public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
To: Balaji Rao <balajirrao-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Cc: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org,
	Markus Armbruster
	<armbru-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Subject: Re: Performance monitoring units and KVM
Date: Wed, 30 Jan 2008 20:14:39 +0200	[thread overview]
Message-ID: <47A0BE8F.4090508@qumranet.com> (raw)
In-Reply-To: <200801302353.19872.balajirrao-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>

Balaji Rao wrote:
> On Wednesday 30 January 2008 11:11:51 pm Avi Kivity wrote:
>   
>> Markus Armbruster wrote:
>>     
>>> System-wide profiling of the *virtual* machine is related to profiling
>>> just a process.  That's hard.  I guess building on Perfmon2 would make
>>> sense there, but as long as it's out of tree...  Can we wait for it?
>>> If not, what then?
>>>       
>> Give the guest access to the real PMU.  Save them on every exit
>> (switching profiling off), and restore them on every entry (switching
>> profiling on).  The only problem with this is that it is very cpu model
>> dependent, losing the hardware independence that virtual machines have.
>> If you are satisfied with the architectural performance counters, then
>> we even have hardware independence.
>>     
> But don't the architectural performance counters vary between Intel and AMD 
> cpus ? AFAIK, they do. And, this would pose problems during migration between 
> Intel and AMD hosts.
>
>   

The also vary between Intel hosts of different models, and likely 
different AMD hosts as well.  The PMU is not architectural (or, in other 
words, model specific).  So migration and PMU pass-through are mutually 
exclusive unless you have a homogeneous server farm.

> I am not sure how important is it to support migration between Intel and AMD 
> hosts. If it were not that important, then IMO we could go ahead with exposing 
> the real PMU. Maybe we could warn users against running profilers in the guest 
> if they intend it to to be Intel<->AMD migrateable ?
>   

We can give the user the option to expose only the architectural PMU 
(which is quite limited) and have cross-model migration, or to expose 
the full PMU and lose hardware independence.

-- 
error compiling committee.c: too many arguments to function


-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2008.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/

  parent reply	other threads:[~2008-01-30 18:14 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-01-30 17:06 Performance monitoring units and KVM Markus Armbruster
     [not found] ` <87wsprxmyb.fsf-A7mx1g9ivIOttUaS3K59qNi2O/JbrIOy@public.gmane.org>
2008-01-30 17:41   ` Avi Kivity
     [not found]     ` <47A0B6DF.40208-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2008-01-30 18:05       ` Andi Kleen
2008-01-30 18:23       ` Balaji Rao
     [not found]         ` <200801302353.19872.balajirrao-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2008-01-30 18:14           ` Avi Kivity [this message]
     [not found]             ` <47A0BE8F.4090508-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2008-01-30 18:26               ` Andi Kleen
     [not found]                 ` <p73ir1b5fvy.fsf-KvMlXPVkKihbpigZmTR7Iw@public.gmane.org>
2008-01-30 19:14                   ` Balaji Rao
     [not found]                     ` <200801310044.11055.balajirrao-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2008-01-31  3:12                       ` Andi Kleen
     [not found]                         ` <20080131031232.GB27115-qrUzlfsMFqo/4alezvVtWx2eb7JE58TQ@public.gmane.org>
2008-01-31  3:44                           ` Performance monitoring units and KVM II Andi Kleen
2008-01-31  7:12                           ` Performance monitoring units and KVM Balaji Rao
2008-01-30 18:55               ` Balaji Rao
2008-01-30 19:55       ` Markus Armbruster
     [not found]         ` <87fxwfw0jn.fsf-A7mx1g9ivIOttUaS3K59qNi2O/JbrIOy@public.gmane.org>
2008-01-31  7:03           ` Avi Kivity
     [not found]             ` <47A172D4.6040505-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2008-01-31 15:42               ` Markus Armbruster
     [not found]                 ` <87odb2gfx5.fsf-A7mx1g9ivIOttUaS3K59qNi2O/JbrIOy@public.gmane.org>
2008-01-31 16:37                   ` Avi Kivity

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=47A0BE8F.4090508@qumranet.com \
    --to=avi-atkuwr5tajbwk0htik3j/w@public.gmane.org \
    --cc=armbru-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=balajirrao-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
    --cc=kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox