Think twice about Wayland. It breaks everything!

Wayland.md

Think twice before abandoning Xorg. Wayland breaks everything!

Hence, if you are interested in existing applications to "just work" without the need for adjustments, then you may be better off avoiding Wayland.

Wayland solves no issues I have but breaks almost everything I need. Even the most basic, most simple things (like xkill) - in this case with no obvious replacement. And usually it stays broken, because the Wayland folks mostly seem to care about Automotive, Gnome, maybe KDE - and alienating everyone else (e.g., people using just an X11 window manager or something like GNUstep) in the process.

Wayland proponents make it seem like Wayland is "the successor" of Xorg, when in fact it is not. It is merely an incompatible alternative, and not even one that has (nor wants to have) feature parity (missing features). And unlike X11 (the X Window System), Wayland protocol designers actively avoid the concept of "windows" (making up incomprehensible words like "xdg_toplevel" instead).

DO NOT USE A WAYLAND SESSION! Let Wayland not destroy everything and then have other people fix the damage it caused. Or force more Red Hat/Gnome components (glib, Portals, Pipewire) on everyone!

Please add more examples to the list.

Wayland seems to be made by people who do not care for existing software. They assume everyone is happy to either rewrite everything or to just use Gnome on Linux (rather than, say, twm with ROX Filer on NetBSD).

Edit: When I wrote the above, I didn't really realize what Wayland even was, I just noticed that some distributions (like Fedora) started pushing it onto me and things didn't work properly there. Today I realize that you can't "install Wayland", because unlike Xorg, there is not one "Wayland display server" but actually every desktop envrironment has its own. And maybe "the Wayland folks" don't "only care about Gnome", but then, any fix that is done in Gnome's Wayland implementation isn't automatically going to benefit all users of Wayland-based software, and possibly isn't even the implementation "the Wayland folks" would necessarily recommend.

Edit 12/2023: If something wants to replace X11 for desktop computers (such as professional Unix workstations), then it better support all needed features (and key concepts, like windows) for that use case. That people also have displays on their fridge doesn't matter the least bit in that context of discussion. Let's propose the missing Wayland protocols for full X11 feature parity.

Wayland is broken by design

• A crash in the window manager takes down all running applications
• You cannot run applications as root
• You cannot do a lot of things that you can do in Xorg by design
• There is not one /usr/bin/wayland display server application that is desktop environment agnostic and is used by everyone (unlike with Xorg)
• It offloads a lot of work to each and every window manager. As a result, the same basic features get implemented differently in different window managers, with different behaviors and bugs - so what works on desktop environment A does not necessarily work in desktop environment B (e.g., often you hear that something "works in Wayland", even though it only really works on Gnome and KDE, not in all Wayland implementations). This summarizes it very well: https://gitlab.freedesktop.org/wayland/wayland/-/issues/233

Apparently the Wayland project doesn't even want to be "X.org 2.0", and doesn't want to provide a commonly used implementation of a compositor that could be used by everyone: https://gitlab.freedesktop.org/wayland/wayland/-/issues/233. Yet this would imho be required if they want to make it into a worthwile "successor" that would have any chance of ever fixing the many Wayland issues at the core.

Wayland breaks screen recording applications

• MaartenBaert/ssr#431 ❌ broken since 24 Jan 2016, no resolution ("I guess they use a non-standard GNOME interface for this")
• https://github.com/mhsabbagh/green-recorder ❌ ("I am no longer interested in working with things like ffmpeg/wayland/GNOME's screencaster or solving the issues related to them or why they don't work")
• vkohaupt/vokoscreenNG#51 ❌ broken since at least 7 Mar 2020. ("I have now decided that there will be no Wayland support for the time being. Reason, there is no budget for it. Let's see how it looks in a year or two.") - This is the key problem. Wayland breaks everything and then expects others to fix the wreckage it caused on their own expense.
• obsproject/obs-studio#2471 ❌ broken since at least 7 Mar 2020. ("Wayland is unsupported at this time", "There isn't really something that can just be easily changed. Wayland provides no capture APIs")
• There is a workaround for OBS Studio that requires a obs-xdg-portal plugin (which is known to be Red Hat/Flatpak-centric, GNOME-centric, "perhaps" works with other desktops)
• phw/peek#1191 ❌ broken since 14 Jan 2023. Peek, a screen recording tool, has been abandoned by its developerdue to a number of technical challenges, mostly with Gtk and Wayland ("Many of these have to do with how Wayland changed the way applications are being handled")

As of February 2024, screen recording is still broken utterly on Wayland with the vast majority of tools. Proof

Workaround: Find a Wayland compositor that supports the wlr-screencopy-unstable-v1 protocol and use wf-recorder -a. The default compositor in Raspberry Pi OS (Wayfire) does, but the default compositor in Ubuntu doesn't. (That's the worst part of Wayland: Unlike with Xorg, it always depends on the particular Wayand compositor what works and what is broken. Is there even one that supports everything?)

Wayland breaks screen sharing applications

• jitsi/jitsi-meet#2350 ❌ broken since 3 Jan 2018
• jitsi/jitsi-meet#6389 ❌ broken since 24 Jan 2016 ("Closing since there is nothing we can do from the Jitsi Meet side.") See? Wayland breaks stuff and leaves application developers helpless and unable to fix the breakage, even if they wanted.

NOTE: As of November 2023, screen sharing in Chromium using Jitsi Meet is still utterly broken, both in Raspberry Pi OS Desktop, and in a KDE Plasma installation, albeit with different behavior. Note that Pipewire, Portals and whatnot are installed, and even with them it does not work.

• raspberrypi/bookworm-feedback#149 (comment) ❌ broken since at least Nov 17, 2023 ("window sharing not being available in wlroots derived compositors (such as wayfire)")
• flathub/us.zoom.Zoom#22 Zoom ❌ broken since at least 4 Jan 2019. ("Can not start share, we only support wayland on GNOME with Ubuntu (17, 18), Fedora (25 to 29), Debian 9, openSUSE Leap 15, Arch Linux"). No word about non-GNOME!
• https://community.zoom.com/t5/Meetings/Screensharing-only-works-on-GNOME-wayland-when-it-should-work-on/m-p/64823 Zoom ❌ Still broken as of 24 Jun 2022. ("... we only support Wayland on Gnome with Ubuntu 17 and above, Fedora 25 and above, Debian 9 and above ...")
• probonopd/Zoom.AppImage#8 ❌ broken since 1 Oct 2022 Zoom: "You need PulseAudio 1.0 and above to support audio share" on a system that uses pipewire-pulseaudio

Wayland breaks automation software

sudo pkg install py37-autokey

This is an X11 application, and as such will not function 100% on 
distributions that default to using Wayland instead of Xorg.

Wayland breaks Gnome-Global-AppMenu (global menus for Gnome)

• https://gitlab.com/lestcape/Gnome-Global-AppMenu/-/issues/116 ❌ broken since 24 Aug 2018 ("because the lack of the Gtk+ Wayland support for the Global Menu")

• https://bugs.kde.org/show_bug.cgi?id=424485 ❌ Still broken as of late 2023 ("I am also still not seeing GTK global menus on wayland. They appear on the applications themselves, wasting a lot of space.")

Wayland broke global menus with KDE platformplugin

• https://blog.broulik.de/2016/10/global-menus-returning/ ("it uses global window IDs, which don’t exist in a Wayland world... no global menu on Wayland, I thought, not without significant re-engineering effort"). KDE had to do additional work to work around it. And it still did not work:

• https://bugs.kde.org/show_bug.cgi?id=385880 ("When using the Plasma-Wayland session, the global menu does not work.")

Good news: According to this report global menus now work with KDE platformplugin as of 4/2022

Wayland breaks global menus with non-KDE Qt platformplugins

• https://blog.broulik.de/2016/10/global-menus-returning/ ❌ broke non-KDE platformplugins. As a result, global menus now need _KDE_NET_WM_APPMENU_OBJECT_PATH which only the KDE platformplugin sets, leaving everyone else in the dark

Wayland breaks AppImages that don't ship a special Wayland Qt plugin

• https://blog.martin-graesslin.com/blog/2018/03/unsetting-qt_qpa_platform-environment-variable-by-default/ ❌ broke AppImages that don't ship a special Wayland Qt plugin. "This affects proprietary applications, FLOSS applications bundled as appimages, FLOSS applications bundled as flatpaks and not distributed by KDE and even the Qt installer itself. In my opinion this is a showstopper for running a Wayland session." However, there is a workaround: "AppImages which ship just the XCB plugin will automatically fallback to running in xwayland mode" (see below).

Wayland breaks Redshift

• https://wiki.archlinux.org/index.php/redshift ❌ broken ("Redshift does not support Wayland since it offers no way to adjust the color temperature")

Update: Some Wayland compositors (such as Wayfire) now support wlr_gamma_control_unstable_v1, see https://github.com/WayfireWM/wayfire/wiki/Tutorial#configuring-wayfire and jonls/redshift#663. Does it work in all Wayland compositors though?

Wayland breaks global hotkeys

• albertlauncher/albert#309 ❌ broken since 7 Jan 2017 ("This is a security measure, but has the side effect of preventing applications from registering their own global hotkeys") YouTube video by René Rebe

Wayland does not work for Xfce?

See below.

Wayland does not work properly on NVidia hardware?

Apparently Wayland relies on nouveau drivers for NVidia hardware. The nouveau driver has been giving unsatisfactory performance since its inception. Even clicking on the application starter icon in Gnome results in a stuttery animation. Only the proprietary NVidia driver results in full performance.

See below.

Wayland does not work properly on Intel hardware

• https://cfenollosa.com/blog/fed-up-with-the-mac-i-spent-six-months-with-a-linux-laptop-the-grass-is-not-greener-on-the-other-side.html ❌ broken since at least 02 Apr 2021 ("Screen tearing with the intel driver. Come on. This was solved on xorg and now with Wayland it's back.")

Wayland prevents GUI applications from running as root

• https://bugzilla.redhat.com/show_bug.cgi?id=1274451 ❌ broken since 22 Oct 2015 ("No this will only fix sudo for X11 applications. Running GUI code as root is still a bad idea." I absolutely detest it when software tries to prevent me from doing what some developer thinks is "a bad idea" but did not consider my use case, e.g., running truss for debugging on FreeBSD needs to run the application as root. https://bugzilla.mozilla.org/show_bug.cgi?id=1323302 suggests it is not possible: "These sorts of security considerations are very much the way that "the Linux desktop" is going these days".)

Suggested solution

Wayland is biased toward Linux and breaks BSD

• https://blog.netbsd.org/tnf/entry/wayland_on_netbsd_trials_and ❌ broken since 28 Sep 2020 ("Wayland is written with the assumption of Linux to the extent that every client application tends to #include <linux/input.h> because Wayland's designers didn't see the need to define a OS-neutral way to get mouse button IDs. (...) In general, Wayland is moving away from the modularity, portability, and standardization of the X server. (...) I've decided to take a break from this, since it's a fairly huge undertaking and uphill battle. Right now, X11 combined with a compositor like picom or xcompmgr is the more mature option."

Wayland complicates server-side window decorations

• https://blog.martin-graesslin.com/blog/2018/01/server-side-decorations-and-wayland/ ❌ FUD since at least 27 January 2018 ("I heard that GNOME is currently trying to lobby for all applications implementing client-side decorations. One of the arguments seems to be that CSD is a must on Wayland. " ... "I’m burnt from it and are not interested in it any more.") Server-side window decorations are what make the title bar and buttons of all windows on a system consistent. They are a must have_ for a consistent system, so that applications written e.g., Gtk will not look entirely alien on e.g., a Qt based desktop, and to enforce that developers cannot place random controls into window titles where they do not belong. Client-side decorations, on the other hand, are destroying uniformity and consistency, put additional burden on application and toolkit developers, and allow e.g., GNOME developers to put random controls (that do not belong there) into window titles (like buttons), hence making it more difficult to achieve a uniform look and feel for all applications regardless of the toolkit being used.

Wayland breaks windows rasing/activating themselves

• https://phabricator.kde.org/D16648#470609 ("Wayland clients can't raise or activate themselves"), ❌ broken since May 27 2019

Wayland breaks RescueTime

• https://help.rescuetime.com/article/117-common-linux-issues ("One of the features of Wayland is that it prevents apps from doing precisely what RescueTime is trying to do—track activity in other windows.") ❌ broken since June 3, 2021

Wayland breaks window managers

Apparently Wayland (at least as implemented in KWin) does not respect EWMH protocols, and breaks other command line tools like wmctrl, xrandr, xprop, etc. Please see the discussion below for details.

Wayland requires JWM, TWM, XDM, IceWM,... to reimplement Xorg-like functionality

• https://gitlab.freedesktop.org/wayland/wayland/-/issues/233

• Screen recording and casting
• Querying of the mouse position, keyboard LED state, active window position or name, moving windows (xdotool, wmctrl)
• Global shortcuts
• System tray
• Input Method support/editor (IME)
• Graphical settings management (i.e. tools like xranrd)
• Fast user switching/multiple graphical sessions
• Session configuration including but not limited to 1) input devices 2) monitors configuration including refresh rate / resolution / scaling / rotation and power saving 3) global shortcuts
• HDR/deep color support
• VRR (variable refresh rate)
• Disabling input devices (xinput alternative)

As it currently stands minor WMs and DEs do not even intend to support Wayland given the sheer complexity of writing all the code required to support the above features. You do not expect JWM, TWM, XDM or even IceWM developers to implement all the featured outlined in ^1.

Wayland breaks _NET_WM_STATE_SKIP_TASKBAR protocol

• https://github.comelectron/electron#33226 ("skipTaskbar has no effect on Wayland. Currently Electron uses _NET_WM_STATE_SKIP_TASKBAR to tell the WM to hide an app from the taskbar, and this works fine on X11 but there's no equivalent mechanism in Wayland." Workarounds are only available for some desktops including GNOME and KDE Plasma.) ❌ broken since March 10, 2022

Wayland breaks NoMachine NX

• https://kb.nomachine.com/TR03S10126?s=wayland ❌ broken since 2021-03-09 ("The session becomes unresponsive once logged-in to the Wayland desktop")

Wayland breaks xclip

xclip is a command line utility that is designed to run on any system with an X11 implementation. It provides an interface to X selections ("the clipboard"). Apparently Wayland isn't compatible to the X11 clipboard either.

• AppImage/AppImageKit#1221 (comment) ❌ broken since 2022-20-15 ("Espanso built for X11 will not work on Wayland due to xclip. Wayland asks for wl-copy")

This is another example that the Wayland requires everyone to change components and take on additional work just because Wayland is incompatible to what we had working for all those years.

Wayland breaks SUDO_ASKPASS

• https://github.com/linuxhw/hw-probe-pyqt5-gui/commit/eb2d6e5145fb8571414bda57676084b7f13b94e5#diff-23cb15995f1502beebb38433bfa83204a5f45b376eaf88e2e41a0d8a1cd44722R290 ❌ broken since 2022-04-09 ("SUDO_ASKPASS doesn't work on Wayland currently, so piping the password")

Wayland breaks X11 atoms

X11 atoms can be used to store information on windows. For example, a file manager might store the path that the window represents in an X11 atom, so that it (and other applications) can know for which paths there are open file manager windows. Wayland is not compatible to X11 atoms, resulting in all software that relies on them to be broken until specifically ported to Wayland (which, in the case of legacy software, may well be never).

Possible workaround (to be verified): Use the (Qt proprietary?) Extended Surface Wayland protocol casually mentioned in https://blog.broulik.de/2016/10/global-menus-returning/ "which allows you to set (and read?) arbitrary properties on a window". Is it the set_generic_property from https://github.com/qt/qtwayland/blob/dev/src/extensions/surface-extension.xml?

Wayland breaks games

Games are developed for X11. And if you run a game on Wayland, performance is subpar due to things like forced vsync. Only recently, some Wayland implementations (like KDE KWin) let you disable that.

Wayland breaks xdotool

(Details to be added; apparently no 1:1 drop-in replacement available?)

Wayland breaks xkill

xkill (which I use on a regular basis) does not work with Wayland applications.

What is the equivalent for Wayland applications?

Wayland breaks screensavers

Is it true that Wayland also breaks screensavers? https://www.jwz.org/blog/2023/09/wayland-and-screen-savers/

Wayland breaks setting the window position

Other platforms (Windows, Mac, other destop environments) can set the window position on the screen, so all cross-platform toolkits and applications expect to do the same on Wayland, but Wayland can't (doesn't want to) do it.

• PCSX2/pcsx2#10179 PCX2 (Playstation 2 Emulator) ❌ broken since 2023-10-25 ("Disables Wayland, it's super broken/buggy in basically every scenario. KDE isn't too buggy, GNOME is a complete disaster.")

Wayland breaks color mangement

Apparently color management as of 2023 (well over a decade of Wayland development) is still in the early "thinking" stage, all the while Wayland is already being pushed on people as if it was a "X11 successor".

https://gitlab.freedesktop.org/pq/color-and-hdr/-/blob/main/doc/color-management-model.md

Wayland breaks DRM leasing

According to Valve, "DRM leasing is the process which allows SteamVR to take control of your VR headset's display in order to present low-latency VR content".

• "Unfortunately not all Wayland compositors support DRM leasing" https://help.steampowered.com/en/faqs/view/18A4-1E10-8A94-3DDA - "not all" highlights one of the fundamental problems with Wayland - there is fragmentation

Wayland breaks In-home Streaming

• ValveSoftware/steam-for-linux#6148 ❌ broken since 2019-03-17

Wayland breaks NetWM

Extended Window Manager Hints, a.k.a. NetWM, is an X Window System standard for the communication between window managers and applications

Wayland breaks window icons

• Wayland breaks window icons when no .desktop files are used: Seemingly Wayland requires developers to use the xdg-shell protocol, which in turn requires developers to use reverse-DNS application IDs and set_app_id, which causes the icon to be loaded from the .desktop file. This is serious breakage, as not all desktop environments (for good reasons) use .desktop files. A display server should have no business in this, as this belongs into the domain of the desktop environment. https://community.kde.org/Guidelines_and_HOWTOs/Wayland_Porting_Notes#Application_Icon, https://gitlab.freedesktop.org/wayland/wayland-protocols/-/issues/52 ❌ broken since 2021-06-21

• Qt setWindowIcon has no effect on KDE/Wayland https://bugreports.qt.io/browse/QTBUG-101427 ("Resolution: Out of scope", meaning it cannot be fixed in Qt, "Using QT_QPA_PLATFORM=xcb works, though", meaning that if you disable Wayland then it works) ❌ broken since 2022-03-03

• LibrePCB developer: "Btw it's just one of several problems we have with Wayland, therefore we still enforce LibrePCB to run with XWayland. It's a shame, but I feel totally helpless against such decisions made by Wayland and using XWayland is the only reasonable option (which even works perfectly fine)..." https://gitlab.freedesktop.org/wayland/wayland-protocols/-/issues/52#note_2155885

Wayland breaks drag and drop

• On Raspberry Pi OS (which is running a Wayland session by default), dragging a file out of a zip file onto the desktop fails with "XDirectSave failed."
• The same seems to be true in Gnome: https://discourse.gnome.org/t/xdnddirectsave-and-wayland/2954

Workarounds

• Users: Refuse to use Wayland sessions. Uninstall desktop environments/Linux distributions that only ship Wayland sessions. Avoid Wayland-only applications (such as PreSonus Studio One) (potential workaround: run in https://github.com/cage-kiosk/cage)
• Application developers: Enforce running applications on X11/XWayland (like LibrePCB does as of 11/2023)

Examples of Wayland being forced on users

This is exactly the kind of behavior this gist seeks to prevent.

• Asahi Linux enforces Wayland for ARM-based Macs: https://social.treehouse.systems/@marcan/110354541574112092
• Fedora enforces Wayland for KDE Plasma: https://fedoraproject.org/wiki/Changes/KDE_Plasma_6#Why_drop_the_X11_session_with_the_Plasma_6_upgrade?
• Red Hat enforces Wayland for RHEL:https://www.redhat.com/de/blog/rhel-10-plans-wayland-and-xorg-server

References

• Dudemanguy's Musings, Wayland Isn't Going to Save The Linux Desktop
• Chris Titus Tech: Wayland vs Xorg https://www.youtube.com/watch?v=U_MBJcD3SFI
• tildearrow: did somebody say "anti-Wayland horseshit"?
• pcsx2: CI/Linux: Disable Wayland and spring cleaning
• Testing SCREEN RECORDERS on Linux Mint Wayland

BTW, mobile is not entirely locked down. Certain specific Android devices with unlockable bootloaders can be reflashed with alternative operating systems. You decide what OS you want to run, then get a compatable device. Not great, but enough to break out of the locked "customer experience."

How can you get a reasonable security/privacy experience with a rooted phone the way it is now setup? OSs like Graphene say letting the user have full filesystem access and root-of-trust "defeats the purpose" of their OS. So there's no straight forwards way to have your cake and eat it anymore like there almost was with phones like the Nokia N900.

you might be locked in by an app you use, as google does not allow some of their apis to be used on open systems

Nothing wrong with getting locked into a specific proprietary app you use, but making it so the only decent way to use these apps you have to give up easy access to your entire device (including updates to some degree) seems to qualify.

Graphene is the OS of choice for those facing state level or other high capability attackers. For a rooted system to allow arbitrary changes you'd use something else. To have both, you'd need something where you set up the image on your desktop, sign it there if you will be using secure boot with custom keys (as Graphene does) , and then add those keys to the phone over USB and flash your modified image to the phone. You have root when and only when the image is on your desktop, in a controlled environment in this scenario. If you need su, add it while the OS image is mounted on the desktop and before signing it, but be aware this does make attacks on the phone easier. You might need it for say, a system level adblocker that doesn't tie up the VPN interface as Tracker Control does.

As for apps that don't work on open devices, those can be either quarantined to a separate phone tethered to your main phone, or not used at all. For instance, banking apps won't work on anything I own, but I don't trust online banking anyway so that doesn't matter. No banking apps on any device I own. Note that I do not allow Google Play Services (or anything that depends on it) on my phones, which closes 90% of the privacy busting attack surface. I use F-droid, note that the Google Play Store is useless without an account anyway, and I refuse to have a Google account.

A computer (ANY computer) can only be trusted by at most one party. Any application that requires a computer to be trusted by Google, by a bank, by Hollywood etc means that computer can no longer be trusted by you and should not be used to handle sensitive information. When they ban rooted/modded/open phones, they demand you use a device they can trust as opposed to one you can trust. Never can both you and they trust the same device as these businesss regard their users as adversaries.

Banking is a special case due to the severity of damage an attacker can do, for that purpose best practices may be to trust nothing save the bank's own ATMs, for it's a lot easier to make them pay if a skimmer gets put on their ATM (under the nose of their own cameras) than to get your money back if a "banker" worm on your phone or desktop (or a phishing attack) gets your creds and empties your account. In other words, banking may be a case of neither you nor the bank can trust the computer.

You might need it for say, a system level adblocker that doesn't tie up the VPN interface as Tracker Control does.

Use DNS level adblocking, it's literally a stock Android feature (Settings > Network > Private DNS) that I don't know why more people don't use.

google does not allow some of their apis to be used on open systems

Specifically Google Pay won't work on GrapheneOS. Anyways, is this thread not about user choice? Why consider subduing oneself to Google when everybody is mad at Wayland for supposedly suppressing user choice? Just use cash if you care about privacy, and a credit card if you don't.

On the topic of Wayland usability and X parity: I've gotten KDE's Wayland to work flawlessly on a laptop with an NVidia card, including gaming and even screensharing via Teams (which uses either Electron or an embedded Chromium browser). If green team laptop hardware and M$ software can cooperate with Wayland well enough for it to become my daily driver, I guess I don't get the vitriol towards Wayland. Granted I am not a GUI developer, but as a user I can't see the issue

Xorg is my go-to for flexibility. I mean, you can tweak just about everything with it. It's got this UNIX philosophy vibe going on, keeping things simple and modular.

But then there's Wayland. Now, don't get me wrong, it's got some cool stuff, especially for specialized devices. But here's where it starts to lose me: it feels like Wayland's going against the whole UNIX philosophy. It's trying to be this monolithic thing (compositor), kinda like a Windows vibe, which is weird for the UNIX world. The lack of a base library or display server in Wayland means that fixes or improvements made in one compositor won't necessarily translate to others. It's like each compositor is doing its own thing.

The folks behind Wayland are also the ones behind Flatpak, right? It seems they're not too bothered about code duplication, which is a bit concerning. I mean, it reminds me a lot of the Windows ecosystem.

It's got this UNIX philosophy vibe going on, keeping things simple and modular.

Seems to me that is what Wayland aims to do. But if you search for the "Unix filosophy" Wikipedia page, it states that this means doing one thing and doing it right. Ask actual X.org devs and they will tell you it's the opposite.

I mean, the X.org server initially included a print server, talk about keeping things simple (yes they scrapped that for obvious reasons).

From an engineering (and funding) standpoint, X can't be maintained

I would never use something like Google Pay. One of the reasons is that there are those who want your phone to be tied to you by a government ID, to BE your government ID,and also be your only way of making payments so as to render private transactions impossible save for barter. Google Pay is fundamentally incompatable with the idea of deniable ownership of a prepaid phone.

The folks behind Wayland are also the ones behind Flatpak, right? It seems they're not too bothered about code duplication, which is a bit concerning. I mean, it reminds me a lot of the Windows ecosystem.

That's design by committee for ya.

The lack of a base library or display server in Wayland means that fixes or improvements made in one compositor won't necessarily translate to others. It's like each compositor is doing its own thing.

That was swiftly rejected: https://gitlab.freedesktop.org/wayland/wayland/-/issues/233

And now we have three libraries:

• libweston
• wlroots
• Louvre

Two major implementations not using them:

• Mutter
• Kwin

And then a ton of minor WMs. Essentially it's a zoo. And God forbid you use anything but KWin/Mutter. Everything else is just woefully incomplete.

I think its quite funny how some people always scream "but its about choice" and when they then have a choice they scream "but its a zoo".

I think its quite funny how some people always scream "but its about choice" and when they then have a choice they scream "but its a zoo".

Some things need to just work without multiple implementations. You don't have multiple display servers in Windows, MacOS, iOS, Android or ChromeOS. The choice proponents would instantly say that those OSes don't have multiple desktop environments either, and that's not true, as no one stops you from creating one for Windows and MacOS, Android has a metric ton of "launchers", and ChomeOS is an Internet OS, so it's just irrelevant. And Windows indeed has several third-party desktop environments, only they are relatively unknown. And I have zero clue how multiple inferior Wayland implementations would even help anyone.

The display server is such a core low-level OS thing, it makes zero sense to waste resources reimplementing it over and over again. In Linux somehow we have a single kernel, a single C library (yeah, there's MUSL but it's mostly for embedded devices), a single font rendering library (freetype which still sucks ass vs. ClearType v2), a metric ton of singular implementations and no one has cried foul about that. Complexity is a bitch you have to deal with.

No one also cried foul about a single X11 implementation (for all intents and purposes Linux distros always came with a single Xorg server, be it XFree86 or Xorg later on) until people decided they needed something more modern and yeah, X11 has a number of glaring issues which couldn't have been resolved without breaking compatibility with the protocol.

That was swiftly rejected: https://gitlab.freedesktop.org/wayland/wayland/-/issues/233

It's disappointing to see the discussion closed without thorough consideration. Rejection doesn't automatically mean it's the best choice or reflects the community's view.

IMHO they should have made screen recording a priority, I cannot share my screen in all meeting apps, and I have to constantly defend why I use Linux when it doesn't allow me to share screens, it's almost as if I am using a calculator for development and trying to justify it as ideal for my workflow

It's almost as if we went back twenty years when there was no screen recording and were lucky to get something to even show up on the screen

You can use wl-sunset instead of redshif.

also wf-recorder can do screencapture instead of ffmpeg.

I've been trying wayland, for a couple months, i do not recommend it unless you are a power user with way too much time on your hands. Even then, the time would proabbly be better spent elsewhere.

How is this not insanely revealing and the best reason to boycott Wayland ever? https://www.reddit.com/r/linux/comments/1bzna16/hyprland_creator_vaxry_is_now_banned_from/ We should stop acting like we're not in the majority here. Not the majority of corporate and political power, but the majority of sane and competent contributors and users. We're catching this quite early on... If you think they won't increase the ideological policing and leveraging their power over you when they're the only game in town, then you've got another thing coming!

It is, they're literally banning developers (and vaxry is imo one of the best ones) from contributing to wayland and wlroots over political nonsense because someone (who is not the developer) said something on discord a few years ago and that is somehow the developers fault and a good reason to ban him from their gitlab.

It's like the wayland devs actually want wayland to suck, it's like they always wanted it to suck, I'm not even surprised to say that the wayland devs want it to suck, i mean look at the bloody thing, it sucks by design! And everyone even knows it.

That's hyprland, not Wayland. Hyprland is CoC cuckery.

That's hyprland, not Wayland. Hyprland is CoC cuckery.

I find it very interesting that in reality the Freedesktop and by proxy Wayland exactly insist on their "code of conducts", wield that like a weapon and impose these onto other people who have nothing to do with them.

It's also very interesting that the circle of people who so rabidly are defending and promoting Wayland (also trying by force) is overlapping really heavily with the GNOME people. Many of these people also have very strong opinions in other topics which they don't shy away to declare that their way of thinking is the one true way and everyone else is a heretic for not exactly aligning with them and must be purged.

They also like to throw things at other people at their heads they are doing themselves or like doing themselves.

I don't mind Wayland, but it is not usable for me and I really dislike people promote that like a religion.

In technical debate the word "cuck" should be avoided: it reeks of Gamergate and the "manosphere" misogynists

and I really dislike people promote that like a religion.

That I can agree with. And it works both ways:

DO NOT USE A WAYLAND SESSION! Let Wayland not destroy everything and then have other people fix the damage it caused. Or force more Red Hat/Gnome components (glib, Portals, Pipewire) on everyone!

IMHO use whatever floats your boat and contribute to projects that share your vision. Otherwise you just come across as some whiny kid. This is FOSS after all, nobody owes you anything.

In technical debate the word "cuck" should be avoided: it reeks of Gamergate and the "manosphere" misogynists

What do you mean? Misogynist is a compliment these days.

Misogynist is NOT a compliment-and I utterly dispise Gamergate, Qanon, and the rest of that fascist SHIT.

Misogynist is NOT a compliment-and I utterly dispise Gamergate, Qanon, and the rest of that fascist SHIT.

Schizoposting? What do any of the words you just typed mean?

Let me make this crystal clear: hating women is NOT acceptable, not now, not ever. No other part of the agenda of creeps like Trump is acceptable to me either.

and I really dislike people promote that like a religion.

That I can agree with. And it works both ways:

DO NOT USE A WAYLAND SESSION! Let Wayland not destroy everything and then have other people fix the damage it caused. Or force more Red Hat/Gnome components (glib, Portals, Pipewire) on everyone!

IMHO use whatever floats your boat and contribute to projects that share your vision. Otherwise you just come across as some whiny kid. This is FOSS after all, nobody owes you anything.

Why would you criticize someone who is warning people who don't understand such thing? The brave person who highlighted the problem with Wayland serves those who struggle to find there way through problems created by something thought to be good thing. I wish I had been able to read this information a year ago, it would have saved me a months worth of head aches.

A warning would be something like "Your wayland session may have the following issues, if you can't accept that or are not comfortable investing time to work around them you may want to keep using the X11 session instead.".

Let Wayland not destroy everything and then have other people fix the damage it caused.

Sounds very different.

Let me make this crystal clear: hating women is NOT acceptable, not now, not ever.

no one here said that is was okay

I have been following this thread for over a year and I am still confused as to how we ended up with Wayland. I like analogies so here is one to express my confusion. We had a ship. It was an large old ship. Whether you liked or disliked the ship, you knew how big it was, how to steer it, provision it, sail on it, etc. It was a known quantity. One day, the operators of the ship decided they needed a new ship. They said they did not want a replacement for the old ship, just a new ship. Oh, and by the way the operators were also going to take the old ship out of service. Eventually, the ship builders delivered the new ship. However, what the ship operator received from the ship builders was a diesel engine, a propeller, and a rudder. When the operator asked about the hull and other parts of the ship, they were told by the builders that they had to create those items themselves. Because the operators were not ship builders, this lead to the construction of a very odd ship, full of quirks, missing features, and confusion for passengers who were not accustomed to the novel idiosyncrasies of the new ship.

So please help me understand why, rather than create a full featured replacement for X Window that directly addressed its shortcomings, we ended up with something replacing it that is explicitly not a replacement for it and decentralizes the implementation of key functionality. What I have heard over the year feels like attempts to rationalize the decisions made for Wayland. My interest in this is not just as a developer who relies on X Window features, but as a decades long user and believer in Linux, who is concerned that fragmentation of such core capabilities will hurt the platform.

Your analogy isn't perfect. What is missing is that the old ship can be duplicated many times within seconds and you can put a new crew on each of the duplicated old ships.

Regarding why wayland doesn't offer "all the features" I think it boils down to:

1. xorg didn't offer all the features from the start either, they were added over a long period of time. Writing a completely fully-featured new system from scratch is just not feasible and even if it were, there are just too many potential use-cases to cover that might even contradict themselves.
2. The wayland-protocols members have a very strict view on some things and prefer enabling use-cases rather than generic features that can be used in bazillion different ways. Add to that that the whole accepting-a-protocol process is *slooow*.
3. There is also xwayland support in almost every wayland compositor so running (most) X11 applications should not be an issue. This might remove some incentives to support something in a wayland protocol because there exists this fallback path.

@Consolatis Thank you for the quick and thoughtful reply.

xorg didn't offer all the features from the start either, they were added over a long period of time. Writing a completely fully-featured new system from scratch is just not feasible and even if it were, there are just too many potential use-cases to cover that might even contradict themselves.

I'm sick of reading this nonsense. Wayland has been flawed since day one. No amount of time will fix it, because the architecture is just bad.

The wayland-protocols members have a very strict view on some things and prefer enabling use-cases rather than generic features that can be used in bazillion different ways. Add to that that the whole accepting-a-protocol process is slooow.

Okay, everyone's already realized that Wayland-CСP are jerks. Where the fck is the library with all the display server features? Where the fck is it?

There is also xwayland support in almost every wayland compositor so running (most) X11 applications should not be an issue. This might remove some incentives to support something in a wayland protocol because there exists this fallback path.

Stop lying, XWayland won't run half of the applications, and those that it does run, run with limitations.

xorg didn't offer all the features from the start either, they were added over a long period of time. Writing a completely fully-featured new system from scratch is just not feasible and even if it were, there are just too many potential use-cases to cover that might even contradict themselves.

Yeah, Xorg was made in a different time when tech was way simpler. Hardware and software were way less advanced back then. Also, for something trying to replace Xorg and being the standard for many Linux distros, it can't start off incomplete like that. Wayland should've come out stronger right from the start if it wants to be the go-to choice for everyone.

Yeah, Xorg was made in a different time when tech was way simpler. Hardware and software were way less advanced back then.

The hardware and software remains exactly the same. All that has changed is mostly hardware performance.

Yeah, Xorg was made in a different time when tech was way simpler. Hardware and software were way less advanced back then.

The hardware and software remains exactly the same. All that has changed is mostly hardware performance.

Really? Did we have DRI back in the '80s? Over the years, Xorg got a bunch of extensions like Xinerama, RANDR, and more to tackle current issues. Saying Xorg was "incomplete" from the start isn't an excuse for Wayland's limitations. It aims to replace what Xorg does now, not what Xorg did decades ago.

@gustavosbarreto

Really? Did we have DRI back in the '80s? Over the years, Xorg got a bunch of extensions like Xinerama, RANDR, and more to tackle current issues.

These are improvements regarding the graphical stack that followed the development of hardware. Wayland has not invented anything new. It's just some stupid desire to "be different" for the sake of showing off or something like that.

No one back then even seriously thought of making a bunch of incompatible graphical servers with different protocols for each DE. This option has always been unsustainable.

Saying Xorg was "incomplete" from the start isn't an excuse for Wayland's limitations. It aims to replace what Xorg does now, not what Xorg did decades ago.

Absolutely agree, all the developers had to do was make an improved version of X11 and Xserver without reinventing the wheel. Either that or nothing at all.

Wayland, however, is a complete deception. First it was that Wayland was "X12", then Wayland was just a replacement for X11/Xorg. Now its fanatics are giving up and promoting it as "an incompatible modern alternative that must destroy everything before it, because the old must die. Why? Because we can."

I'm sick of reading this nonsense. Wayland has been flawed since day one. No amount of time will fix it, because the architecture is just bad.

okay @Monsterovich so you have made this claim are you able to prove it? (this is not a gotcha i would like to know)

Wayland, however, is a complete deception. First it was that Wayland was "X12", then Wayland was just a replacement for X11/Xorg. Now its fanatics are giving up and promoting it as "an incompatible modern alternative that must destroy everything before it, because the old must die. Why? Because we can."

The more I read about Wayland the more I get the impression what started as a technical issue is now rooted in ideology, almost like a social engineering op.

@Consolatis

xorg didn't offer all the features from the start either, they were added over a long period of time. Writing a completely fully-featured new system from scratch is just not feasible and even if it were, there are just too many potential use-cases to cover that might even contradict themselves.

@gustavosbarreto

Really? Did we have DRI back in the '80s? Over the years, Xorg got a bunch of extensions like Xinerama, RANDR, and more to tackle current issues. Saying Xorg was "incomplete" from the start isn't an excuse for Wayland's limitations. It aims to replace what Xorg does now, not what Xorg did decades ago.

This is a garbage reply/counter-argument.

The XFree86/Xorg server later on offered the same featureset for all its users. At no time people dealt with different levels of implementation of X11 on Linux.

This is exactly the case with Wayland. Multiple Wayland protocols are not mandatory, and the experience and features that you're getting with compositor X for Wayland could be radically different from compositor Y.

The wayland-protocols members have a very strict view on some things and prefer enabling use-cases rather than generic features that can be used in bazillion different ways. Add to that that the whole accepting-a-protocol process is slooow.

Desktop users need none of this shit. Wayland was promised to be a better X11/Xorg out of the box. It's still not by a long shot. Microsoft replaced the entire graphics stack in Vista (and moved it into user space for good measure) and even low-level Windows XP and earlier applications continued to work just fine. Some very rare applications broke, e.g. those that hooked into low-level Windows features with no public APIs, e.g. WindowBlinds, but those worked against Microsoft's will and guidelines. There's no concept of private APIs in Linux.

There is also xwayland support in almost every wayland compositor so running (most) X11 applications should not be an issue. This might remove some incentives to support something in a wayland protocol because there exists this fallback path.

Another garbage reply. XWayland is good only for running basic single-window applications because everything else is broken.

@baron1405

Your analogy is almost perfect, except you were talking about this:

However, what the ship operator received from the ship builders was a diesel engine, a propeller, and a rudder.

No, they didn't receive even that. They received blueprints for certain parts of the new ship. And those blueprints were quite vague as to whether you needed to be put them in place or not, thus we now have multiple ships, some of which are missing toilets, others are missing hallways or kitchen, others have no poles, etc. etc. etc.

And now we have multiple ships where only few selected come with all the amenities but it's claimed that they are all better than the old clunky ship.

Wayland is just a spec where x11 is a spec and implementation

I'm sick of reading this nonsense. Wayland has been flawed since day one. No amount of time will fix it, because the architecture is just bad.

okay @Monsterovich so you have made this claim are you able to prove it? (this is not a gotcha i would like to know)

I (and others) in this thread have already written thousands of proofs that Wayland is flawed, and I already post in circles sometimes.

@zarlo

Wayland is just a spec where x11 is a spec and implementation

The fact that Wayland is just a spec (and every DE has their own) is VERY BAD. The reason for this is fragmentation.

Wayland is just a spec where x11 is a spec and implementation

Well. X11 is the spec and Xorg is just one of multiple implementations, but the one practically everyone is using on the *nix desktop.

Contrast this with Wayland where not even Gnome and KDE use the same implementation, and hence are broken in different ways (as in: different features supported, different bugs).

... not even Gnome and KDE use the same implementation, and hence are broken in different ways (as in: different features supported, different bugs).

I think we'll see the free market take care of what features make it in as things progress. It shouldn't have taken this long, however.

Wayland, however, is a complete deception. First it was that Wayland was "X12", then Wayland was just a replacement for X11/Xorg. Now its fanatics are giving up and promoting it as "an incompatible modern alternative that must destroy everything before it, because the old must die. Why? Because we can."

The more I read about Wayland the more I get the impression what started as a technical issue is now rooted in ideology, almost like a social engineering op.

100%

Use DNS level adblocking, it's literally a stock Android feature (Settings > Network > Private DNS) that I don't know why more people don't use.

That isn't a solution when you realize how few adverts it can block versus ublock.

The folks behind Wayland are also the ones behind Flatpak, right?

Don't you want to be part of their wonderful utopia? Wayland + systemD + flatpak + ... secure boot with Google/Intel/AMD/Apple at the root-of-trust. Being able to enforce DRM (amongst other things) onto everyone will give us all a century of the Linux Desktop! Utopia!

Don't you want to be part of their wonderful utopia? Wayland + systemD + flatpak + ... secure boot with Google/Intel/AMD/Apple at the root-of-trust

I bet if you repeat the same strawman slop 100 more times it'll eventually be funny.

import gi

gi.require_version("Gtk", "3.0")
from gi.repository import Gtk, Gdk

offset_x = 0
offset_y = 0

def press(widget, event):
    global offset_x, offset_y
    offset_x = event.x
    offset_y = event.y

def move(widget, event):
    win.move(event.x_root - offset_x, event.y_root - offset_y)

win = Gtk.Window()
win.connect("destroy", Gtk.main_quit)
win.connect("button-press-event", press)
win.connect("motion-notify-event", move)
win.set_events(Gdk.EventMask.BUTTON1_MOTION_MASK|Gdk.EventMask.KEY_PRESS_MASK)
win.show_all()
Gtk.main()

xdecor1.mp4

If someone promoted something like libdecor for any X clients decades ago, we wouldn't need window managers for X.Org in the first place.

BTW, found this in Xnest logs: http://selinuxproject.org/page/NB_XWIN

You don't need a ship at all if all you need in reality is a bunch of boats.

https://en.wikipedia.org/wiki/Cossack_raid_on_Istanbul_(1615)

But ship lovers keep assuring you need a full-fledged ship to win.

That is some very weird example for you to pick. Movement of windows should belong to the user (e.g. the compositor) rather than to random applications. Anyway, running it with GDK_BACKEND=x11 (and thus via xwayland) magically makes it work for me.

That is some very weird example for you to pick

Wayland haters criticize Red Hat, GOOME or whatever for attempting to push libdecor onto everyone and enforce all the Wayland clients to support CSD, instead of accepting that every compositor should support SSD as an option and not mandate simplistic clients to support CSD, regardless of the Wayland spec.

My point is to demonstrate that X clients can in fact support CSD too, and talk to the X server directly instead of relying on some window manager to draw decorations for them and to provide ability to move and resize their windows. So if they massively did, it wouldn't be crucial to also run some window manager along with X.Org.

A decade ago, I already was willing to ditch any window managers and only use pure X.Org and small UNIX-way utilities to manage the windows. But discovered that such tools don't work without any WM at all somehow (and only years later discovered the reason: that they actually talk not to X.Org but to a WM via EWMH, and it does not even work with any WM). I was highly frustrated that if I kill a WM, X clients become totally helpless, I couldn't even change their z-order, not even focus them if I have X-Mouse disabled. Some simpler apps had CLI flags or other means to specify their initial geometry, but more normie things like browsers just launched their windows with some default geometry, not even occupying the whole screen by default as I wished.

Oh, I just checked that GTK+3 CSD apps in fact support window manipulations with pure X server and no WM too. So I did not even need to write an artificial example, hehe. Just the maximize button doesn't work (it probably works via EWMH on X11 as well).

Instead of the quirky conception of struts, I would implement the non-fullscreen maximization in a way where every window advertises its geometry to others, and tells if it allows collisions or not. Something like it happens in game engines (2D or 3D, doesn't matter). X clients would then, when changing their window geometries, query all the other windows and check if there is any room for them. Just like when you join some Minecraft server and look for an unoccupied area for your buildings lol.

How is it better than struts? Panels may occupy not the whole screen side, but only a part. Thus some space around remains, where a wallpaper can be usually seen through. There's no reason non-maximized window cannot occupy this space, but that's exactly how struts work! It would also provide a simple way to avoid physical notches: just put a dummy non-colliding window there.

Oh, and of course, if some non-colliding window appears, or changes its geometry, it should send a «посунься!!!» signal to other windows, just in the case they already occupy some space where it is supposed to appear. It could even query their geometries first and send such a signal only to those who actually occupy some space there, neat? Just make sure to avoid race conditions… somehow… transactions? And to manage conflicts, like what if two non-colliding windows claim overlapping regions the same time, what would happen?

Sounds like fun to implement in every single application. And if the application doesn't implement it you can't move the window at all as a user. Doesn't sound that great to me. Not even starting to think about features like snap to edge.

And if the application doesn't implement it you can't move the window at all as a user.

Some think splash screens are in fact a feature.

They always were frustrating to me, and I'm glad that for Word 2007 in Wine I can omit them and switch to other window anyway by putting a splash screen down, unlike for Word 2007 on Windows (but I suspect, even there it's possible to force it down via some 3rd party tools).

i hate splash screens like why show some thing just to hide it and like 99% of them dont set a sane _NET_WM_WINDOW_TYPE so tiling window managers dont know to make them auto flow

The point is to discourage the user from doing anything while the app is launched so it is launched as fast as possible and nothing interferes with the process.

It's all wlroots. Nothing works without wlroots. Wayland is Wayland + wlroots in the same way that X11 is X11 + XOrg.server. Anything usable that doesn't use wlroots pulls a thousand fucking dependencies. Fuck that.

It's all wlroots. Nothing works without wlroots.

Except the desktop environment "everyone" is using... it's so sad that many new Linux users get served Gnome by distributions - not only by Fedora (which is to be expected due to IBM Red Hat control), but also Ubuntu. Otherwise we could just not care about it anymore at this point.

It's all wlroots. Nothing works without wlroots.

Except the desktop environment "everyone" is using... it's so sad that many new Linux users get served Gnome by distributions - not only by Fedora (which is to be expected due to IBM Red Hat control), but also Ubuntu. Otherwise we could just not care about it anymore at this point.

I've never had GNOME work, on X11, or Wayland , it just sucks. Something is always broken even on default settings for GNOME Debian. Never had any issues with Kwin{FT,} on plasma

What the hell is wlroots?

@Espionage724 its a Wayland compositor library that a lot of compositors use, it was a part of sway

It's all wlroots. Nothing works without wlroots.

Except the desktop environment "everyone" is using... it's so sad that many new Linux users get served Gnome by distributions - not only by Fedora (which is to be expected due to IBM Red Hat control), but also Ubuntu. Otherwise we could just not care about it anymore at this point.

I've never had GNOME work, on X11, or Wayland , it just sucks. Something is always broken even on default settings for GNOME Debian. Never had any issues with Kwin{FT,} on plasma

Oh please, stop using broken hardware or use a mainstream distro. Fedora, Ubuntu, and openSUSE all provide good implementations for GNOME and have for years. I'm using GNOME 46 on Xorg on Fedora 40 right now.

Mainstream distro? You mean the mainstream distros that force me to use Snap? No thanks.

Broken hardware? You mean the ThinkPad X220 and Ryzen 7800X3D systems I have. Yes, very broken!

I have Ryzen and Wayfire (Wlroots based) working just fine. Mate on wayland with a window list and icons on the desktop. This was supposed to be impossible but I proved otherwise by coding it up.

Fedora, Ubuntu, and openSUSE all provide good implementations for GNOME and have for years.

I never heard anyone praise Debian for their GNOME implementation.

implementation feels like the wrong word here configuration or distribution feels more right

It's all wlroots. Nothing works without wlroots.

Except the desktop environment "everyone" is using... it's so sad that many new Linux users get served Gnome by distributions - not only by Fedora (which is to be expected due to IBM Red Hat control), but also Ubuntu. Otherwise we could just not care about it anymore at this point.

It is one of many reasons to stop recommending these "mainstream distributions". Mint if someone is super novice and wants the easiest possible experience. Void or Arch for basically anyone wanting a workstation. Debian/Devuan for servers.

The ThinkPad I guess can be explained by the distro implementation, and I never heard anyone praise Debian for their GNOME implementation. Can't say I'd rule hardware out with Ryzen.

More likely is that Gnome is just bad, lol.

They finally woke up, almost according to my prediction, in an attempt to unite the whole GTK+ ecosystem beyond GNOME against GNOME: https://blog.linuxmint.com/?p=4675

Sadly, too late, and not in GTK+2 times, as GTK+3 has an awful rendering performance. This had to be done in times when Audacious and LXDE refused from porting to GTK+3, stayed on GTK+2 and were ported to Qt later.

I really hope the insanity of GNOME developers will finally make it as a marginal thing as Enlightenment is. Decades ego, E16 was much more open to integration with other environments, but further versions turned into a totally isolated and alien thing following crazy guidelines. Just like, well, GNUstep. Modern GNOME Shell is totally something akin to those.

Im facing some problems with KDE and Wayland, all the web apps like VS Code or web browsers are flikering on wayland sessions, some times it makes unusable all the apps.
For Brave Browser it function very well moving on brave://flags OzoneWayland to use wayland but the whole webapps are flikering and make it unusable.
And it happens on Fedora 40, Arch Linux and Ubuntu
I have been switch to X11 and the problems gone, but its compatibiliti with Nvidia it not the best like wayland, pros and cons.

Im facing some problems with KDE and Wayland, all the web apps like VS Code or web browsers are flikering on wayland sessions, some times it makes unusable all the apps. For Brave Browser it function very well moving on brave://flags OzoneWayland to use wayland but the whole webapps are flikering and make it unusable. And it happens on Fedora 40, Arch Linux and Ubuntu I have been switch to X11 and the problems gone, but its compatibiliti with Nvidia it not the best like wayland, pros and cons.

The problems is with the Nvidia drivers and lack of implicit sync and bad GBM support, since Nvidia only want to support explicit sync. Explicit Sync was added recently in the Linux kernel. This should be solved with the driver 555 from Nvidia that will be released this year. I hope that fixes all this.

Thanks for your answer, and it also fix the zoomed apps? everything looks bigger on waylando, like taskbar on KDE looks bigger compared with XORG

Thanks for your answer, and it also fix the zoomed apps? everything looks bigger on waylando, like taskbar on KDE looks bigger compared with XORG

I didn't hear about that problem, maybe it's a KDE problem, is everything big or just specific things?

I think it's just KDE things, window decorations like the title bars, the taskbar, for example the terminal in wayland by default looks much larger as if the pixels were not well calculated in wayland

first one screenshot its X11 and second one its wayland, as you can see both images have the same scroll on the page but in wayland its bigger compared with X11 yaou can see also the difference on title bars

Good Wayland v X11 thread: https://www.phoronix.com/forums/forum/phoronix/latest-phoronix-articles/1461854-netbsd-on-the-state-future-of-x-org-x11

Thanks for the pointer. Looks like some people are waking up. Some of the points from this gist are discussed there as well. tl;dr:

• Wayland is Linux centric, leaving the BSDs in a lesser position (my 2 cents: not good)
• Some people think BSDs are not relevant on the desktop (my 2 cents: I'd like to help change that)
• People realize that Wayland leads to feature and bug fragmentation (my 2 cents: not good)
• Some people say "but it works for me on Gnome/KDE" (my 2 cents: that is besides the point)
• People realize that Wayland does not offer feature parity for all actively used X11 features (my 2 cents: not good)

Good Wayland v X11 thread

Aside from a large number of insults, maybe. Especially from mrg666 who calls anyone who he disagrees with a troll.

Strangely myownfriend has disappeared. Must be a day off for the dude. He always finds a way to turn Wayland deficiencies into advantages or downplays them as if they are irrelevant.

10 cents in total. My jar gets heavier.

I think it's just KDE things, window decorations like the title bars, the taskbar, for example the terminal in wayland by default looks much larger as if the pixels were not well calculated in wayland

first one screenshot its X11 and second one its wayland, as you can see both images have the same scroll on the page but in wayland its bigger compared with X11 yaou can see also the difference on title bars

Your images are broken for some reason. Are you in Plasma 6 of 5?

I think it's just KDE things, window decorations like the title bars, the taskbar, for example the terminal in wayland by default looks much larger as if the pixels were not well calculated in wayland
first one screenshot its X11 and second one its wayland, as you can see both images have the same scroll on the page but in wayland its bigger compared with X11 yaou can see also the difference on title bars

Your images are broken for some reason. Are you in Plasma 6 of 5?

I dont know why are broken :( but im on Plasma 6
Will try here


first one its wayland and second X11
both with same settings ej: Taskbar 32 px

I think it's just KDE things, window decorations like the title bars, the taskbar, for example the terminal in wayland by default looks much larger as if the pixels were not well calculated in wayland
first one screenshot its X11 and second one its wayland, as you can see both images have the same scroll on the page but in wayland its bigger compared with X11 yaou can see also the difference on title bars

Your images are broken for some reason. Are you in Plasma 6 of 5?

I dont know why are broken :( but im on Plasma 6 Will try here first one its wayland and second X11 both with same settings ej: Taskbar 32 px

Looks like even the web pages are bigger, did you try changing the scale in settings?

:O yup that solved the problem, I'm using Endeavor OS and every time I installed it everything always seemed much bigger apparently by default in Wayland it uses a scale of 125%, or I moved it by accident but it happened every time install it, now we just have to wait for the release of the 555 driver

I dont know why are broken :( but im on Plasma 6

The Wayland screenshot is blurry as hell.

Make sure you've enabled widget.wayland.fractional-scale.enabled in about:config or otherwise Firefox under Wayland looks like ass.

Too bad Thunderbird 115, the last stable version, still does not support this option and is basically unusable for me.

Maybe by 2040 linux will have a display server that matches windows in 2015. If this bad joke that is wayland and gtk 3+ starts to degrade the linux desktop too much, then I will just move back to windows and use my linux tools from wsl.

Im not sure if wayland and gtk devs have considered that they are in competition with windows and mac. They can try to perform a type of coupe and force themselves into dominant position of control over the linux desktop, but you can get access to all the power that headless linux has from other platforms.

Im not sure if wayland and gtk devs have considered that they are in competition with windows and mac.

There's none.

Windows of any version after at least Windows 2000 is known to contain at least one extra governmental signing key. Also Windows 10 and 11 contain all kinds of antifeatures related to privacy that are on by default, must be turned off, and who knows if that's all of the phone-home crap? Worst of all is the efforts to "nudge" people to logging into their desktop with a Microsoft account or any other online account, and the dangers that MS could attempt to turn Windows 11 into a subscription product. There is no amount of bugs, breakage, etc that could cause me to use Windows due to my particular needs, which include complete isolation of all systems from the ad and tracking world. The data they scarf up is traded on the open market and can find its way to "people finder" doxxing sites, law enforcement is a known and proven buyer as of a couple years ago, no doubt private investigators buy it, etc. Thus, I do not run Windows, and I do not use Google Play Services or Gapps on phones, the works. The only real issues with updates to hardware breaking things on the desktop are the kernel and GPU drivers. I don't see any new kernel that any new CPU must use coming out with neither x11 nor wayland support anytime soon.

Windows of any version after at least Windows 2000 is known to contain at least one extra governmental signing key.

I would be curious to know if ameliorated.info has ameliorated that - which I would assume so... I don't think it is impossible to run modern windows without the nonsense. However, it is impossible to run a modern computer/phone without a "management engine" that is transparent with respect to the OS. This is a bit off topic, but I didn't bring it up :) However, where I suppose the topics intersect is digital rights management control on open source operating systems - and potential funding & strategies for that. Maybe that would be entirely restricted to the GPU drivers - but maybe include the DE/WM as well.

For my purposes both digital rights management and all files dependent on it are banned from all of my hardware. The only use I have for such things is repurposing them for other purposes. Example: HDCP might be possible to use to encrypt all traffic from your computer to your monitor, so as to scramble the take for anyone sniffing for monitor signals to spy on your screen. While HDCP is broken, all the cracks for it depend on having access to the cable and probably on posession of the monitor in question. Might be unbroken for this use, but I don't know.

Other than that, I operate on a zero subscription model and do not purchase digital media of any type.

Windows of any version after at least Windows 2000 is known to contain at least one extra
governmental signing key.

We don't need conspiracy crap in this discussion.

and who knows if that's all of the phone-home crap?

Crap is solely in your head. Fire up Wireshark and show what Windows leaks. It literally takes 10 minutes to download it and enable MITM using your own SSL certificate. Considering Windows has been leaking left and right for over a decade now, we now must have had thousands of web pages documenting it. Where are they?

@probonopd

Hide or delete this reply. I don't want "Windows leaking data to MS/government" crap in this discussion.

Gist comments have no "hide" function, so the only option is to leave it as-is or delete.
So please let's stay on the topic of Wayland deficiencies in this gist and discuss unrelated topics elsewhere.
Posts that stray away from the topic too far may get deleted. Not something I like to do but it seems necessary to have a somewhat focused discussion.

Gnome people acknowledge that "GNOME Wayland" exists:

So it's not fixed for Wayland as a whole, just for "GNOME Wayland"?

Please read again what that post actually says. There is a new wayland protocol and gnome implements it in its wayland variant. Don't get me wrong, there are issues with wayland but you are actively framing and rewording things that were never said (nor implied).

@Consolatis

Please read again what that post actually says.

It says "GNOME Wayland", literally.

Yes, Gnome in its wayland variant compared to Gnome in its X11 variant. The post above frames it as if it was meant to say "wayland belongs to gnome and gnome only". Lets please keep being objective here and not maliciously frame things in this way.

Gist comments have no "hide" function, so the only option is to leave it as-is or delete.

Why have you even chosen Gist as the platform? It obviously bites for many reasons for this purpose.

Yes, Gnome in its wayland variant compared to Gnome in its X11 variant. The post above frames it as if it was meant to say "wayland belongs to gnome and gnome only".

It's worse: it somehow implies than X.Org is only a backend for Gnome, rather than gnome-shell being merely an ordinary X client which can be killed at any time in runtime and replaced with some other WM.

Why have you even chosen Gist as the platform?

Well... I have just used Gist to collect my thoughts, never would have expected more than 5 comments ;-)

Yes, Gnome in its wayland variant compared to Gnome in its X11 variant.

OK, that's one way to read it. I was reading it as "Wayland in its Gnome variant". But that is the thing - you can never know whether something that has been fixed in "Wayland" for one desktop will automatically make it work in all desktops.

Well... I have just used Gist to collect my thoughts, never would have expected more than 5 comments ;-)

And now you suddenly have a burden of moderating all of this.

I switched to sway so that I wouldn't have to recreate a workflow without having the fall back of x11. Of course this is under the assumption that x11 won't be an option at some point in the future thanks to the powers that be (so i might as well learn it now). While I have mostly been able to stick with sway/wayland, it has been one sacrifice after another with no gain to speak of for me. So for that reason my stance is that wayland (various implimentations and supporting software included) is an inferior product.

Hide or delete this reply. I don't want "Windows leaking data to MS/government" crap in this discussion.

lmao just close your eyes

But that is the thing - you can never know whether something that has been fixed in "Wayland" for one desktop will automatically make it work in all desktops.

Wayland can either refer to a collection of protocols or to a shared library that basically only handles the wire format. Many (but not all) compositors use that shared library so fixing a bug in there could indeed fix something in multiple compositors at once. In the case of the protocols.. they are just a bunch of XML files so any "fixes" there don't do anything at all. If a compositor supports a new version of a given protocol or not is completely up to the compositor. Same for which protocols it supports in the first place.

So to sum up: in most cases, a compositor "fixing" something will only "fix" it in that compositor. Other's might not have had the issue in the first place or decide against supporting some protocol or new version of a protocol (for example due to a lack of manpower or because of disagreement with the goals of the protocol).

Edit:
There are also libraries like wlroots or smithay, fixes there may obviously impact multiple compositors that use that library.

HAHAHAH WAYLAND > X11 IT IS THE FUTURE ADAPT OR DIE!!!!!!!!!! NEANDERTHAL!!!!!

I switched to sway so that I wouldn't have to recreate a workflow without having the fall back of x11. Of course this is under the assumption that x11 won't be an option at some point in the future thanks to the powers that be (so i might as well learn it now). While I have mostly been able to stick with sway/wayland, it has been one sacrifice after another with no gain to speak of for me. So for that reason my stance is that wayland (various implimentations and supporting software included) is an inferior product.

What sacrifices have you made? I sacrificed nothing but gained a lot after the i3->sway transition.

I switched to sway so that I wouldn't have to recreate a workflow without having the fall back of x11. Of course this is under the assumption that x11 won't be an option at some point in the future thanks to the powers that be (so i might as well learn it now). While I have mostly been able to stick with sway/wayland, it has been one sacrifice after another with no gain to speak of for me. So for that reason my stance is that wayland (various implimentations and supporting software included) is an inferior product.

What sacrifices have you made? I sacrificed nothing but gained a lot after the i3->sway transition.

Sway does not support (and devs say will not support) i3 layouts or an equivalent. I can't find anything to replace xrandr's functionality. I couldn't get sunshine to actualy share the screen (eventually figured out the screen sharing is broken on wayland which Seems like something that is important to a lot of people.) For the one xorg application that I use on wayland, xrdb behaves erraticly, and I would randomly have to reload Xresources. Transparency issues that will not be fixed. Other things that I eventualy found work arounds for. etc... I'm glad that you haven't had to make sacrifices but I and may others have had a different experience. Since we're sharing experiences, what have you gained from switching to sway over i3?

Sway does not support (and devs say will not support) i3 layouts or an equivalent

What are i3 layouts? My config supports a load of different layouts.

I can't find anything to replace xrandr's functionality.

All that is handled by swaymsg.

I couldn't get sunshine to actualy share the screen (eventually figured out the screen sharing is broken on wayland which Seems like something that is important to a lot of people.)

I can't say for sunshine specifically, but if you have xdg-desktop-portal-wlr installed and running then any applications that support the portal protocol can screenshare on sway.

For the one xorg application that I use on wayland, xrdb behaves erraticly, and I would randomly have to reload Xresources. Transparency issues that will not be fixed.

I can't say for these as I've never heard of xrdb and never hears of anyone having transparency issues...

Since we're sharing experiences, what have you gained from switching to sway over i3?

Outside of sway having better configuration, I also noticed considerable performance gains, with marginally less RAM usage and great improvement in draw time and CPU/GPU usage. I later found out this is partially caused by Xorg having a weird obscure bug in their driver for that specific computer (it was an '06 laptop which sold terribly, nobody used it let alone Linux users). In spite of this, I still see marginal to decent improvement in draw time and resource usage even on my balls to the wall overpowered desktop running a 7800X3D and an RX6600. I imagine the compositor being built-in rather than running it separately is partially responsible.

I sacrificed nothing but gained a lot after the i3->sway transition.

YWNBAS.

What

https://copypastatext.com/wayland/

https://copypastatext.com/wayland/

You need to step up your trolling game. It has potential but is full of errors.
Like the forced vsync example: there is actually a tearing protocol which allows applications to opt-in to render broken frames and waste CPU and GPU resources.

Also the general assumption that wayland compositors are written to gain some popularity and make them famous is pretty ridiculous. There may be compositors out there that are maintained and written for personal use and because its fun to write and work in a team to enhance it. Corporate projects can be different obviously and there are definitely compositors out there that try to tell everybody that they are the best since sliced bread but you really can't generalize it that way.

Posting random links in here rather than writing what you have to say directly is also pretty weak.

What are i3 layouts? My config supports a load of different layouts.

It is i3's format for saving the current layout to disk so that you could easily script loading that exact layout later. When loading it would capture the programs as they are launched and everything would match the layout you manually created.

I can't find anything to replace xrandr's functionality.

All that is handled by swaymsg.

Much of it but not all of it. Particularly the color shifting. I had a script running in the background to shift yellow at a certain battery percentage while discharging and red for another percentage. Losing that ability sucks since in Sway the notifications don't show up when a window is in full-screen mode. I believe Wayfire is the only one who has implemented it and that was fairly recent.

I can't say for sunshine specifically, but if you have xdg-desktop-portal-wlr installed and running then any applications that support the portal protocol can screenshare on sway.

Well, that looks interesting. Are there any open-source applications that implement this in a low-latency remote desktop application like Sunshine/Moonlight? That would be awesome, and one less sacrifice.

I can't say for these as I've never heard of xrdb and never hears of anyone having transparency issues...

For some xorg applications that don't have their own configs, they can take configuration from an x resources database.
And as far as transparency it just doesn't behave the same way on sway as it did in i3 with picom. Sway community says those were violations of the standards so they have no interest in implementing that behavior. I don't agree with the standards on this. There are some patches that kinda work-ish, I'm not a dev so it would probably take me more time than it's worth to write a solution myself.

Outside of sway having better configuration, I also noticed considerable performance gains, with marginally less RAM usage and great improvement in draw time and CPU/GPU usage. I later found out this is partially caused by Xorg having a weird obscure bug in their driver for that specific computer (it was an '06 laptop which sold terribly, nobody used it let alone Linux users). In spite of this, I still see marginal to decent improvement in draw time and resource usage even on my balls to the wall overpowered desktop running a 7800X3D and an RX6600. I imagine the compositor being built-in rather than running it separately is partially responsible.

What do you consider better about Sway's config? It's pretty similar to i3's. I do prefer that sway has includes built-in but despite me being an amateur, I didn't find it difficult to script around not having includes.
I hear a lot about performance gains but I don't personally notice them. My system felt just as snappy/responsive on i3, If I have to open up benchmarking software to notice a difference then that difference is inconsequential to me. I don't usually do graphicly intense things on my daily driver. I'd much prefer to not lose functionality that impacts my daily workflow/usage. Aside from the screen sharing, for which I briefly switch back to x11 on that box (fortunately I can accomplish that switch over SSH), nothing else is a deal breaker, Just a collection of small sacrifices. But those sacrifices do impact my opinion of Wayland vs Xorg.

Well, that looks interesting. Are there any open-source applications that implement this in a low-latency remote desktop application like Sunshine/Moonlight? That would be awesome, and one less sacrifice.

A looooong time ago I remember reading about a VNC protocol in the works for Wayland. I have no idea how far it's gotten or if it still exists. I think there is some kind of way to do remote desktop though.

What do you consider better about Sway's config?

It's been so long since I used i3 that I can't recall the specifics, lol. All I really know is that my i3 config was a lot more clunky than sway for whatever reason (skill issue is possible). Also, I like waybar a lot more than polybar.

For performance I do many graphics intensive tasks on my desktop, while my older laptop is just unbelievably underpowered. For my X220 where I don't do many graphically intensive things while its still decently powerful, I don't see much difference. Just a veeery slight increase in snappiness.

For sway (and other wlroots based compositors): https://github.com/any1/wayvnc/

For sway (and other wlroots based compositors): https://github.com/any1/wayvnc/

This is what I was thinking of. I believe the consensus in that discussion that once KWin used wlroots (now KwinFT), that would be the standard.

Pushing wayland onto people: it is enabled by default in ubuntu 22.

Breaking stuff: found right after the first reboot when upgrading from 20 on an old machine as I could not access it with x11vnc.
I guess they are ways around (working in some or all cases) but I don't care or have time to get basic things to work again: it's a small server doing a few things, not the project of my life. The linux machines I admin and use for work don't have any display anyways so I don't care.
Linux is not a religion or a hobby for me. It's a tool.

At windows haters: you can still run 20+ years old applications on windows 10. Open 30 years old office files.

@phourglass

At windows haters: you can still run 20+ years old applications on windows 10. Open 30 years old office files.

Windows 11 and Ubuntu 22 compete to see who has degraded the most. :)

...and Ubuntu wins easily (thanks to Wayland and Snap). Typing this from Windows 11. So sad.

For sway (and other wlroots based compositors): https://github.com/any1/wayvnc/

So each wayland flavour needs its own vnc implementation?

kwin vnc
wlroots vnc
mutter vnc
?

For sway (and other wlroots based compositors): https://github.com/any1/wayvnc/

So each wayland flavour needs its own vnc implementation?

kwin vnc wlroots vnc mutter vnc ?

@hendrack Yes.

...and Ubuntu wins easily (thanks to Wayland and Snap). Typing this from Windows 11. So sad.

Fortunately there is still Xubuntu + Xfce which limits the damage.

For sway (and other wlroots based compositors): https://github.com/any1/wayvnc/

So each wayland flavour needs its own vnc implementation?

kwin vnc wlroots vnc mutter vnc ?

Fortunately only one of these actually works, so only one implementation is needed.

For sway (and other wlroots based compositors): https://github.com/any1/wayvnc/

So each wayland flavour needs its own vnc implementation?
kwin vnc wlroots vnc mutter vnc ?

Fortunately only one of these actually works, so only one implementation is needed.

I've tried the kde vnc client and other than screen, I could not control anything. It recently broke or something, who knows.
Or perhaps its only cause I use Fedora on mac m1 (asahilinux) ...

...and Ubuntu wins easily (thanks to Wayland and Snap). Typing this from Windows 11. So sad.

Wins what? Or this is sarcasm? I don't get why engineers give Ubuntu & RedHat so much free press considering most that have honestly looked into it have better distro preferences (whether for personal workstation or server) with good reasons to cite. Like I described more thoroughly in this thread, an OS/distro is a meaningful and useful unit of abstraction to consider for the purposes of software development - especially regarding the pain-points discussed here.

Fortunately only one of these actually works, so only one implementation is needed.

You're American, you need only one keyboard layout, no surprise you somehow believe Sway "works".

XKB_DEFAULT_LAYOUT env var..

env var.

Pfff.

Runtime switching of layout sets means nothing for you, right?

I did even experiment with my own layouts, so I had to reload them often.

Runtime switching of layout sets means nothing for you, right?

XKB_DEFAULT_LAYOUT=de,us
XKB_DEFAULT_OPTIONS=grp:alt_shift_toggle

← You ←

 . My point

Runtime switching of sets is

setxkbmap us,ru,ua
setxkbmap us,gr,ua
setxkbmap us,ar,ua
setxkbmap 'us,ru,ua(aesthetic)'
setxkbmap 'us,ru,ua(shavian)'

...and Ubuntu wins easily (thanks to Wayland and Snap). Typing this from Windows 11. So sad.

Wins what? Or this is sarcasm? I don't get why engineers give Ubuntu & RedHat so much free press considering most that have honestly looked into it have better distro preferences (whether for personal workstation or server) with good reasons to cite. Like I described more thoroughly in this thread, an OS/distro is a meaningful and useful unit of abstraction to consider for the purposes of software development - especially regarding the pain-points discussed here.

@dm17 I think he is replying to the these comments:

At windows haters: you can still run 20+ years old applications on windows 10. Open 30 years old office files.

Windows 11 and Ubuntu 22 compete to see who has degraded the most. :)

So he's saying Ubuntu easily wins the race toward trashing itself.

@probonopd in my opinion Windows took a flying leap into the trash with Windows 8. I think I used Windows 10 breifly and I've been full time linux ever since so I don't know much about anything after. Last time I used ubuntu was with a live usb to do one task so I usually don't have snaps shoved down my throat. But I believe you can use other deb package repos like Debian's and Cinnamon's and stuff mostly works, so at least there is some escape from Ubuntu's crap.

Fortunately only one of these actually works, so only one implementation is needed.

You're American, you need only one keyboard layout, no surprise you somehow believe Sway "works".

I'd gladly believe you if all three of your points were correct. Also, wlroots is more than sway... I've used other wlroots WMs (KwinFT mostly) and they work just as well. Layout switching has worked well for me through a simple rofi script.

wlroots is more than sway

That's the point: there is still no generic mechanism. Wayfire has implemented it by reloading its config at runtime. Nice solution, hehe.

I'm delving through the Pango source code to hunt a bug and discovered there are areas which remain unchanged since 00s:

Hilariously, the only modern change there by modern GOOME developers is for migrating to the new documentation generator. The one which requires JS, unlike the old static HTML one, which still isn't a complete replacement, and which they manage to put down from time to time which already caused butthurt to me and totally not just to me.

I doubt there still is even a single person who remembers how this code works. Still, no one seems to whine that Pango is dying like X.Org, because of bitrot. Think about it.

Still, no one seems to whine that Pango is dying like X.Org, because of bitrot. Think about it.

You know what else was likely not changed in forever? The yes command. Think about it.

wlroots is more than sway

That's the point: there is still no generic mechanism. Wayfire has implemented it by reloading its config at runtime. Nice solution, hehe.

wlroots supports it natively and wayfire's solution is stupid.

wlroots supports it natively

What do you mean exactly? The aforementioned environment variable mechanism is not dynamic.

The yes command

Nice derailing attempt, but Pango is definitely way more complex. And text rendering is not cast in stone since 00s, at least combined emojis appeared since then. BTW, the genmon plugin for xfce4-panel has drastically increased RAM usage several years ago when I upgraded Pango to a version supporting fonts with embedded colourful images.

The yes command

Nice derailing attempt, but Pango is definitely way more complex. And text rendering is not cast in stone since 00s, at least combined emojis appeared since then. BTW, the genmon plugin for xfce4-panel has drastically increased RAM usage several years ago when I upgraded Pango to a version supporting fonts with embedded colourful images.

Yes, that was exactly my point. You were comparing Pango to X11.

What do you mean exactly? The aforementioned environment variable mechanism is not dynamic.

Keyboard layout switching is supported in wlroots natively, not through whatever Wayfire does. It supports XKB and can switch at runtime for 7 years now.

A fellow user just reported running a highly demanding patched game with an old lwjgl version runs pretty poorly on wayland KDE plasma6. Switched to X11 and it was immediately playable.
So much for backwards compatibility.

I knew already, X11 performs better for such an old game, but now I got confirmation.

Seems like the return of blackouts in Ukraine would finally motivate me to pay more attention to Wayland, huh?


BTW, I wondered if my anti-GUI ideology and the belief (justification, rather) that the text mode is beneficial in terms of power consumption is still relevant on modern video cards which don't support the text mode natively anymore. Back then, one of primary reasons of my migration to GNU/Linux was the deprecation of text mode in Windows: Alt+Enter doesn't work in CMD.EXE with WDDM anymore, and later (in Windows 10?) they replaced it with a fake fullscreen mode. Back in my student years, I had spent a lot of time in the framebuffer console, being one of the few text mode idelogists on L.O.R. (the other one was saahriktu), and installed a lot of tools like fbi/fim/fimgs/fbterm (Vim/elinks work there "for free") to survive there without having to make a sluggish switch to the X.Org VT. (Wayland totally wasn't ready to use in any form on bare hardware that years.)

And you know what? the consumption is also around 9W when in a text TTY, hehe. X.Org (or Compiz?) consumes energy merely by repaints, so having it in a separate inactive VT doesn't matter much.

(I wonder what would happen if I launch that many windows in Wayfire session, hehe. Or replace Compiz with some lighter WM with no compositing. Wait for more tests.)

The consumption barely changed when I replaced Compiz with Openbox. But it dropped to 9W too when I minimized (almost) all the windows, hehe.

Yeah, just launched Chromium and it's like this:

Case closed, it's not X11, it's GUI apps who are greedy.

I have no idea how anyone is continuing to follow this discussion,* so I decided to ask one of those large neural networks for some help.†

Queries

I've attached 500 comments on a controversial blog post about Wayland vs Xorg. Summarize both sides of the debate.

Based on the 500 comments, there seem to be two main sides to the debate around Wayland vs Xorg:

Arguments critical of Wayland:

• Wayland breaks compatibility with many existing Linux applications and tools that were built for Xorg, requiring them to be ported or patched to work with Wayland compositors. This places a burden on application developers.
• Wayland lacks some features and capabilities that Xorg has, like global hotkeys, controlling mouse cursor position, screen capture/sharing in some cases, color management, etc. Implementing these often requires using additional libraries or Wayland protocol extensions.
• Wayland compositors lack consistency - things that work on GNOME's Mutter may not work the same way on KDE's Kwin or Sway. More standardization is needed.
• Some see Wayland as being biased towards or controlled by GNOME/Red Hat/Fedora and not caring about other environments.
• As a newer, less mature protocol, Wayland may have more undiscovered security issues compared to the battle-tested Xorg.

Arguments in favor of Wayland:

• Xorg is old, archaic and has accumulated a lot of bloat over the years with its many extensions. It has fundamental architectural limitations that are hard to change. A fresh, modern protocol is needed.
• Wayland has some technical advantages over Xorg, like better performance, smoother graphics, easier HiDPI and mixed refresh rate support, more secure architecture.
• Many of the lacking features can be implemented as Wayland protocol extensions without the core protocol getting bloated. Libraries like wlroots make it easier to implement compositors.
• With toolkits like GTK and Qt supporting Wayland and projects like PipeWire, XDG desktop portals providing key functionality, most applications work fine on Wayland now with a few exceptions. XWayland provides backwards compatibility for X11 apps.
• As Wayland matures and gains adoption, remaining issues and gaps in functionality will get ironed out. But this is a gradual transition and some breakage is inevitable in the process of replacing something as entrenched as Xorg.

In summary, opponents see Wayland as immature, not respecting existing ecosystem/workflows, and trying to force change for change's sake. Proponents see it as a necessary modernization step for the Linux graphics stack to overcome Xorg's legacy limitations, even if the transition is painful. The debate is often quite heated and emotional on both sides.

Here are the last 100 comments. What issues remain to be resolved among the participants—or is the debate simply running in circles?

Based on the last 100 comments, it seems the debate is largely running in circles at this point, with a few new specific issues being raised but no real progress or consensus being reached.

The main recurring points of contention appear to be:

1. Wayland's readiness and feature-completeness compared to X11. Critics argue it is still lacking key functionality and consistency across implementations, while proponents say it is usable for most people's needs now.

2. The fragmentation of Wayland implementations across different desktop environments and the lack of universal standards for certain features. This is seen as a regression from X11's uniformity.

3. Whether the architectural changes in Wayland are justified improvements or needlessly disruptive changes that burden application developers. There is disagreement on how much of an improvement Wayland actually provides over X11.

4. The influence/control of GNOME, Red Hat, and other major corporate players over the direction of Wayland and surrounding technologies like systemd, compared to the more decentralized development of X11.

5. Some debate over the backwards compatibility story - how well Wayland supports legacy X11 applications and workflows.

A few new specific pain points were brought up, like issues with screen sharing, VNC remote access, color management, keyboard layout switching, and performance regressions for some games. But in general, the discussion seems to be rehashing earlier arguments rather than reaching any new understanding or agreement.

Both sides appear quite entrenched in their views at this stage. The Wayland critics see it as an immature, over-hyped and politically driven change that is shattering the X11 ecosystem to serve corporate/GNOME interests. The Wayland advocates argue it is a overdue modernization of the Linux graphics stack that is already usable and will only get better, and that X11 is an unmaintainable legacy system holding back progress.

Some frustration and animosity is evident between the camps, with accusations of shilling, trolling and spreading FUD. But no clear resolution seems in sight, as the debate has deadlocked into restating grievances rather than finding common ground. The intractability of some architectural differences between X11 and Wayland makes compromise challenging.

Code for this

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import github
from github import Github

import json

from util import *

def serialize_datetime(dt):
    return dt.strftime('%Y-%m-%d %H:%M:%S')

def serialize_user(user):
    if hasattr(user, 'login'):
        return {
            'login': user.login,
            'id': user.id,
            'avatar_url': user.avatar_url,
            'html_url': user.html_url
        }
    elif user is not None:
        return {
            'deleted': True,
            'raw_extra_data': dict(user)
        }
    else:
        return {
            'deleted': True
        }

class SerializableGistComment:
    def __init__(self, comment):
        self.comment = comment

    def serialize(self):
        return {
            'id': self.comment.id,
            'body': self.comment.body,
            'created_at': serialize_datetime(self.comment.created_at),
            'updated_at': serialize_datetime(self.comment.updated_at),
            'user': serialize_user(self.comment.user)
        }

    def to_json(self):
        return self.serialize()

class Gist:
    def __init__(self, username, gist_id, token=None):
        if token:
            self.g = Github(token)
        else:
            self.g = Github()
        self.username = username
        self.gist_id = gist_id
        self.gist = None
        self.comments = None
        self.get()

    def get_gist(self):
        self.gist = self.g.get_gist(self.gist_id)
        eprint('Got gist:', self.gist.description)

    def get_comments(self, max_comments=None):
        self.comments = []
        i = 1
        for comment in self.gist.get_comments():
            comment = SerializableGistComment(comment)
            self.comments.append(comment)
            eprint("Got comment №{}: {}".format(i, comment.comment.body))
            i = i + 1
            if max_comments is not None and max_comments > -1 and i > max_comments:
                eprint('Gist has more than {} comments, stopping'.format(max_comments))
                break
        eprint('Got {} comments'.format(len(self.comments)))


    def get(self):
        self.get_gist()
        self.get_comments()

    def serialize(self):
        return {
            'id': self.gist_id,
            'description': self.gist.description,
            'files': {name: {'language': file.language, 'content': file.content, 'filename': file.filename, 'size': file.size, 'raw_url': file.raw_url}
                      for name, file in self.gist.files.items()},
            'comments': self.comments,
            'created_at': serialize_datetime(self.gist.created_at),
            'updated_at': serialize_datetime(self.gist.updated_at),
            'owner': serialize_user(self.gist.owner),
            'html_url': self.gist.html_url,
            'public': self.gist.public,
            'comments_count': len(self.comments)
        }

    def to_json(self):
        return json.dumps(self.serialize(), indent=4, default=gist_comment_serializer)

def gist_comment_serializer(obj):
    if hasattr(obj, 'serialize'):
        return obj.serialize()
    else:
        raise TypeError('Object of type {} is not serializable'.format(type(obj)))

if __name__ == '__main__':
    import os
    import sys

    get_github_token_from_env_file_if_exists()

    assert len(sys.argv) == 3, 'Usage: {} <username> <gist_id>'.format(sys.argv[0])
    username, gist_id = sys.argv[1], sys.argv[2]

    token = os.getenv('GITHUB_TOKEN')
    if token is None:
        eprint('Warning: GITHUB_TOKEN is not set, you may encounter rate limit.')

    gist = Gist(username, gist_id, token)

    print(gist.to_json())

python getgist/gist.py probonopd 9feb7c20257af5dd915e3a9f2d1f2277 > 9feb7c20257af5dd915e3a9f2d1f2277.json
jq -r '.comments[]|[.user.login, .body]|@tsv' < 9feb7c20257af5dd915e3a9f2d1f2277.json > 9feb7c20257af5dd915e3a9f2d1f2277_comments.tsv

Notes

* Even loading the whole thing is proving impossible, so I had to use GitHub's API's to put it all in one large Markdown file which I could then attempt to read.
† “Claude AI Opus 3”, it'll probably be out of date by tomorrow so that's not important.

10/10 method name get_github_token_from_env_file_if_exists i hope it does what it says

Good catch, I forgot to attach util.py, but you'll be glad to know it does:

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

# getgist utilities

import os
import sys
import warnings
from pathlib import Path

def eprint(*args, **kwargs):
    print(*args, file=sys.stderr, **kwargs)

def get_github_token_from_env_file_if_exists():
    env_file = Path('.env')
    if env_file.exists():
        with env_file.open() as f:
            for line in f:
                key, value = line.strip().split('=', 1)
                if key == 'GITHUB_TOKEN':
                    os.environ['GITHUB_TOKEN'] = value
                else:
                    warnings.warn('Unknown key in .env file: {}'.format(key))
    return None

Okay, okay, got it, Wayland matters and we widget developers need to adapt.
From our side, a "pure Wayland with wlroots" target is on the way, but moving from Form X11 to Wayland is not "out of the box" and will take time.

So, one of our solutions to become "pure Wayland" would be to use SDL (we already have this target working):
https://jan.newmarch.name/Wayland/SDL/

What do you think about SDL-Wayland, does it work well and can it be called a “pure Wayland” application?

What do you think about SDL-Wayland, does it work well and can it be called a “pure Wayland” application?

The concept sounds like a slow wrapper for a whole layer of wrappers. I want stuff as-close-to-bare-metal as possible, and Wayland is already further away than Xorg with stuff like libinput -> evdev vs just evdev. SDL as I understand is a giant compatibility library for targeting cross-platform (like Unity engine), and not raw-performance.

Of course if it just works well enough to not be noticed, I guess it could be cool :p

As for running stuff with SDL on Wayland, the only two games I played that use it (RuneScape/NXT, Dota 2) crashed on-start and needed forced-Xwayland earlier this year.

...and Ubuntu wins easily (thanks to Wayland and Snap). Typing this from Windows 11. So sad.

Come on, you have to know what's inferior by now :p Why are you typing that from W11 and not W10 LTSC?

My personal migration plan for when or if the day comes that I buy graphics hardware which is supported in the Linux kernel, but which is not supported by Xorg, due to abandonment of its development on GNU/Linux more broadly, is to just run fullscreen Xwayland with some Xorg supporting window manager.

Is there some reason of which I'm unaware that makes this unworkable? If not, I'm not sure what all of the fuss is about, really. :) !

Come on, you have to know what's inferior by now :p Why are you typing that from W11 and not W10 LTSC?

Why would you not use Spectre if you're using Windows?

Come on, you have to know what's inferior by now :p Why are you typing that from W11 and not W10 LTSC?

Why would you not use Spectre if you're using Windows?

Because I like my operating system coming from legit sources and patching with legit updates; I can't imagine using someone else's modified Windows image in an age of ransomware and coin miners. Plus I know how to tweak my OS probably beyond whatever Spectre does :p https://github.com/Espionage724/Windows

Nice job @ctrlcctrlv! Would you mind asking it what it thinks a reasonable amount of years to catch up would be? Or if there should be a cut off or due date before another option is considered?