[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20090529085309.GP1065@one.firstfloor.org>
Date: Fri, 29 May 2009 10:53:09 +0200
From: Andi Kleen <andi@...stfloor.org>
To: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: Andi Kleen <andi@...stfloor.org>, eranian@...il.com,
LKML <linux-kernel@...r.kernel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...e.hu>,
Robert Richter <robert.richter@....com>,
Paul Mackerras <paulus@...ba.org>,
Maynard Johnson <mpjohn@...ibm.com>,
Carl Love <cel@...ibm.com>,
Corey J Ashford <cjashfor@...ibm.com>,
Philip Mucci <mucci@...s.utk.edu>,
Dan Terpstra <terpstra@...s.utk.edu>,
perfmon2-devel <perfmon2-devel@...ts.sourceforge.net>
Subject: Re: comments on Performance Counters for Linux (PCL)
> You're talking about VT stuff, right?
Yes.
> Does that virtualize the PMU too?
A hypervisor can in software, but another common case is a global profiler on
the host to be able to profile all guests too. e.g. xenoprofile is able to do
that.
If you want a full system picture with virtualization that's pretty much
required.
For that you need a concept of more priviledge levels (host user, host sys,
guest user, guest sys)
> Happen to have more details? If they really run in user context their
> priv level would be the same right, otherwise they run in something
> weird, not quite user not quite kernel. Now that might be the case, but
> I'm utterly ignorant on itanic.
See Documentation/ia64/fsys.txt
-Andi
--
ak@...ux.intel.com -- Speaking for myself only.
--
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