With the Legion Go S, we can now directly compare performance between official builds of SteamOS and Windows
-
Windows Gamers (who will never switch to Linux): Linux still isn't ready for mass adoption
Windows Gamers (who will never switch to Linux)
So you accept that Linux is not the problem.
We are litterally at the point where it will get mass Adoption in the next few years.
That is what this post is about. That you can litterally go out and buy a fully complete gaming system preinstalled with Linux that performs better than the same system with Windows.We are very close to the point where the only thing holding Linux gaming back is marketing.
-
I think there's in play also background activity from Windows' bloat.
Probably this. Especially on low end hardware that doesn't really have a lot of background resources to give.
Just open task manager and see all the shit windows thinks is essential to run all the time. Scanning the drive for viruses, downloading updates for shit you've never even looked at...
-
Source is this video:
Windows Was The Problem All Along - Dave2D
We could obviously compare performance between windows and steamOS before on the steam deck, or between windows and Bazzite on other handhelds. But this is the first time we have had official windows and SteamOS builds for the same hardware.
Back in ~2010, my first dual boot was an Ubuntu. It was fairly easy to run WoW from Linux and it gave me a solid >15fps while Windows ran at less than 10fps.
I was very young at the time but still aware that this was super impressive with extra compatibility layers. That definitely took part in selling Linux to me.
-
Windows Gamers (who will never switch to Linux)
So you accept that Linux is not the problem.
We are litterally at the point where it will get mass Adoption in the next few years.
That is what this post is about. That you can litterally go out and buy a fully complete gaming system preinstalled with Linux that performs better than the same system with Windows.We are very close to the point where the only thing holding Linux gaming back is marketing.
Marketing and market availability are the biggest problems. People need to be able to go into any store, buy a handheld/laptop/desktop and have it include Linux without them asking.
-
Marketing and market availability are the biggest problems. People need to be able to go into any store, buy a handheld/laptop/desktop and have it include Linux without them asking.
Don't forget educational institutes. Linux should be the defacto OS at such places. The younger generation's first interaction with a PC is at school. If they are used to Linux from a young age, this is greatly help them ease into the Linux mindset (package manager, terminal).
-
Source is this video:
Windows Was The Problem All Along - Dave2D
We could obviously compare performance between windows and steamOS before on the steam deck, or between windows and Bazzite on other handhelds. But this is the first time we have had official windows and SteamOS builds for the same hardware.
I'd still take this with a grain of salt. Not many games tested, and the SteamOS build might've been tweaked and worked on more to be more optimized.
-
Don't forget educational institutes. Linux should be the defacto OS at such places. The younger generation's first interaction with a PC is at school. If they are used to Linux from a young age, this is greatly help them ease into the Linux mindset (package manager, terminal).
That too, as well as in professional and government settings.
-
Source is this video:
Windows Was The Problem All Along - Dave2D
We could obviously compare performance between windows and steamOS before on the steam deck, or between windows and Bazzite on other handhelds. But this is the first time we have had official windows and SteamOS builds for the same hardware.
Holy shit triple the hours
-
It's just Vulkan outperforming DirectX by translating DirectX to Vulcan. If you're comparing the default experience with Windows and Linux, how can you say Proton isn't technically improving performance? What would you call that if a performance increase is caused by running through Proton?
As pointed out higher up this thread DXVK and Vulkan also work in Windows (without Proton) were they give performance improvements.
Further, it's perfectly possibly to run Windows games via DXVK and Vulkan in Linux without Proton - just use plain Wine (of which Proton is a branch) instead - and you also get the performance improvements (certainly that's my perception in my system since I tend to get my games from GoG instead of Steam when available and thus run them via Wine instead of Proton).
So that's at least two situations were the performance improvements are present without Proton, hence you cannot logically claim they're due to Proton, even indirectly.
Logically the place most likely to yield performance improvements is the full implemention of a rendering stack directly on top of the hardward which even has its own architecture - Vulkan - since there's a lot more room to improve usage of hardware resources at that level, though things like pre-conversion and caching of Vulkan shaders from DirectX shaders, which are done at a higher level (Proton or DXVK), can also improve performance.
It's possible that Proton itself is delivering some performance improvements (for example, via the trick of, pre-converting shaders from DirectX to Vulkan before game start, uploading the generated shaders to the Steam servers and then other users just download the converted shaders and do not require that step, which should speed up game start tough I have at least one game were it actually can slow down A LOT game start because the generated shaders are massive) versus solutions using DXKV + Vulkan without Proton, but that's not really enough to sustain a claim that the performance improvements are mainly thanks to Proton in the face of also seing the performance improvements when Proton isn't there.
-
I'd still take this with a grain of salt. Not many games tested, and the SteamOS build might've been tweaked and worked on more to be more optimized.
wrote last edited by [email protected]Does this look optimized to you, Windows side?
-
I think there's in play also background activity from Windows' bloat.
wrote last edited by [email protected]They say I/O schedulers on Windows are weird.
Edit: or was it CPU schedulers? I'm sure i've read something about this forever ago.
-
Source is this video:
Windows Was The Problem All Along - Dave2D
We could obviously compare performance between windows and steamOS before on the steam deck, or between windows and Bazzite on other handhelds. But this is the first time we have had official windows and SteamOS builds for the same hardware.
makes a lot of sense honestly. I never knew the numbers behind it (tks for sharing). when I was ripping witcher 3 on nobara and then changed my OS back to Windows due to work related issues, I felt a SIGNIFICANT performance drop. the game became laggy, when it used to run top on Linux with the same settings. good share - the time for Linux gaming is now.
-
IMHO you shouldn't have to run a stripped down Windows to get good results. It should just work that way out of the box. LTSC is not supposed to be a consumer OS.
Shouldn't have to, absolutely, but its done anyway, so I think its can be relevant.
Until that last little bit of stuff I have to use windows for becomes linux native or at least doesn't have a tutorial to make it work that makes my eyes cross, its just easier for me to use my stripped down windows install because it just works.
-
Proton uses Wine, which is a Windows system call API translation layer for Linux. In other words, it translates commands for the Windows kernel into calls for the Linux kernel.
So it's kind of an emulator and kind of not, but regardless the metaphor of a translator is fine. As a lightweight translator, you might say it's like using Google Translate on your phone to translate back and forth quickly and automatically, rather than having a person in the middle who needs to think about it.
In Software Design terminology, Wine and DXVK are "adaptor" layers (each convert one kind of API interface into a different kind - Wine doing Windows API to Linux API conversion and DXVK doing DirectX API to Vulkan API - and nothing more) whilst Proton is more a controller that just manages those things and adds some more functionality on top such as Steam integration for ease of use.
Without Proton users would have to know a bunch of command lines parameters and environment setup to launch all the right components with the right configuration so that they can first install and then run their Windows game in Linux. In fact this is the situation if you use Wine directly without something like Lutris to do a similar work as Proton.
Personally I prefer Lutris since it's more flexible - for example I can configure it to run games sandboxed with networking disabled - and it's not tightly bound to a single games store.
-
Does this look optimized to you, Windows side?
wrote last edited by [email protected]While I get it, it does look pretty damning, skepticism when we haven't been presented with rigorous documented testing is always good. I don't think ex: gamersnexus is going to find different results, but I'm pretty damn sure they'll at least be comparing chipsets to ensure the hardware actually is identical (and making sure that things like system settings are configured to be as fair as possible). Lets not be apple fans and leap to the top of the superiority heap just because a good looking infographic said we should.
-
They say I/O schedulers on Windows are weird.
Edit: or was it CPU schedulers? I'm sure i've read something about this forever ago.
wrote last edited by [email protected]Yes/no.
The linux scheduler is a work of art - heuristics to dynamically determine resource access priority, checks for resource locking that are some of the most elegant pieces of code written by humanity, incredibly adaptable and clever. It took me the better part of a year before I really understood the underlaying mechanics, and even now I could by no means reproduce it on my own. It's truly an amazing bit of mathematics.
...
Windows solves the same problem by randomly elevating processes to maximum priority. That's it, that's the whole algorithm.Depressingly, they're equally effective.
-
What's nice is that Microsoft today doesn't have capability to improve in the short or even medium term. They could drop a billion dollars into it and it would still take them years to improve their offering, if they can at all.
I'd wager they could cut a lot of cruft from a handheld gaming device specific version of Windows.
I bet Antimalware Service Executable is still randomly springing it's way to the top of task manager in this build. All sorts of crap that just doesn't need to be running. On my PC right now I can see Service Host: DNS Client at 1-4% all the fucking time. Random driver update checks that run in fucking Electron for some godforsaken reason. That kind of shit.
-
Source is this video:
Windows Was The Problem All Along - Dave2D
We could obviously compare performance between windows and steamOS before on the steam deck, or between windows and Bazzite on other handhelds. But this is the first time we have had official windows and SteamOS builds for the same hardware.
wrote last edited by [email protected]So a specialized OS wins over a general OS in their specific tasks?
Amazing ...
-
Windows Gamers (who will never switch to Linux): Linux still isn't ready for mass adoption
wrote last edited by [email protected]Even gamers do more than just game on their PC, though.
-
Does this look optimized to you, Windows side?
No, because Windows isn't optimized for games. It is for general use, including games.