If its of any help, I was doing some testing and make these notes some time ago:

https://docs.google.com/spreadsheets/d/1oQgEcaIU0wIfkUAtcnFohVzhNpj3GMZamjtmkqAjcKA/edit#gid=1794409316
 
<https://docs.google.com/spreadsheets/d/1oQgEcaIU0wIfkUAtcnFohVzhNpj3GMZamjtmkqAjcKA/edit#gid=1794409316>

Particularly the VirtIO tab. I came to the same conclusion that version 0.1-49 
was the best combination of latest driver/performance.

- Dave

> On 6 Oct. 2016, at 7:20 pm, Jorge Schrauwen <[email protected]> wrote:
> 
> On 2016-10-06 00:48, Ian Collins wrote:
>> On 10/ 6/16 10:03 AM, Matthew Parsons wrote:
>>> Have you installed the VirtIO drivers in windows? (And what version?) For 
>>> testing I'd try disabling/removing the guest NICs and just see if 
>>> interrupts die down.
>> Which version is often an issue!  There are so many out there and some
>> work with one version of windows and not another!  The ISO I use is
>> named "me-ws2012std-20130712.iso" and I've been using it for a couple
>> of years so its origins are lost in the mists of time.
> This which version works/is best used to come up a lot.
> A while ago most seem to be in agreement which was the best set. I managed to 
> find it and also host it on my package repository site to not have it go lost:
> 
> http://pkg.blackdot.be/extras/virtio-win-0.1-49.iso
> 
> Not sure this is the same version as you mention but I had decent results on 
> windows 7 and 2008 R2 (didn't have access to newer stuff)
> 
>>> Also (again for testing) perhaps reduce cores to the amount on a physical 
>>> CPU socket and assign/restrict to avoid crossing NUMA boundries.
>> The problem only becomes an issue when the core number gets high, as I
>> said in my original post the load average almost quadruples when going
>> from 16 to 32 cores.
>>> (I trust that whatever workload you're running benefits from that many 
>>> cores, but typically I'd keep 2 or so for the hypervisor/management/other.)
>> The workload is compiling a large C and C++ code base, so the more
>> cores the better.
>> Experimenting on a smaller machine shows the build times to cores
>> ratios reflect those on bare metal, that is if I give the VM the full
>> system picture (using qemu_extra_opts) build times are about 25%
>> faster than giving it the number of physical cores (using vcpus).  For
>> example to get optimum performance on a single quad core, use "vcpus":
>> 1, "qemu_extra_opts": "-smp cpus=1,cores=4,threads=2".
>> Cheers,
> 
> 



-------------------------------------------
smartos-discuss
Archives: https://www.listbox.com/member/archive/184463/=now
RSS Feed: https://www.listbox.com/member/archive/rss/184463/25769125-55cfbc00
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=25769125&id_secret=25769125-7688e9fb
Powered by Listbox: http://www.listbox.com

Reply via email to