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

Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

marco-nett.de

Post reply on HN
Print view View original

181–190 of 297 posts

Re: Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

#181

Post by its-summertime »

cgyvbunji wrote: post #3

He seems confused at the end why people think wayland is so slow, but don't you think it's because of his xwayland result? People were probably running x11 games on wayland and noticed that significant lag. Just a wild guess. Very nice article, wish people did actual measurements like this more often, of all sorts of things.

the statements of wayland being slow or not need a lot of context: what version of the game they played, the display server, the game settings, the display server settings, the monitor's feature set, the video card's feature set, the video card driver version, etc.

Re: Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

#182

Post by TheTon »

Aurornis wrote: post #44
cgyvbunji wrote: post #3

He seems confused at the end why people think wayland is so slow, but don't you think it's because of his xwayland result? People were probably running x11 games on wayland and noticed that significant lag. Just a wild guess. Very nice article, wish people did actual measurements like this more often, of all sorts of things.

> and noticed that significant lag Only xwayland showed that result. The difference was only a couple milliseconds. That’s in the range where I start to doubt that people are feeling the latency difference. If it was 10-20ms I could believe it, but not when it’s a couple milliseconds. The author of this post did a good job of getting all of the other confounding settings out of the way. It’s possible that the people…

I think the author’s use of a 500Hz display covers up or minimizes a lot of issues. It’s really easy to look at this data and say 8ms click to flash is fabulous even though he has an config that does 4ms.

A better way to interpret this data is to normalize by the vsync interval or the swap chain depth. The slowest config is 2 frames slower than the fastest. At 500Hz this is 4ms extra which is likely imperceptible to everyone but elite pro gamers. At 60Hz this is 34ms extra which is pretty noticeable to even casual gamers.

Re: Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

#183

Post by abhinavk »

admax88qqq wrote: post #94
marcinostefano wrote: post #86

Earlier quoted context omitted.

Why not for developers? You can install tools from flatpak or in home directory. My workflow includes toolbox containers. Distrobox is also good option.

mostly i'm trying to get out of the terminal and most IDEs don't understand devbox/distrobox well without lots of finagling.

I install the IDE as well as tools inside distrobox.

Re: Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

#184

Post by seba_dos1 »

9029 wrote: post #180
seba_dos1 wrote: post #12

There's no such thing as "Wayland input latency". It's just a word salad, akin to "HTTP animation smoothness". The post is measuring Xorg vs. KWin (and also XWayland), other implementations of either X11 or Wayland will have different characteristics. I wonder where the XWayland's added latency comes from though, it seems suspiciously high to just be easily hand-waved as overhead.

Another post suspects Nvidia drivers: https://davidjusto.com/articles/m2p-latency/#results

Oh yes, that makes a lot of sense.

Re: Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

#185

Post by seba_dos1 »

cwillu wrote: post #175
seba_dos1 wrote: post #125

Earlier quoted context omitted.

Is this some kind of Pavlov's dog reaction? That's not what my comment was about, and even if it was it wouldn't make any sense anyway as KWin had good results in these measurements.

It's exactly what your comment was about: the same boring motte and bailey fallacy of “you don't understand, wayland is a protocol” If your protocol you pushed to replace a working implementation invites a dozen poor implementations which people routinely confuse, that's a problem with the protocol and the push to get people to use it.

Looks like this pavlovian reaction is quite widespread. It's baffling how can you so confidently miss the point.

Re: Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

#186

Post by amlib »

michaelmrose wrote: post #149
amlib wrote: post #119

Earlier quoted context omitted.

> I tried to be an early adopter of wayland ~ 5 years ago. Found all sorts of things broken Yeah, because it wasn't ready. Pretty much no one recommended using it back them, if you thought it was ready you were either misguided or misled. It's time to put your skepticism aside and give it another try, there is a pretty good chance it's going to work great now. Even Valve Steam OS is now adopting it. It's a pretty goo…

People were declaring it ready in 2016 10 years ago and talking about how people needed to switch off the working "obsolete" X and switch ASAP to the broken wayland. It is completely counterfactual that "pretty much no one" was recommending it in 2021

Let's ignore this point of the discussion. For how long do you think users stayed on wayland back in 2016? The vast majority of users experience was... nothing because it wasn't even being shipped by 99% of distros yet, and if they cared to sought it they used it for 5 minutes until it crashed or even 0 minutes because it couldn't even display anything on their graphics card. Very few people actually experienced and tried to use wayland for real back then. Most of them were either devs or enthusiasts.

Fast forward to 2021 and most users experience with wayland was that GDM (on some distros) would try to start on wayland mode but couldn't for some reason and would fallback to X11. Note: I do think that the distros that were pushing for this were being reckless with their users. Introducing it as an opt-in would be much better and would still lower the barrier for testing. Also, KDE didn't even offer a wayland mode, taking until 2024 for it to start defaulting to it and any other wayland desktop had to be sought after by the user.

So really, I think people only started to "suffer" wayland's wonky-ness for the last three to five years depending how you view it. And honestly the last year or two has been pretty usable.

Re: Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

#187

Post by hoechst »

inigyou wrote: post #160
hoechst wrote: post #126

Earlier quoted context omitted.

Hello, this is my website and I do not know what you mean by this. If you give me technical details (like the subnet your operating out of), I can take a look at it. My webserver is using crowdsec ( https://www.crowdsec.net ) to ban malicious IPs and I would guess that you are somehow unintentionally affected by this. You can also test your IP by entering it into the crowdsec website to see if it is affected.

There you go then. Thank you for confirming my determination of IP blocking. The archive link above may work for the users you censor. Paying $1900/month for an IP address blocklist for a website? Yikes.

Yes, I am determined to shield my servers from malicious actors and bots that attempt to exploit it. This sometimes can lead to false positives and I am willing and cooperative in rectifying this to allow open access to real people that want to access the services I provide and make sure stuff like this won't happen again.

The security and availability of my servers is as important to me as the ability for anyone to access the public services I provide. Which is why I responded to you immediately and asked for your cooperation to help me fix the problem.

You not being cooperative helps no one. Not yourself, not other people with the same issue and not me who's trying to fix it.

Crowdsec is free btw, I do not pay anything.

Re: Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

#188

Post by wing-_-nuts »

yxhuvud wrote: post #176
wing-_-nuts wrote: post #81

Earlier quoted context omitted.

My biggest problem with wayland was how it was basically forced on the community. It broke innumerable things for years , put all the responsibility for implementing things down on the DEs and WMs themselves. All of this hassle, forcing so much more work on DE/WM devs, for the sake of 'better security' in scenarios that don't really apply to 99% of linux users, with the promise of 'better latency' which this very art…

Forced on who, by who? It is the DE/WM people that is driving the thing.

It is absolutely not the DE/WM devs driving this, it's the wayland folks saying that xorg would no longer be maintained. They literally just dumped an Ikea box of protocols on the table without even bothering to provide a decent sample implementation and said 'good luck!'

Re: Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

#189

Post by abhinavk »

inigyou wrote: post #160
hoechst wrote: post #126

Earlier quoted context omitted.

Hello, this is my website and I do not know what you mean by this. If you give me technical details (like the subnet your operating out of), I can take a look at it. My webserver is using crowdsec ( https://www.crowdsec.net ) to ban malicious IPs and I would guess that you are somehow unintentionally affected by this. You can also test your IP by entering it into the crowdsec website to see if it is affected.

There you go then. Thank you for confirming my determination of IP blocking. The archive link above may work for the users you censor. Paying $1900/month for an IP address blocklist for a website? Yikes.

That's the price of Enterprise/Business plan. He might be using the free community version.

Re: Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK

#190

Post by wing-_-nuts »

uecker wrote: post #130
wing-_-nuts wrote: post #81

Earlier quoted context omitted.

My biggest problem with wayland was how it was basically forced on the community. It broke innumerable things for years , put all the responsibility for implementing things down on the DEs and WMs themselves. All of this hassle, forcing so much more work on DE/WM devs, for the sake of 'better security' in scenarios that don't really apply to 99% of linux users, with the promise of 'better latency' which this very art…

And all the gaslighting. Using X forward basically every day but being told it is useless and broken and nobody needs it...

Yeah I used x forwarding to access matlab from my uni lab from the comfort of my own home, while all the other students had to slog to the lab lol
Post reply on HN