Op vrijdag 25 januari 2019 14:26:46 CET schreef Liam Proven:
On 1/25/19 2:14 PM, Knurpht-openSUSE wrote:
Critisizing Phoronix != bashing.
Isn't it?
You don't think that "Phoronix is a click-bait site" is bashing? Those are your words. They look like bashing more than criti
But let's be fair, his benchmarks lack info. Which services are started at boot, what is in each distro's initrd, which filesystems are being used etc. etc.
As far as I can see, isn't the thing that he compares default installs without specific optimizations?
That seems pretty fair to me. It is how I would test.
I used to do this sort of performance-testing for a living. I ran PC Pro Magazine's in-house testing labs for some years. I did the 32-bit port of PC Pro's Windows benchmark suite. I have a little knowledge in this area.
If I was comparing the Windows installs of 2 vendors, for instance, then the _point_ of the exercise was to compare them as shipped, _not_ to optimize them first and _then_ compare them. What we were trying to find out for our readers was how quick they were out of the box.
It would be _less fair_ if I optimized them first. For instance, what if I only knew of optimizations for one particular hardware config and so did not apply them to a different vendor's equipment?
Then some machines would be optimized better than others. That is _increasing_ the unfairness.
If special steps are needed on openSUSE that are not needed on rival distros, then it is _fair_ *not* to include those steps.
No? No. Which does not mean we cannot improve things.
-- Gertjan Lettink a.k.a. Knurpht openSUSE Board Member openSUSE Forums Team -- To unsubscribe, e-mail: opensuse-factory+unsubscribe@opensuse.org To contact the owner, e-mail: opensuse-factory+owner@opensuse.org