[Info-vax] Some VMS/x86 perf test data from WASD maintainer.

[Simon Clubley]

On 2023-04-27, Single Stage to Orbit <alex.buell at munted.eu> wrote:
> On Thu, 2023-04-27 at 17:31 +0000, Simon Clubley wrote:
>> If those are the kernel figures for an Intel box, I would love to see
>> what they are for an AMD box...
>
> Point me in the direction of a copy of VUPS.COM and I can run these
> benchmarks.

VUPS.COM is interesting, but it isn't the thing that's showing up
the extra kernel mode overheads for real-world activities.

Mark's numbers shown here:

https://wasd.vsm.com.au/info-WASD/2023/0077

with real-world I/O activity, are showing major increases in the percentage
of kernel mode overhead time consumed.

I would be interested in seeing what VSI have to say about Mark's numbers.

We need to be focusing less on artificial tests such as VUPS.COM and more
on the real-world tests like the ones that Mark is running.

Simon.

-- 
Simon Clubley, clubley at remove_me.eisner.decus.org-Earth.UFP
Walking destinations on a map are further away than they appear.