2017: Should Linux Benchmarking Still Be Mostly Done With Ubuntu?

Written by Michael Larabel in Operating Systems on 26 March 2017 at 09:56 AM EDT. 81 Comments
OPERATING SYSTEMS
Every year or so it comes up how some users believe that at Phoronix we should be benchmarking with Antergos/Arch, Debian, or [insert here any other distribution] instead of mostly using Ubuntu for our Linux benchmarking. That discussion has come back up in recent days.

In our forums and Twitter the past few days, that discussion seems to have come up by some users requesting I use a different Linux distribution than Ubuntu as the main test platform for all of our benchmarking. As I've said before, Ubuntu is used given it's the most popular when it comes to Linux desktop usage as well as significant usage of it on servers / workstations / cloud. But I have no tie to it beyond focusing upon using the Linux distribution that's used by the most folks for obtaining the maximum relevance to users, gamers, and enthusiasts reading said articles. And for allowing easy comparisons / out-of-the-box expectations. On my main production system I still use Fedora Workstation as my personal favorite and in the basement server room there are a variety of operating systems -- both BSDs and Linux and from Antergos to openSUSE and Debian.

I have no plans to switch away from using Ubuntu for most of our benchmarks in the near future. As many of our cross-distribution performance comparisons have shown, when at similar package versions, Antergos, openSUSE, Debian, and others generally don't perform vastly different from Ubuntu. The only exception to that rule is Clear Linux and we already test that a lot on Intel x86 hardware as probably our second-most benchmarked distribution around here. That will continue to be the case especially as Intel continues investing in more Linux optimizations, kernel-level improvements, etc. Clear Linux is doing interesting technical work, especially in regards to performance, compared to most other Linux distributions.

When Unity 8 and Mir (and more Snaps) roll-out by default on Ubuntu, I may re-evaluate my decision of using it as the basis for most Linux benchmarks on Phoronix. Especially as no other Linux distribution is actively looking at using Mir, the Ubuntu-generated results particularly for graphics tests may begin to differ more from other Linux distributions.

But anyhow for the annual "why don't you test with XYZ Linux distribution?", there's been a user poll and unofficial discussion in this forum thread. Of course, in Phoronix discussions like this, more weight is given to the feedback of premium members who have more of a stake in future article requests. You can also share your two cents by commenting on this article in the forums. On Twitter there is also an informal poll.
Related News
About The Author
Michael Larabel

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 20,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter, LinkedIn, or contacted via MichaelLarabel.com.

Popular News This Week