I use Arch as my main distro, but if it was maximum efficiency and speed I wanted, Gentoo would be the distro to do it, not Arch (although Arch is very nicely configured out of the box, I love it's default kernel settings)
Announcement
Collapse
No announcement yet.
Is Antergos Arch Linux Really Faster Than Ubuntu, Fedora?
Collapse
X
-
Originally posted by mir3x View PostLast time i checked phoronix test suite - it tested THE SAME binaries between systems, so xonotic from arch and xonotic from ubuntu are the same ... those tests are far far from decent ...
Comment
-
Thank you Michael for the article
And thank you 'guy' who provided the 'tweaking' guides for openSuse and Arch.
I'm curious, would the tweaking guides, if applied to both all testing systems fairly, yield differant results, or same?
Anyway, I got my own hardware to test on and Michael and Co have some software to test with.
rabcor
I use Arch as my main distro, but if it was maximum efficiency and speed I wanted, Gentoo would be the distro to do it, not Arch (although Arch is very nicely configured out of the box, I love it's default kernel settings)
Hi
Comment
-
Originally posted by Alejandro Nova View PostArch isn't inherently faster than any Linux system.
OTOH, a Linux system tuned according to the guides published in the ArchWiki is WAY faster than any other Linux system.Hi
Comment
-
Originally posted by LinuxFaiT View PostSo I totally get the "defaults" approach to benchmarking. Being able to reproduce the results is, in fact, the cornerstone of benchmarking. But the issue here is that Arch is not about "defaults" its about doing it yourself and adding all the tweaks and mods you want. This is why Phoronix went with Antergos, to get some defaults. But I think the best way to go about it would be if somebody (somewhat knowledgeable) took his offer and posted the tweaks they would do in detail.
At the end of the day though, I use Arch because of the documentation, Aur, package management, and rolling release. I don't claim any "magic" speed improvement. However, the nature of Arch makes it easy to strip down (or simply not install in the first place) a lot of the overhead most other distros install to appeal to as many people as possible.Originally posted by Article, duhFor those that will then say "the results are invalid because you didn't tune the system properly" or "you should have done XXX first", my response to which is assuming the distribution defaults given that's what a majority of users will do in the real-world and is the only way for the results to be reproducible and meaningful to any large number of users. For those that insist on tweaked system results, my offer still stands of having such ardent users put together a Wiki page or forum thread that extensively details all the recommended tunables for achieving maximum performance, etc. I'll happily follow such run for a separate article to see the performance impact made and then at least allows the community to evaluate the options and understand all of the tweaks being made so that they too can reproduce them. That really is my offer and belief for any topic, just not about Arch Linux, and from there it's easy to determine who is just blowing hot air.
(I am an Arch user, and I think pretty much the same thing, default settings is how do you show the distro to the world, anything else is obviously let a the user choice, but if you don't show the true strenght of Arch, the distro wouldn't be chosen because anything else)
Comment
-
Originally posted by akincer View PostIt's been at least a year since I last gave Arch a whirl, but I did NOT find this to be the case. At all. I'm not a Linux noob and have run and managed various distros for quite a few years. But my experience in building a highly functional desktop from scratch is non-existent, so that's what I set out to do with Arch and turned to the documentation to assist me in this.
To call that experience frustrating would be too kind. I'm not quite sure what I'd call it, but the one thing I can say is that the documentation for building what I'd call a highly functional desktop was nearly worthless. And I tried browsing the Wiki directly and Googling thirty ways from Sunday. I was not impressed with the results.
Maybe in the last year or two the documentation on this has made leaps and bounds, but if not then I'd call it a dismal failure for what seems like a very ordinary task someone might want to accomplish.
FWIW -- I tried finding documentation on building a highly function desktop using both GNOME and XFCE. IIRC, the XFCE documentation was light years better than the GNOME, but both were absurdly incomplete.
Comment
-
Originally posted by Hamish Wilson View PostI have to agree with kaprikawn that the documentation is the best in the Linux world and really do not understand how you encountered problems. I jumped to Arch on my main system because the Arch Wiki had already become my go-to source for Linux information.
I also agree with many of the comments in this thread - the reason people choose to use Gentoo/Arch is to have the ability to configure their system to how they like it and squeeze some extra performance via compile flags and/or package configuration settings. If you installed the same kernel/drm/mesa stack on Ubuntu as what was used on Arch, you'd probably discover that the performance difference is nigh neglible.
Comment
-
I have been arch user for years, but switched to kubuntu from last year, because i didnt have time to resolve all the issues arch had while switching to systemd, for my own system.
Anyways. I think main advantage on arch is the amazing ABS which helps you build fast and easily the missing packaged or install experimental or newest version of software without depency hell that example you can come across with ubuntu etc.
What comes to different Graphics performance. I think they are pretty equal if you run KDE or GNOME or what ever desktop which will eat your resources.
Anyways the advantages for arch being fast comes from ABS in my opinion.
Comment
-
Originally posted by stiiixy View PostThank you Michael for the article
And thank you 'guy' who provided the 'tweaking' guides for openSuse and Arch.
I'm curious, would the tweaking guides, if applied to both all testing systems fairly, yield differant results, or same?
Anyway, I got my own hardware to test on and Michael and Co have some software to test with.
Iit would depend on a lot of stuff. Some times X distro is shipping bug, regression, etc in a lib or app, while Y distro has already patched it. Or maybe they have slightly different toolchains, etc..
Originally posted by stiiixy View PostIt was my impression that Arch was always that one level of nerdiness below Gentoo. It alllowed for simultaneous simple package management and source compiling with tweaks when and where you wanted, and that was the plan.
Originally posted by stiiixy View PostYes, but can the tweaks to Arch be applied to any other distro's, and will they perform similarly. Truly reproducible, or is Arch doing some 'magic faerie dust' things to their binaries before comilation that is opening up feature's for more tweaking?
Comment
Comment