What Linux Distribution Should Be Benchmarked The Most?

[bakgwailo]

OK, so totally didn't read through all of the past 180+ comments, but here is what I think (in no particular order):

1) Redhat/Fedora - Used to be pretty much the defacto distro (especially for enterprise), and still is fairly important today in the corporate world (server at least, Ubuntu has cut into the desktop)
2) OpenSuse - Again, used to be the defacto KDE distro - great support currently
3) Kubuntu or Xubuntu - pretty much Ubuntu (with all the PPA support for cutting edge that you need), but without the insanity
4) Debian - Pretty much the defacto (next to Slack) rock solid distro. Only issue I see is the cutting edge - note sure how compatible Debian is now with Ubuntu's repos (like XSwat/Edgers/etc)
5) Arch - More involved initial setup, but you can pretty much clone after the initial. Bleeding edge and generally support the latest and greatest via the AUR repo and this can be automated

So, I will say its been years since I messed with Redhat or Opensuse, so I don't know how easy it is to automate everything like updates and Git source building. Arch would be a great idea as I think you can automate most of this. However, for the easy way out, Kubuntu or Xubuntu pretty much would be a drop in and they both have pretty much decided to stay with the normal Linux stack. I am semi-prone to Kubuntu being that I use KDE, and while Kubuntu has not had the best KDE install around, it has gotten pretty good lately in my limited exposure.

[dee.]

Any other distro that uses ubiquity in their installer?

Mint. Probably many other Ubuntu-derived distros use it as well.

No? Then go for Ubuntu, you won't trouble your users and everyone will be happy.

Of course if you want to do bad marketing go with another distro...I want my bloat!
Don't use Mint. It comes with bloated MATE 1.6.

Mint comes with lots of desktops. Cinnamon and MATE are the main versions, but there are also KDE, Xfce and LXDE versions.

[powdigsig]

Any other distro that uses ubiquity in their installer? No? Then go for Ubuntu, you won't trouble your users and everyone will be happy.

Of course if you want to do bad marketing go with another distro...I want my bloat!
Don't use Mint. It comes with bloated MATE 1.6.

[Soul_keeper]

I vote for gentoo or slackware.

[juliom]

Mint is Ubuntu with a beautiful art and other desktop.

Not really. Mint's main edition is Ubuntu based, but you also have a Debian testing based Mint.

And it would be nice to have Debian benchmarks You could use Sid, almost all packages are very recent.

[timothyja]

im not a fanboy, im expresing my opinions or i dont have the right to?

I suggest you grab a dictionary and look up hypocrite. Yes you have a right to express you opinions but according to you noone else does unless they agree with your views.

[verde]

How about the top 10 from Distrowatch?

Today that would be:

1 Mint 3636<
2 Ubuntu 1976<
3 Mageia 1850<
4 Debian 1820=
5 Fedora 1450<
6 openSUSE 1361<
7 PCLinuxOS 1269>
8 Arch 1076<
9 Manjaro 1040>
10 Puppy 882=

It is 100% unreliable tool to measure distro usage. Who uses Manjaro Linux or Mageia? Less than 3% of Linux users.

[Artemis3]

Top 10 from Distrowatch

How about the top 10 from Distrowatch?

Today that would be:

1 Mint 3636<
2 Ubuntu 1976<
3 Mageia 1850<
4 Debian 1820=
5 Fedora 1450<
6 openSUSE 1361<
7 PCLinuxOS 1269>
8 Arch 1076<
9 Manjaro 1040>
10 Puppy 882=

Also Michael, you should get special sponsoring from the likes of Red Hat and Canonical, if they want to always appear in the benchmarks no matter their popularity...

Sysadmins might want to know what they trade in production performance when switching from red hat to ubuntu server, etc.

And workstation benchmarks need timed tests, from boot to login, login to desktop, desktop to launching libreoffice, stuff like that (with macro like movement of cursor and pushing things to launch apps, etc). This will show the "snappiness" of the different desktops and can help to figure out if a real time kernel; or changing the scheduler helps or harms, etc.

Oh and power consumption and temp readings for the portable and datacenter people.

Well i suppose you could stick to the 3 most popular community distros + sponsored or such.
There is no need for loyalty to a for profit company that is not contributing to your site.

[Gps4l]

Reading all the comments, about who's distro is the best. Perhapse the best idea for benchmark is to benchmark the foundation distros instead of the child ones.

Debian 7 (no GUI) instead of Ubuntu.
Redhat instead of say OpenSuse.

The child distros add and tweak their linuxes, or add or subtract things that may skew results. You need a baseline before you can compare.

So I'd advise to benchmark Debian 7, right from debian.org. Then compare it to Ubuntu. The same with Redhat as well.

I look forward to the results then.

Are you sure openSUSE comes form Red hat?

I know that openSUSE comes from slackware.

So then we should benchmark slackware....

[GreatEmerald]

I never claimed that Ubuntu was "needed by the rest of the "GNU/Linux platform" - obviously the kernel and GNU tools would continue to exist without Ubuntu, as would every distribution that is not based on Ubuntu. What I was pointing out is that there are many derivatives of Ubuntu, in response to the comment that disagreed with "Be careful what u wish for, if ubuntu would to fall it wont fall alone...". Yeah, if Ubuntu falls then there would be a bunch of Ubuntu based distributions that would fall too. Their users would suddenly find that they can't upgrade, and aren't getting any more bug or security fixes. The world would survive and people would move on, either switching to other distributions or Windows, but in the end the failure of one of the most popular and high profile Linux distributions would be incredibly bad PR for the Linux community. We need more successful Linux-based companies, not less. And if millions of Linux users are suddenly left without upgrades, security and bug fixes, then you can bet that it will be remembered for a long time, and Apple/Microsoft will be gloating that "You can't rely on Linux, your distribution can just disappear without any warning, leaving you to clean up the mess".

Oh. Well, your first post was really ambiguous in that regard, but good to know what you actually meant by that. But Ubuntu is not going anywhere any time soon, in any case.

Reading all the comments, about who's distro is the best. Perhapse the best idea for benchmark is to benchmark the foundation distros instead of the child ones.

Debian 7 (no GUI) instead of Ubuntu.
Redhat instead of say OpenSuse.

The child distros add and tweak their linuxes, or add or subtract things that may skew results. You need a baseline before you can compare.

So I'd advise to benchmark Debian 7, right from debian.org. Then compare it to Ubuntu. The same with Redhat as well.

I look forward to the results then.

No, that still doesn't make much sense. Both Debian and CentOS are very stable, which means that they don't reflect the current state. Also, openSUSE is a foundation distribution ? it started off as a fork of Slackware, but hasn't relied on it for many years now. Fedora is likewise a foundation distribution. It started off as a fork of Red Hat Linux, but it's been the driving force behind RHEL ever since, not the other way around. So while I would agree that the more independent distributions should be tested, they shouldn't be oldly stable. Debian testing would be fine in that regard, though.