<snip> > I don't need a core sample of the moon to know that it isn't made of green > cheese. Doesn't matter what the videos showed. There are lots of videos > that "prove" and impossible claim. If you want to believe that, it's > completely up to you. > > VMs have longer code paths than native. That alone would cause a perf hit. > Then there is the noisy neighbor problem and the fact that dom0 has to cycle > steal. Anyone with a lick of common sense would see the impossibility of > such a claim.
You are correct their are some wacky videos out on the Internet. I wouldn't trust these videos if they didn't come from reliable sources, Level1techs are legit. I will assume by longer code paths you are referring to the execution times. This is true however the path is roughly only a 5% longer to execute time penalty yielding 95% of the bare metal performance. Red Hat provides most of the speed boost with their virtio drivers. You can learn more here, https://docs.fedoraproject.org/en-US/quick-docs/creating-windows-virtual-machines-using-virtio-drivers/index.html When we believe strongly about something we tend to have tunnel vision and can't see outside the box. I can only present that it works, I can not open your mind up to see outside the box nor do I want too. I respect your opinion and will hope you can do the same. Anyway, this will be my last response unless I have something new to share. I freely give you the last word if you need it. I hope you and family and everyone on this group have a very Happy New Year! Peace! -- You received this message because you are subscribed to the Google Groups "qubes-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to qubes-users+unsubscr...@googlegroups.com. To post to this group, send email to qubes-users@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/qubes-users/424bdaba-7989-4251-a881-39c555bfc8e1%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
