<br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;"><div class="im">
> If I understand that paper correctly, HVM+VT-d outperforms PV by quite a<br>
> lot (if you have VT-d support on your system).<br>
><br>
<br>
</div>Thanks for that link. Just to make my criticism of the initial claim more<br>
clear: I don't claim that HVM can never be faster than PV but that you need<br>
to understand when exactly this is the case. For example I'm not sure that<br>
x86_64 vs. x86 really enters into this but I can definitely see VT-d making<br>
an impact there.<br>
<br>
Regards,<br>
<font color="#888888"> Dennis<br>
</font><div><div></div><div class="h5"><br>
<br></div></div></blockquote><div><br>Even though this is Intel talking I'd still be very sceptical of getting those numbers since this is quite the opposite of what I've seen. <br>Maybe the vt-d is getting good enough to actually accelerate IO operations but even so that would only happen on the latest hardware.<br>
<br>I will say that Xen has a really long packet path though.<br><br>Grant McWilliams<br></div></div>