Ubuntu 13.04 Desktop Gaming Performance Comparison

[Cyborg16]

Link

Results of fgl_glxgears (5 sec)

glxgears isn't a particularly useful benchmark. Rexilion, certainly don't interpret that to mean "Ubuntu and Cinnamon 2D will perform far slower than other desktops in demanding games."

[Cyborg16]

we need a universal call, like Windows has, for programs to be able to tell the WM to disable compositing when needed.

Plus much more, like making sure Alt+Tab and media keys still work inside games with a keyboard grab. It's a long list...

[brosis]

we need a universal call, like windows has, for programs to be able to tell the wm to disable compositing when needed.

_NET_WM_STATE_FULLSCREEN / _NET_WM_FULLSCREEN_MONITORS
written in capitals, stupid vbulletin board is stupid.

Plus much more, like making sure Alt+Tab and media keys still work inside games with a keyboard grab. It's a long list...

Multimedia keys work in games for me. I use compiz, so its WM-related.
Alt-Tab should be implemented on application side, works for me.

[Rexilion]

glxgears isn't a particularly useful benchmark. Rexilion, certainly don't interpret that to mean "Ubuntu and Cinnamon 2D will perform far slower than other desktops in demanding games."

Agreed, glxgears is not a useful OpenGL 'wide' benchmark. But, to my opinion, should not exhibit such behaviour by just changing desktop environments. That's insane.

Even though it should not be seen as a useful benchmark, it should not run faster or slower depending on the DE used.

[stqn]

Xfwm is composited and it does not slow things down. (Even if Michael apparently did the benchmarks without compositing.)

[david_lynch]

There were two things I got from those benchmarks: 1) light-weight desktops are in general slightly faster than heavyweights (but usually not more than about 20% which implies for casual games it may not be an issue), and 2) there are a few unusual cases like Prey on Unity where the slowdown is higher than expected.

Michael, you're benchmark articles tend to lack two things: 1) a conclusion (like the above, expanded a little but still short, at the end) and 2) a little speculative discussion on why, e.g. one of the first questions in the forums was:

Especially since this feature has to be selected manually but has a significant effect it's worth a quick mention.

Actually it doesn't have to be selected manually every time. KDE allows the user to specify window rules, such as "suspend compositing when openarena is running" which makes it automatic. Any gamer on KDE would naturally add such rules.

[Pawlerson]

The bad news: Linux desktops are still unoptimized for gaming. Inconsistent at best, complete random at worst.

Then I wonder why it kills windoze in performance?

The fun news: KDE is freaking slow. Im already looking forward to the neckbeards suggesting hundreds of configs to change instead of just admitting the facts.

With suspend compositions it's running at full power and it's just a single option. I wouldn't be surprised if such option doesn't exist in gnome shell.

[xpressrazor]

That's odd... Maybe because they use something fglrx doesn't support? wow...

I had good result with vsync turned off on kde. I have not tested games on 2d desktop environments

[ElderSnake]

Would there be any argument as to why Undirect Fullscreen Windows SHOULDN'T be enabled by default in KDE?

I installed Ubuntu 12.04 last week on a machine and went to enable the equivalent functionality in Compiz Settings Manager and noticed the option was already enabled by default, so I wonder if the KDE devs should do the same thing.

If gaming in windowed mode, again I personally just switch off effects. Not like I need a cube or fancy transparency effects while playing a game anyway

[gururise]

I disagree, sticking to the default is the most realistic test. What is 'unredirect fullscreen'?
Every benchmark someone says it's useless because: "Distro Y sucks, distro X wasn't tested", "gcc didn't A,B,C parameters", "kernel ....", "Testing version 3.5.71 is stupid", "Gosh, proper gaming is done with low latency real time kernel."....

Last time I saw a blog post by kwin dev about Phoronix benchmark. He thought the benchmark was useless, because it didn't use kwin with three different drawing back-ends and n other settings. If everyone had their way, each chart would have thousands of items.

Agreed. Most Linux users are going to be using default settings.

To those who are complaining about these benchmarks: Do you really think it is realistic for the average user coming from Windows to know how to tweak numerous settings in each Desktop? I've used Gnome-Shell since its release, and still not sure how to "Unredirect fullscreen", or if there is even an option.