Re: Utility of PV on non-obsolete hardware

["Mathew, Cherry G." <cherry%zyx.in@localhost>]

On 4 April 2019 3:06:18 PM GMT+05:30, tg%gmplib.org@localhost wrote:
>I recently realised that GNU/Linux PV guests run poorly compared to PVH
>and HVM guests.  I only noticed that since my FreeBSD PVHVM guests
>greatly outperformed any other guests.
>
>Now I tested a HVM guest for NetBSD 8.0 (-STABLE) on 3 random machines.
>The following table indicates wall clock build times for configure+make
>of a package (the GMP bignum library):
>
>                  PV    HVM      HVM speedup
>AMD k10           282   207         36%
>Intel Goldmont    585   329         78%
>Intel Broadwell   225   188         20%
>
>The HVM guests here do not use any PV or Virtio drivers, so any I/O
>will
>pay a toll.  Still, the speedup with HVM is huge.
>
>Perhaps a caution about not using PV should be added to the NetBSD web?
>:-)
>
>Seriously, plain PV is perhaps only useful on machines without EPT/NPT.
>Our test systems with Intel Conroe (2006), Intel Penryn (2007), and AND
>K8 (2003) are the only ones which benefit from PV.

That's a good point - I'm surprised about the I/o performance though - were you using virtio ?

 I'm about 70% of the way enabling PVHVM for domU - we have PoC but needs a bit more debugging etc. Also looking at non PV Dom0 solutions.


Cherry
-- 
Sent from my phone. Please excuse my brevity.