What Linux Distribution Should Be Benchmarked The Most?

[TheOne]

This is just insane, this forums are full of fanboysm! I thought developers/coders with some knowledge of the inner working of things and neutral view visited this forums, but it seems that the majority is religious, people who uses linux based operating systems and feel superior even when they haven't written one single application or line of code. Thats what I perceive of the people posting on this thread, people with the attitude of a child.

Is fun and at the same time disgusting to see people threatening Michael to stop visiting Phoronix because he uses Ubuntu for benchmarking software, are they kidding? So now the guy providing us nice benchmarks has to support all the distros people use here so he can please everyone, thats insane. Why doesn't that people running other distros (since they are so superior) provide the benchmarks them self? I'm sure they don't have the minimum idea of how to do it, thats laughable.

One of the must laughable thing is those guys suggesting gentoo for benchmarking software compiled with optimizations to the target CPU, come on, even most advanced developers don't go to the trouble of compiling the whole system from scratch, ask kernel developers which distro they use.

In any case besides all the crazyness going on this forums I would suggest to Michael to keep doing what he is already doing, a great job! Also it may be nice idea a community initiative where third party people can provide benchmarks of other linux distros so Michael can include them on the comparisons. So Michael could post which kind of benchmark he is going to make, so the community can duplicate it on the distro of choice and publish results.

Edit: Same hardware duplication can be a problem, but with a community so big there may be other people with hardware that matches those of Michael.

[rudregues]

+1 OpenSUSE

Phoronix members:
- Select your Gentoo and configure it with -march=x86_64 instead of -march=native or -march=btver1 or whatever
Think about this.


Now, about the question: OpenSUSE. From what I see in this thread it fits very well the needs of phoronix . Easy to use latest kernel, easy to install new packages and easy to someone reproduce.


Obs.: sometimes it would be interesting to see cross-distro comparisons too :-)

[droste]

+1 for openSUSE latest release or tumbleweed (why was already mentioned ;-))

[GreatEmerald]

I fully agree. There is no point in benchmarking distributions which are not used by many people. So for now, just stick with Ubuntu until the majority of Linux users moves on.

Also, if you decide to use a different distribution, please choose one which is actually usable for daily work. Many people here in the forums use their operating system as a playground and don't mind if it breaks. The majority of the people however, need an operating system which can be used to get some work done. Therefore, please use a distribution for your benchmarks which can also be used in an enterprise environment, not a toy-distribution for OS devs.

And how will you know when the majority of users have moved on? How do you know they haven't moved on already?

I don't think any of the distributions discussed here are not usable for daily work. I'm pretty sure nobody is suggesting to benchmark only Rebecca Black from now on...

i don't know which other distro recommend to the noobs

Mageia, hands down.

I guess Lubuntu will be the only relatively massive one relying on X, and then Xubuntu or Kubuntu (I'm not saying Fedora because of the debug build, which might lead to misinformation about the performance of this kind of stack) are likely to use Wayland eventually.

I don't think Lubuntu would stick to X. Once LXDE ports everything to Qt 5, it will be able to use Wayland without issues.

I am not a fan of Ubuntu/Canonical, but this is just ridiculous. How do you people think that using Ubuntu instead of Fedora/openSuse/Arch/Slackware/... will affect the results of those benchmarks? The only thing that comes to my mind (and where Ubuntu had problems in the past) is the compositor/WM that can influence the gaming benchmarks, a thing that can easily be fixed by using a version with a non-compositing WM, for example Lubuntu. But if Michael makes a comparison of kernel versions, graphic drivers or anything else the OS that is used shouldn't matter at all, otherwise the benchmarks setup is flawed in itself.

The problem is Mir. If you do graphics benchmarks, and it's running on Mir, while the readers are using Wayland, the results are useless to the readers. This topic is about discussing future plans, not just looking at this exact moment in time. And Lubuntu is a distinct distribution from Ubuntu, so nobody is saying that it's not up for consideration among the other distributions.

(following not a name) ... some slackware based distro

You mean openSUSE?

[mrugiero]

I don't think Lubuntu would stick to X. Once LXDE ports everything to Qt 5, it will be able to use Wayland without issues.

LXDE might not stick strictly with X, but Lubuntu maintainers want to avoid the extra memory use compositing implies (from the buffers you need for every window and such, not implying that either Mir or Wayland would use more memory by themselves because that's not even likely). Remember one of the focus of Lubuntu is to minimize memory use, and they already stated they might want to avoid compositing all in all. Wayland and Mir mandate compositing for traditional desktop use.
Also, Openbox might not be ported (it's not very active, so I don't think anyone will port it in the short term), so they'll have to use a different window manager than the de facto standard for LXDE if they want to use Wayland.

[chrisb]

You can name even a bigger list of distros, and those distros will still not be a game changer. They can rebase on anything else. And that's pretty much trivial.

Yes, all the Ubuntu derivatives could rebase on something else, but how could they do that seamlessly so that users can upgrade from their existing installs? It certainly isn't trivial to write an upgrade program that takes arbitrary Ubuntu derivative desktop install X and replaces it with Fedora whilst maintaining all the user's custom configuration and packages. I suppose they could take the easy way out and not allow users to upgrade - demand a fresh install - but that's not user friendly. There is also the issue of converting all of their custom package patches, package/ISO build scripts, installers, etc. to a new distribution. It could be done, Debian would be the obvious choice. For some derivatives the switch might be trivial, but for some others it could be quite a bit of work.

But why should the people who make those Ubuntu derivatives bother switching? I doubt their users are demanding it. Perhaps they are still happy using Ubuntu. Should they do it to satisfy the whims of Phoronix users? Keep in mind that Xorg isn't being removed on Ubuntu, so any reason you propose has to be better than the default of carrying on using Ubuntu+Xorg. The only possible reason I can see is if Ubuntu ceased as a distribution - but that is unlikely - it is much more likely to morph into something else than to disappear altogether from the face of the earth.

[verde]

This is just insane, this forums are full of fanboysm! I thought developers/coders with some knowledge of the inner working of things and neutral view visited this forums, but it seems that the majority is religious, people who uses linux based operating systems and feel superior even when they haven't written one single application or line of code. Thats what I perceive of the people posting on this thread, people with the attitude of a child.

Is fun and at the same time disgusting to see people threatening Michael to stop visiting Phoronix because he uses Ubuntu for benchmarking software, are they kidding? So now the guy providing us nice benchmarks has to support all the distros people use here so he can please everyone, thats insane. Why doesn't that people running other distros (since they are so superior) provide the benchmarks them self? I'm sure they don't have the minimum idea of how to do it, thats laughable.

One of the must laughable thing is those guys suggesting gentoo for benchmarking software compiled with optimizations to the target CPU, come on, even most advanced developers don't go to the trouble of compiling the whole system from scratch, ask kernel developers which distro they use.

In any case besides all the crazyness going on this forums I would suggest to Michael to keep doing what he is already doing, a great job! Also it may be nice idea a community initiative where third party people can provide benchmarks of other linux distros so Michael can include them on the comparisons. So Michael could post which kind of benchmark he is going to make, so the community can duplicate it on the distro of choice and publish results.

Edit: Same hardware duplication can be a problem, but with a community so big there may be other people with hardware that matches those of Michael.

I am covered. I dont have to add anything else from now on in this thread.

[pmorph]

You're right, there is absolutely nothing that builds on Ubuntu... apart from Edubuntu, Ubuntu GNOME, Kubuntu, UbuntuKylin, Lubuntu, Mythbuntu, Ubuntu Studio, Xubuntu, BackBox, Baltix, Fluxbuntu, FrogLinux, Guadalinex, Itis Linux, ChristianUbuntu, Ubuntu Mini, Sabily, Ubuntulite, UbuntuRescueRemix, Dubuntu, liUbuntu, Tilix, Runtu, gNewSense, Ichthux, Linux Secure, Mint, Pioneer, MMourcebuntu, TeXbuntu, Vinux, BlankOn, Elbuntu, Zorin OS, Gnoppix, gOS, ImpiLinux, Kiwi_Linux, nUbuntu, PUD Gnu/Linux, Pyramid Linux, TheOpenCD, Ulteo, Bardinux, FreezyLinux, OzOS, moonOS, Ubuntu Eee, SuperX, Satux, BigLinux, LliureX, OpenTLE, Polippix, BoliviaOS, Bubuntu, iMagic OS, Securpc, Zevenos, and Estobuntu.

Yeah, and if all those were to die today, GNU/Linux goes on without much trouble.

[rudregues]

+1 OpenSUSE

Phoronix members:
- Select your Gentoo and configure it with -march=x86_64 instead of -march=native or -march=btver1 or whatever
Think about this.


Now, about the question: OpenSUSE. From what I see in this thread it fits very well the needs of phoronix . Easy to use latest kernel, easy to install new packages and easy to someone reproduce. It has even a rolling release


Obs.: sometimes it would be interesting to see a cross-distro comparisons too :-)

[mrugiero]

But why should the people who make those Ubuntu derivatives bother switching? I doubt their users are demanding it. Perhaps they are still happy using Ubuntu. Should they do it to satisfy the whims of Phoronix users? Keep in mind that Xorg isn't being removed on Ubuntu, so any reason you propose has to be better than the default of carrying on using Ubuntu+Xorg. The only possible reason I can see is if Ubuntu ceased as a distribution - but that is unlikely - it is much more likely to morph into something else than to disappear altogether from the face of the earth.

Why should I propose any reason for them to switch, if I'm not asking them to? I just say they won't die just because Ubuntu may or may not fall.

EDIT: As for the update not being trivial, Ubuntu distro upgrades broke my system more than once, so it's not like they are the ultimate cure for everything. I agree the update process might not be trivial, but since a fresh install is preferred usually anyway (because sometimes the upgrade breaks the system) is not that much of a change. As for rebasing, rebasing on Debian is quite trivial for an experienced maintainer.