Intel's Clear Linux Outpacing Ubuntu 22.04 LTS, Fedora 36 & Other H1'2022 Distros

[Grinness]

Michael

Am i missing something or the calculations w.r.t. number of last places for arch linux is wrong?

in the last graph you report for number of last places:

Arch Linux 21 [20.8%]

But going through the article I count a total of 10 -- below Arch linux n. of last places in graphs by page in the article:

Distro	Page	N.Last
Arch	2	0
Arch	3	3
Arch	4	4
Arch	5	3
Arch	6	0
Total		10

Sorry results are correct, did not see the link:

https://openbenchmarking.org/result/2205127-NE-XEONLINUX78&sgm=1&sor

[-MacNuke-]

Please don't help me. I prefer to deal with something which is tested using proper methodology and the scientific method. Nothing in your reply contains even a modicum of it.

Okay, good luck for your search of the obvious.

[mlau]

Let's continue to test then, right? It makes the world a better place, right? It's outright useful, right? There's so much value in it, right? Ad impressions I guess, yeah.

Why do you care so much what Michael does with his time ?

[Michael]

Michael

Am i missing something or the calculations w.r.t. number of last places for arch linux is wrong?

in the last graph you report for number of last places:

Arch Linux 21 [20.8%]

But going through the article I count a total of 10 -- below Arch linux n. of last places in graphs by page in the article:

Distro	Page	N.Last
Arch	2	0
Arch	3	3
Arch	4	4
Arch	5	3
Arch	6	0
Total		10

Click the openbenchmarking link on the last page of the article... There were more than 100 tests conducted. The uninteresting / redundant / etc results, can all be seen from that OB result file.

[CochainComplex]

Let's continue to test then, right? It makes the world a better place, right? It's outright useful, right? There's so much value in it, right? Ad impressions I guess, yeah.

well I'm using a HPC once in a while with virtualization to analyse measurement data. I do consider the results of benchmarks here to get out more performance. Even if it is just choosing a more performant base image. That saves time and power ...so yes it basically does make the world a little better. At least it helps me.

[brucethemoose]

Are any of the other distros tweaked for x86-64v3?

CachyOS is more-or-less an optimized vanilla Arch distro. They build x86-64-v3 packages, and also host some performance-related modifications.


ALHP.GO is a drop-in x86-64-v3/LTO replacement for the vanilla Arch repos.


I use both, and so far they're great projects.

[George99]

• GCC flags? (I guess the most important)
• Kernels' CONFIG_HZ/CONFIG_PREEMPT settings?
• Kernels' debugging options?
• Default schedulers and their options?
• Something else?

Hand written x86_64 assembler code for time critical sections?

[3iswolf]

Thank you very much for this review. Very helpful.

I would love to know how this comparison would be with an Epyc 3rd gen. What distro would be there in the front?

[Michael]

Thank you very much for this review. Very helpful.

I would love to know how this comparison would be with an Epyc 3rd gen. What distro would be there in the front?

Here are benchmarks from autumn on the EPYC Milan across distros - https://www.phoronix.com/scan.php?pa...-distros&num=1

[fong38]

Arch Linux is one of the slowest distro, when a decade ago it used to be one of the fastest. They need a x86-64v3 port as soon as possible.

I'm confused. Doesn't arch already compile their packages with -march=x86-64-v3 already? https://gitlab.archlinux.org/archlin...0002-march.rst