[<prev] [next>] [day] [month] [year] [list]
Message-ID: <alpine.DEB.2.11.1412030907250.21872@vincent-weaver-1.umelst.maine.edu>
Date: Wed, 3 Dec 2014 09:17:46 -0500 (EST)
From: Vince Weaver <vincent.weaver@...ne.edu>
To: "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
cc: Peter Zijlstra <peterz@...radead.org>,
Paul Mackerras <paulus@...ba.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
gleb@...hat.com, joerg.roedel@....com
Subject: perf: exclude_hv vs exclude_host in perf_event_attr
So what *is* the difference in perf_event_attr between
.exclude_hv
and
.exclude_guest
.exclude_host
>From what I gather .exclude_hv excluces hypervisor counts if the hardware
supports that type of measurement, but only Power implements this.
.exclude_guest and .exclude_host are x86 only? AMD does them in hardware
but it's implemented in software on Intel?
Do they only work when KVM is running, or do they tell you meaningful
stuff otherwise? What happens if I set them and KVM isn't running?
Also PEBS only will work if .exclude_guest is specified?
As always the code could use some commenting and the relevant commit
messages aren't really that stellar either.
Vince Weaver
vincent.weaver@...ne.edu
--
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