X.Org vs. Wayland Browser Performance With Firefox + Chrome

[phoronix]

Phoronix: X.Org vs. Wayland Browser Performance With Firefox + Chrome

Given the release of Firefox 75 with Wayland improvements and also Firefox 76 now being in beta with even more work on the Wayland front, here are some web browser benchmarks under Wayland and the X.Org Server session with GNOME Shell 3.36 on Ubuntu 20.04. Additionally, Google Chrome benchmarks on Wayland and X.Org were also carried out.

http://www.phoronix.com/vr.php?view=29059

[Mthw]

Is DMABuf enabled by default in FF Beta? That could explain why was Webrender visibly faster. Also, it would be interesting to see some DMABuf on vs off benchmark with FF Nightly.

[birdie]

IOW Wayland doesn't really improve your desktop performance.

[Hibbelharry]

IOW Wayland doesn't really improve your desktop performance.

And this, ladies and gentleman, is how you adhere to all important rules of trolling. Chapeau!

Now, let's go on.

[Britoid]

I'm actually curious for the reason why Firefox Wayland runs faster than the Xorg version.

It's not too surprising given all the upstream Firefox Linux work is mainly Wayland now, but maybe it helps Firefox spend less time needing to send updates to the display server or can do partial repaints?

[Volta]

It's good to see Firefox not only catches up to Chrome, but it's sometimes noticeably faster. It's also great performance advantages on Wayland are much higher than regressions.

IOW Wayland doesn't really improve your desktop performance.

Get lost clown.

[kozman]

I'm actually curious for the reason why Firefox Wayland runs faster than the Xorg version.

It's not too surprising given all the upstream Firefox Linux work is mainly Wayland now, but maybe it helps Firefox spend less time needing to send updates to the display server or can do partial repaints?

Could be Firefox giving some perf love toward Wayland. Given that we're almost 2 years since 1.20.0 was released and no 1.21.0 in sight, Mozilla might be putting some eggs in the other basket per se.

[bug77]

And this, ladies and gentleman, is how you adhere to all important rules of trolling. Chapeau!

Now, let's go on.

I don't think he's trolling. X is constantly getting bashed because it's bloated, outdated and such. And yet, you remove X out of the equation, insert the new, modern solution and performance barely moves. It's obvious something doesn't add up.

[andyprough]

IOW Wayland doesn't really improve your desktop performance.

You failed to read the fine print at the bottom of all the wayland promises over the past 12 years:
"It will improve your performance. Next year. Or the year after that. Or maybe the year after that. If you have the right hardware. And the right desktop. On certain tasks with certain apps. Maybe. Depends on the alignment of the stars and the moon, and if Jupiter is in the 2nd house."

[gregzeng]

Both X.org & Wayland may differ, according to the GPU. Using just the CPU's inbuilt GPU may differ. Using different drivers for all GPU's will probably vary.
There are special drivers, adjusted for different GPU's. Drivers released by closed sources such as AMD, Intel or Nvidia are expected to perform better than the general purpose open source drivers.
Often the CPU & GPU drivers are assisted in different ways in the Linux kernel. This depends on the version & type of Linux kernel. Low latency, with high speed memory and high speed hardware channels would outperform "normal" settings. Stress tests also require heat sinks to be added to hardware memory chips, to avoid heat-throttling on overheated chips.
Many other tweaks can also be done by those wanting maximum performance.
The other concern is Closed Source corporate-tweaked CHROME is compared to open source FIREFOX. Google Chrome is suspected to have privacy traps, compared to the two open sourced products. These privacy traps may be creating the performance difference. Instead of Chrome, the test should have been done with the other open source product: CHROMIUM.