We do often include affiliate links to earn us some pennies. See more here.
Ars Technica recently ran a few Windows vs SteamOS benchmarks, and it shows what we here already know: A lot of ports have worse performance on SteamOS & Linux.

While the benchmark is limited in the selection, and it's only on one system, we've all seen this before ourselves. I would also like to point out SteamOS has a much older Nvidia driver version, and I doubt the Ars guy manually updated the SteamOS driver, so the Windows tests are done on a much newer driver.

It's a shame, but there's no point hiding from the facts. Right now most ports run worse on Linux, a lot of it is down to OpenGL, but porters are also to blame for not optimising enough. I get why porters can't spend all their time optimising, they have to make money after-all and ports need to be pushed out quickly, but it's still annoying.

Vulkan could be SteamOS & Linux only real chance at having a level playing field, I just hope it doesn't take too long for it to come out and be used in games for us.

In regards to the gaps in performance on Valve titles: I saw first-hand how big a performance jump Dota 2 gave with Source 2 having a fully native OpenGL implementation, so I hope Valve have plans to update their other titles.

QuoteHopefully, Valve and other Linux developers can continue improving SteamOS performance to the point where high-end games can be expected to at least run comparably between Linux and Windows. Until then, though, it's hard to recommend a SteamOS box to anyone who wants to get the best graphical performance out of their PC hardware.

This bit caught my attention, as it's not down to Valve or Linux developers. It's down to the game developers, the game porters, Nvidia and AMD pushing performance in their drivers and Vulkan coming along to help out too.

What are your thoughts? Personally, I know I'm going to get less performance, but I'm in it for the long-run here.

Windows has pretty much had a monopoly on PC gaming for how many years? It will take time for Linux performance to catch up. Not even getting into all the game-specific optimizations the driver vendors do on Windows. Article taken from GamingOnLinux.com.
Tags: Editorial
0 Likes
About the author -
author picture
I am the owner of GamingOnLinux. After discovering Linux back in the days of Mandrake in 2003, I constantly came back to check on the progress of Linux until Ubuntu appeared on the scene and it helped me to really love it. You can reach me easily by emailing GamingOnLinux directly.
See more from me
The comments on this article are closed.
90 comments
Page: «9/9
  Go to:

reaVer Nov 14, 2015
@MayeulC: That was pretty informative, thanks. I'll come with a refutation when I come up with one ;)
slaapliedje Nov 14, 2015
Quoting: ricki42
Quoting: Mountain ManThe other thing to keep in mind is that even with the reduced performance, performance in Linux is still more than acceptable and won't negatively affect anybody's gaming experience. That's the problem with looking at benchmark numbers, because you'll see Windows getting 200FPS and Linux getting 100FPS, and everybody says, "Oh my gosh! Linux has 50% of the performance of Windows!" but does it really matter when everybody locks their refresh rate to 60Hz?

This may be valid for Portal, but if you want to run Shadow of Mordor on the Alienware SteamMachine, you'll have to make some serious compromises in the graphics settings to run it at 60Hz. I don't have the data, but the point remains that if you got the Alienware Alpha with the same hardware but running Windows, you'd get better graphics. And while that might not matter to you, it does matter to a lot of people, just look at any discussion comparing PS4 and XB1 performance.
Also, not everybody locks their games at 60Hz, I have a 144 Hz monitor (running at 120 Hz) and I like to put it to good use. Of course, I also have a better PC than an Alienware SteamMachine, so I'm good :D

The point is, most people (sanely) set their options to vsync so you don't get screen tear. Max frames per second never mean anything anyway, it's the damned minimum and average that count.

If I had more time, I'd try out some benchmarks on my system, but then again I'm not running SteamOS, I'm running Debian Unstable...

I do have to laugh at whomever it was earlier in this thread that said that Debian is so slow and they should have used Arch or Gentoo... I seriously notice no difference in speed between the two (actually I run Debian on an SSD, and Arch on a normal hard drive, so for me, Debian is way faster.) I'm just wondering why A) SteamOS still hasn't updated their installer so that it doesn't wipe out your drive. and B) It still shows it as being a beta on their site.

http://store.steampowered.com/steamos/buildyourown
raonlinux Nov 14, 2015
Here there is nothing new even you don't need to own a steam machine we the majority tested in our own, We knew the performance was less of course, what do u expect when you use some translation or wrapper from directx to openl more cpu more gpu and less performance of course is different is already native.
The only things that those guy just did a benchmark without understand how everything works. Just make oh check the results but you need to explain how this result were affected, and how it works.
All the games that have been release the majority were designed to been use with directx.
MayeulC Nov 14, 2015
Quoting: reaVer@MayeulC: That was pretty informative, thanks. I'll come with a refutation when I come up with one ;)
You're welcome. I'll be happy to refute your refutation by then. (Or just to argue with it, I can recognize when I am wrong :) )


Quoting: slaapliedjeI do have to laugh at whomever it was earlier in this thread that said that Debian is so slow and they should have used Arch or Gentoo... I seriously notice no difference in speed between the two (actually I run Debian on an SSD, and Arch on a normal hard drive, so for me, Debian is way faster.) I'm just wondering why A) SteamOS still hasn't updated their installer so that it doesn't wipe out your drive. and B) It still shows it as being a beta on their site.
That's not me, but I must confess that when someone says Debian, I always think about the stable branch, which has quite outdated OSS graphics drivers.
Then, just my guesses :
A) It is designed for OEMs or someone who don't know what (s)he is doing, so wiping out the entire hard drive and partition automatically might be the safest bet. Moreover, if you install this as a gaming console in your living room, you probably only want to use SteamOS. Keep in mind it's designated for the broader audience.

B) I think it's just a mistake on their part, you should report this on github.

Regarding A) I think (but I am not sure, I haven't used debian in a long time) that you could just install a minimal Debian system, or say, Linux with apt-get, add the steam repo, and perform a dist-upgrade. I don't see why this wouldn't work.


Last edited by MayeulC on 14 November 2015 at 7:09 pm UTC
Mountain Man Nov 14, 2015
Quoting: raonlinuxHere there is nothing new even you don't need to own a steam machine we the majority tested in our own, We knew the performance was less of course, what do u expect when you use some translation or wrapper from directx to openl more cpu more gpu and less performance of course is different is already native.
The only things that those guy just did a benchmark without understand how everything works. Just make oh check the results but you need to explain how this result were affected, and how it works.
All the games that have been release the majority were designed to been use with directx.
This is exactly what I mean. There's no attempt by these sites to look at things objectively or put the data into its proper context. It just comes across as cheerleading for Microsoft.
X6205 Nov 14, 2015
It does not matter what is arstechnica saying. I will not change the fact that linux gaming is stronly rising more than ever before and has a bright future :)
Purple Library Guy Nov 14, 2015
Quoting: DrMcCoy
Quoting: Purple Library GuyI guess if I'm not with you, I'm against you?
No, but you do have see who is using a group you belong to, you identify with, to justify doing harm. I do not want to stand idly by while someone who purports to speak for me does harm.

That's why I speak out against Richard Dawkins, despite identifying as an atheist. That's why I speak out against fefe, despite him being in similar computer-ish circles than me. That's why I take a hard stand against the crocodiles, despite being one of those geeks who enjoys the odd game or two.

I just have little patience left for people who so blatently throw in arguments that have been debunked so. many. times. That I have debated so. many. times. This whole blunderbuss boiled over a year ago, and by now, I nearly count people who still unreflectingly parrot the "collusion!" line as lost causes.

And yes, what is "doing harm" is subjective. I do have ideologies and biases -- and I'm quite open about them. And there are certainly issues that are important enough for me that I can't "agree to disagree".

My little digression about certain political issues here in Germany was quite overdrawn, yes. It's a thing that's been on my mind a lot lately, considering I live in the middle of it. There is a significant overlap between the crocs and several factions of neo-reactionaries and identitarians; you just have to look at what Breitbart otherwise publishes, for example.

I don't even mean to insult or implicate Nyamiou; I don't know the person enough to judge one way or another. I wanted them to see from what corner they get their arguments from, their views on culture. And I may have gone a bit overboard there.
Fair enough. Just to be clear, I'm quite in agreement with you about all the vicious knuckle-dragging crap burbling around this "gamergate" thing.
But mistrust of the media is hardly a pastime limited to the dangerous right. I still haven't seen a serious challenge to the validity of Chomsky and Herman's "propaganda model" of the corporate media.
Purple Library Guy Nov 14, 2015
Quoting: reaVer
Quoting: DrMcCoy
Quoting: reaVerYes and yes.
This has been debunked over and over and over again. There were no articles for Zoe's games while she was together with Nathan. In fact, the only two articles that Nathan wrote was one for Kotaku, before he was in a relationship with her (and that wasn't even a review) and one for Rock, Paper, Shotgun, where the game is shortly mentioned. No full review, nothing while they were dating.

No one ever managed to produce any of the alleged review articles Zoe allegedly received by "sleeping around". This is and always has been a character assassination.
You think someone would get targeted like that by thousands of people without actually instigating anything?
Yes. Duh.
Mobs and gossips and bullies do that kind of thing all the time. Had you not noticed that large scale cyberbullying has become one of the distinctive social problems of the internet era? People commit suicide from it. In Canada we haven't forgotten Rehtaeh Parsons.
In any case, this is not an argument. If you want to claim person X did thing Y, and someone shows the evidence that person X did not do thing Y, the only valid thing you can do is produce actual evidence that they did.
Liam Dawe Nov 14, 2015
Since I asked people not to keep quoting all that gamergate bollacks, and people have repeatedly not listened, I'm locking the comments before I have to deal with more comment reports and more shit.

To make it clear: We don't want anything to do with GamerGate, or any discussions taking everything with it into a hell-pit.


Last edited by Liam Dawe on 16 November 2015 at 11:35 am UTC
ricki42 Nov 14, 2015
Quoting: Mountain ManYes, there does seem to be a pattern in the broader gaming press of protecting Windows from the unsavory horde of competition, from gleeful reports about Steam Survey results to disparaging comments about the lack of games compared to Windows to the recent articles about performance disparity. We can't deny the facts, of course, but so many of these articles seem to be written with a condescending smirk and a wink to the Microsoft faithful, and that really bothers me. It's like they're trying to kill SteamOS before it even has a chance.

Quoting: Mountain ManThis is exactly what I mean. There's no attempt by these sites to look at things objectively or put the data into its proper context. It just comes across as cheerleading for Microsoft.

I don't see how you see this article as deliberately disparaging Linux or cheerleading for Microsoft. Apart from the one sentence about Valve improving Linux performance, most of it seems quite balanced. Maybe there's some subtext here I'm missing, but the article pretty much starts with
Quoting: ArsTechnicaOn the other hand, developers I talked to about SteamOS development earlier this year told me that the state of Linux's drivers, OpenGL tools, and game engines often made it hard to get Windows-level performance on SteamOS, especially if a game was built with DirectX in mind in the first place.
which is basically what people here are saying: the problem is the drivers and games built on DirectX.
They then more of less dismiss the Geekbench results as 'close enough'. And even after the SoM benchmark, the comment is
Quoting: ArsTechnicaWhile these are two AAA games ported to Linux by respected publishers, it's possible the developers simply weren't able to extract the best performance from the less familiar OpenGL and Linux environment.
Not blaming Linux, but developers' familiarity with OpenGL, which is a fair point, I've read similar comments here several times.
When most of the Source engine games showed weaker performance on Linux, the comment is
Quoting: ArsTechnicaSince the Source engine games we tested were on the older side, the frame rate performance wasn't the difference between "playable" and "unplayable" in any case, even on maxed-out settings. For games like these, which don't push the upper limits of our hardware, most gamers wouldn't even notice the difference between the frame rates listed here.
which is basically the exact same thing you said a few hours ago. And then they reiterate that games built for Linux will perform better on Linux:
Quoting: ArsTechnicaGames built from the ground up with OpenGL and Linux in mind might be able to best their Windows counterparts; similar benchmarking by Phoronix showed Unbuntu [sic] 15.04 outclassing Windows 10 when running open source Quake clone OpenArena, for instance.

The article's conclusion that it is hard to recommend SteamOS to someone looking for maximum performance is, at this point, unfortunately true. I think most of us here have other reasons why we prefer Linux.
While you're here, please consider supporting GamingOnLinux on:

Reward Tiers: Patreon. Plain Donations: PayPal.

This ensures all of our main content remains totally free for everyone! Patreon supporters can also remove all adverts and sponsors! Supporting us helps bring good, fresh content. Without your continued support, we simply could not continue!

You can find even more ways to support us on this dedicated page any time. If you already are, thank you!
The comments on this article are closed.