Much higher CPU usage than on other distors

I know that Qubes OS is built around compartmentalization, so I’m aware(as far as I can) of higher impact on machine resources, however, when my laptop is idle, dom0 eats between 2 and 5 percent of CPU(displayed on qui-domains short-info pop-up), when I watch 1080 youtube video(not even full-screen) with firefox and personal template(debian) that particular template eats 50-80% of the CPU. I don’t see any visual artifacts, however the laptop gets wild both by fan speed and heating. I use xps 13 with i7 and fresh KDE DE. I switched from manjaro and never had anything noticeable like that before.

Is this really the cost of compartmentalization or perhaps something doesn’t work well, how do I troubleshoot this kind of things?
Is there any tweaks I can use to somehow reduce the impact of heavy tasks on the CPU? Perhaps by switching something off, etc?

This might be relevant: Qubes is EXTREMELY slow on very new p1 gen 5 lenovo laptop.

More links:

1 Like

@fsflover So to summarize:

  • it supposed to eat more, due to disabled hardware-acceleration(is it only external GPU or both?)
  • we can now enable HyperThreading with kernel param

Is there anything else I missed in this jungle(I do very appreciate your help with finding and providing the above links)?

I enabled HyperThreading in BIOS and add kernel params. This didn’t solve the 50-80% CPU usage problem, but it did in fact changed something, as right now I’m getting 0% in dom0 while idle.

1 Like


AFAIK both. You can try (second) GPU passthrough though, to have GPU acceleration in a VM.

It’s indeed a lot of links. This post and this post suggest that some things can work better if you tell your software not to rely on GPU (as far as I understood).

That took awhile to go through. Even though it wasn’t updated long time, I guess it should work to passthough GPU… I see lots of recent topics on this forum about it.

Yeah, I digged a lot about this atm, nothing helped me significantly to notice. I guess the passthough solution would be great to use, it’s a reasonable compromise, but require an upgrade.

Is it 50-80% of the total resources or the resources allocated to the appVM?

Per qube(personal one). I do have 2 vCPU allocated for it though.

I don’t think ~65% sounds that crazy if you are using 2 vcpus with hyperthrading, I think the qube has access to 25% of the total resources.

1 Like

@renehoj It’s kind of new to me, as I never used VMs before and never experienced anything like that. Thank you for clarifying this for me.