> > >
> > > We only need to register one pmu with two same graphics cards.
> > > Then we can overload pid argument of sys_perf_event_open() to
> > > differentiate each instance of graphic card.
> > >
> > > Just like perf cgroup does.
> >
> > I don't like that much at all.. For one it will make it impossible to
> > put the pmu device in the right sysfs topology.
>
> So do you prefer adding a number to gpu name, as Stephane mentioned?
Not quite having read back that far (reading my email in date-reverse
manner this morning), yeah. That allows links from /sys/bus/pci/... back
to the pmu device.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists