kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andre Przywara <andre.przywara@amd.com>
To: Sterling Windmill <sterling@ampx.net>
Cc: kvm@vger.kernel.org
Subject: Re: Live migration between Intel Q6600 and AMD Phenom II
Date: Wed, 9 Sep 2009 15:18:55 +0200	[thread overview]
Message-ID: <4AA7AB3F.8070408@amd.com> (raw)
In-Reply-To: <1654389503.81252431159512.JavaMail.root@mail.ampx.net>

Sterling Windmill wrote:
> I've read that it's possible to live migrate KVM guests between Intel
 >  and AMD CPUs, is it also possible to migrate from a CPU without
 > NPT/EPT to the Phenom II that supports NPT?
Yes.
 > Will I lose out on
 > any of the benefits NPT allows without shutting down and restarting
 > the guest?
NPT/EPT is a hypervisor feature, so the guest is unaffected (left alone 
the performance benefit). The guest does it's own paging (the same as on 
native), so the actual hypervisor page handling is not visible to the 
guest. You will immediately benefit from NPT if you migrate from a 
non-EPT/NPT capable host.

Cross-vendor migration experience differs from guest to guest, the most 
important point to look at are the CPUID bits. Start with a conservative 
setting (like -cpu kvm64 if you have a recent qemu-kvm) and if in need 
turn on features that you need (which must be on both hosts).
Also use recent KVM kernel modules, some CVM related bugs have been 
fixed lately.
We have tried migrating several guests without issues between non-NPT 
and NPT hosts.
If you experience problem, feel free to mail me with a description.

> Also, any thoughts on how much more performant a 3.0GHz Phenom II will be for running KVM guests than the 2.4GHz Intel Q6600?
NPT is faster than shadow paging  on almost all workloads (since it 
avoids most of the #VMEXITs), but since the virtualization 
implementation differs in many details between Intel and AMD, 
performance estimation just based on this single feature is not very 
legitimate.

Regards,
Andre.

-- 
Andre Przywara
AMD-Operating System Research Center (OSRC), Dresden, Germany
Tel: +49 351 448 3567 12
----to satisfy European Law for business letters:
Advanced Micro Devices GmbH
Karl-Hammerschmidt-Str. 34, 85609 Dornach b. Muenchen
Geschaeftsfuehrer: Andrew Bowd; Thomas M. McCoy; Giuliano Meroni
Sitz: Dornach, Gemeinde Aschheim, Landkreis Muenchen
Registergericht Muenchen, HRB Nr. 43632


      parent reply	other threads:[~2009-09-09 13:19 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-09-08 17:32 Live migration between Intel Q6600 and AMD Phenom II Sterling Windmill
2009-09-09  5:54 ` Amit Shah
2009-09-09 13:18 ` Andre Przywara [this message]

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=4AA7AB3F.8070408@amd.com \
    --to=andre.przywara@amd.com \
    --cc=kvm@vger.kernel.org \
    --cc=sterling@ampx.net \
    /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;
as well as URLs for NNTP newsgroup(s).