Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Linux gaming is faster because Windows APIs are becoming Linux kernel features

xda-developers.com

Post reply on HN
Print view View original

411–420 of 694 posts

Re: Linux gaming is faster because Windows APIs are becoming Linux kernel features

#411

Post by protocolture »

neverkn0wsb357 wrote: post #295

Given the current momentum, it feels like (to me) the adage of “Windows is for Games” is going by the wayside. If you look at Steam, and OSs like Bazzite it’s clear the consumer-side is finally shoring up. But that aside, from an economic incentive, game providers (for example Amazon Luna), don’t want to be paying the licenses for running Windows machines for Video Game Streaming on Demand. In fact, at my time there…

>Given the current momentum, it feels like (to me) the adage of “Windows is for Games” is going by the wayside.

I think that games have been a strategic priority for Windows for a very long time. Going all the way back to DOS/4GW on Windows 95. But the impression I get from Microsoft is that they kind of don't want the hassle of maintaining a desktop OS anymore, and they would be happier if everyone went elsewhere.

Re: Linux gaming is faster because Windows APIs are becoming Linux kernel features

#412

Post by protocolture »

Night_Thastus wrote: post #140

Show me the numbers. Show me an identical gaming PC running Windows 11 and then Linux, and show not just FPS - but things like frametime pacing, latency, etc. This NTSync stuff is very impressive, but I haven't seen a lot of end-to-end numbers versus Windows. The last comparisons I saw showed pretty much every distribution on the order of 5-30% behind Windows, varying on the game. And Nvidia GPU support was still not…

Faster (than previously) not Faster (than windows).

The title after the jump is "Linux gaming is getting faster because Windows APIs are becoming Linux kernel features"

Getting faster. Not at parity yet.

Re: Linux gaming is faster because Windows APIs are becoming Linux kernel features

#413

Post by poizan42 »

0dayz wrote: post #311

What excites me is that the kernel gets better not only for windows games but can also get benefits that can be more general purpose, such as what the article writes about: program able to wait for multiple events at once. It will be interesting to see how native Linux games differ in what fancy under the hood kernel or syscall features they use.

NTSYNC seems quite cumbersome to use for your own linux software though

> The ntsync driver creates a single char device /dev/ntsync. Each file description opened on the device represents a unique instance intended to back an individual NT virtual machine. Objects created by one ntsync instance may only be used with other objects created by the same instance.

So you need a server process that can open the char device and hold onto the fd that you can then request through a Unix domain socket.

Re: Linux gaming is faster because Windows APIs are becoming Linux kernel features

#414

Post by achierius »

amiga386 wrote: post #294
dullcrisp wrote: post #170

Earlier quoted context omitted.

Why/when are traps used rather than explicit system calls? Is it just historical coevolution? Or is the idea that the user mode program doesn’t need to know that it’s unprivileged? Or is it just repurposing the error handler path to perform privileged operations?

As others have said, a trap is one way to implement system calls. It's literally the TRAP mnemonic on a 68000. https://www.nxp.com/docs/en/reference-manual/M68000PRM.pdf see page 292, also see page 629 for the table of "exception vectors" (addresses for code to handle each specific trap/exception/interrupt) Most processors support both "interrupts" (an external peripheral is banging on the CPU's interrupt pins... but…

> Depending on the processor, accessing the "privileged" mode can be done either by software interrupts, exceptions, or both. An operating system should pick one and stick with it.

Practically most will support access via both, but for different reasons. For example, page faults (which the software cannot possibly predict) are going to be exception-mediated, but syscalls (which the software asks for) are triggered via an interrupt.

Re: Linux gaming is faster because Windows APIs are becoming Linux kernel features

#415

Post by isityettime »

bigyabai wrote: post #373
forrestthewoods wrote: post #371

Earlier quoted context omitted.

Nah. Linux is still too bloody awful for power users, never mind the median gamer. Most Linux usage is SteamOS which only barely counts. It’s a great hedge that keeps Windows almost honest. But we’re a long long long long long long long long ways from the median gaming PC being Linux.

Linux is for power users. Windows 10 with Powertoys and WSL for stuff like yt-dlp is a fine stopgap, but you can get the same workflow on Linux with a leaner system. I never installed Windows 11 on any of my PCs, there's no place for it in my work or gaming regimen. If Linux is supposed to keep Windows honest, then some dev at Microsoft must have a Pinocchio nose.

The problem is that Windows power users arrive on Linux and think they know what they're doing, when in reality they don't know up from down. Very basic things like norms about user confirmation and warnings are frequent stumbling blocks.¹

Windows power users expect their habits and instincts to be right and treat the system as broken wherever they aren't. After all, they "know computers"! So when one of them hits a snag, even if it would have been avoided by heeding a system's warnings, reading the documentation, or adhering to its norms, they declare (for others to repeat) things like "Linux isn't (ready) for power users".

--

1: Windows power users arrive to Linux with a mixture of incredible fatigue from pop-ups and blindness to all interruptions. They are used to mindlessly batting away constant notifications and distractions. They are also used to a host of familiar warnings that they know are bullshit, and reflexively ignore. But the warnings on Linux systems are not the warnings they know. They don't actually know what they mean or which are safe. To the point that their blindness to warnings becomes outright comical, as in this infamous example: https://i.imgur.com/J39WfLK.png

Re: Linux gaming is faster because Windows APIs are becoming Linux kernel features

#416

Post by zrm »

wtetzner wrote: post #363
dragontamer wrote: post #359

Earlier quoted context omitted.

It never was fair to play vs computers in reaction games or skill games. IE: Quakebots and Fighting games have perfect reaction times and perfect combos. They can simply block perfectly and counter attack perfectly and never drop a combo. You act like cheating is new to video games?? -------- We never wanted bot in these games. Still don't want them today, and it's a big reason that playing on public boxes (ex: at an…

> You act like cheating is new to video games?? No, I think the point is that with AI the existing anti-cheat measures can simply be avoided by letting the AI play through the same interface as a human. Therefore anti-cheat kernel modules will no longer be useful, and will no longer be a reason to stay on Windows.

It seems like what this needs is the return of video arcades.

Fill a room at the mall with Linux boxen with midrange GPUs and fiber internet and the sort of keyboards you can clean with pressurized water. Charge an entry fee and then sell pizza, cheetos, coffee, soda and beer. Open at 11AM and close at sunrise.

Then publish the public IPs used by the arcade-owned machines at each location in the chain and use different public IPs for the customer WiFi. No DRM nonsense, just a way to know you're playing with someone at the arcade where the management doesn't allow cheats on their machines.

Re: Linux gaming is faster because Windows APIs are becoming Linux kernel features

#417

Post by kstenerud »

Night_Thastus wrote: post #140

Show me the numbers. Show me an identical gaming PC running Windows 11 and then Linux, and show not just FPS - but things like frametime pacing, latency, etc. This NTSync stuff is very impressive, but I haven't seen a lot of end-to-end numbers versus Windows. The last comparisons I saw showed pretty much every distribution on the order of 5-30% behind Windows, varying on the game. And Nvidia GPU support was still not…

> Show me the numbers. Show me an identical gaming PC running Windows 11 and then Linux, and show not just FPS - but things like frametime pacing, latency, etc.

No.

> I WANT to swap. Please give me cause to do so.

If you won't put the work in, why should we help you? Just stay on Windows, and we'll enjoy our Linux gaming rigs.

Re: Linux gaming is faster because Windows APIs are becoming Linux kernel features

#418

Post by emkoemko »

KennyBlanken wrote: post #313
neverkn0wsb357 wrote: post #295

Given the current momentum, it feels like (to me) the adage of “Windows is for Games” is going by the wayside. If you look at Steam, and OSs like Bazzite it’s clear the consumer-side is finally shoring up. But that aside, from an economic incentive, game providers (for example Amazon Luna), don’t want to be paying the licenses for running Windows machines for Video Game Streaming on Demand. In fact, at my time there…

Online multiplayer games keep trying to allow linux users in and keep having to lock them out because there's an instant influx of cheaters. The Nintendo Switch (which runs Linux) was a favorite of cheaters after jailbreaks came out. When anyone can compile and run their own kernel with god knows what for modifications, that makes it substantially easier for cheaters and substantially harder for anti-cheat. I don't s…

i am really doubting that Nintendo Switch uses Linux?... they would have to provide source code no?

Re: Linux gaming is faster because Windows APIs are becoming Linux kernel features

#419

Post by emkoemko »

ben-schaaf wrote: post #349
QuaternionsBhop wrote: post #333

Earlier quoted context omitted.

> You can't rely on server-side detection either, because some of the cheats are so advanced they go to great lengths to "behave" like a highly skilled human player would with their aiming Shouldn't that be the goal of anti cheat? That cheating is indistinguishable from expert gameplay? Seems to me like these companies are just trying to avoid implementing proper infallible server-authoritative gameplay by offloading…

All these games already have an authoritative server. These cheaters aren't breaking the rules of the game by being invincible, super speedy, etc. they're aim-botting and wall hacking. Those cheats can't be prevented with authoritative networking.

why can't we prevent wall hacking by not sending packets of enemy players position if the user can't see them on their screen

Re: Linux gaming is faster because Windows APIs are becoming Linux kernel features

#420

Post by emkoemko »

Night_Thastus wrote: post #140

Show me the numbers. Show me an identical gaming PC running Windows 11 and then Linux, and show not just FPS - but things like frametime pacing, latency, etc. This NTSync stuff is very impressive, but I haven't seen a lot of end-to-end numbers versus Windows. The last comparisons I saw showed pretty much every distribution on the order of 5-30% behind Windows, varying on the game. And Nvidia GPU support was still not…

they installed Linux on a PS5 and somehow the Windows games running through proton get same or sometimes a little bit more fps then the native ps5 game, its crazy
Post reply on HN