[Gllug] performance of xen dom0 vs native linux

[Richard Jones]

On Sat, May 09, 2009 at 10:31:33PM +0100, James Courtier-Dutton wrote:
> 2009/5/9 Richard Jones <rich at annexia.org>:
> > On Sat, May 09, 2009 at 11:50:28AM +0100, James Courtier-Dutton wrote:
> >> Some of them use more so called "hardware acceleration" such as Intel
> >> VT or AMD-V.
> >> It has been shown that using hardware acceleration can actually slow
> >> some applications down when compared with software emulation,
> >> particularly with the intel vt and amd-v hardware instructions.
> >> Example applications are ones that use a lot of malloc/free calls.
> >> intel-vt and amd-v can slow these applications down quite a lot.
> >
> > James, extraordinary claims such as this one require extraordinary
> > proof, which I'm sure you'll be happy to provide.  I'm interested to
> > know how exactly userspace library details like malloc/free are
> > supposed to influence guest kernel performance.
> >
> 
> It is not extraordinary. I could say "Go google the reason yourself"
> .... but I like to help if I can.

It is extraordinary. You are claiming that malloc/free calls in guest
userspace are affecting the ability of hardware to perform
virtualization.  If you knew anything about what you were talking
about you would know this claim makes no sense, unless you can back it
up, which ...

> This is not the article I read that made well supported claims
> supporting my statements above, but it seems to at least support my
> statement to some extent, in that hardware virtualisation instructions
> are not always better than doing it in software.
> http://developers.slashdot.org/article.pl?sid=06/08/12/2028223

... you haven't.  This paper says nothing on this subject.  It doesn't
even mention 'malloc'.  The paper also talks about the first-gen
hardware virtualization (circa 2006).  Look at the current generation
from Intel and AMD which has significantly tuned and enhanced hardware
virtualization.  The things they metion at the end of the paper about
"the potential of future hardware assistance" have all now *been
implemented*.

> The memeory management problems found in the x86 hardware can be
> mitigated by using software that does it better, e.g. The Java VM.

This doesn't even make sense.  It has nothing to do with
virtualization.

[Another random anecdote that has nothing to do with the subject snipped]

Rich.

-- 
Richard Jones
Red Hat
-- 
Gllug mailing list  -  Gllug at gllug.org.uk
http://lists.gllug.org.uk/mailman/listinfo/gllug