Are Custom Linux Kernels Faster than Stock?

33 thoughts on “Are Custom Linux Kernels Faster than Stock?”

1. I use Liquirix because mainline kernel doesnt support my wifi card

2. I dropped 6.7.10-1-liquorix-amd64 into Zorin 17.1 Pro, and as I'm on Intel graphics and pretty satisfied with that, I probably won't bother with XanMod. Still, cool video.

3. Monstercat ^_^

4. Xanmod

5. Liquorix ruined my audio in Linux Mint using an admittedly blah built-in audio setup. There was heavy reverb. The official kernel was fine as was Xanmod.

6. Im on gentoo and because its a source based distro compiling your own kernel is part of the installation. I set the experimental use flag on and set keyword ~amd64 so i can pull in the latest stable kernel which is 5.18.14 at the time of this comment. Im using a ryzen 7 5700x and the experimental flag pulls in the specific cpu optimizations. Seeing that u can remove extra stuff in the kernel you dont need, i dont see a possible slight increase in performance being worth the stability of mainline kernel, especially if youre building it from source anyways.

7. So these 'alternate' kernels are basically snake oil. I'm not interested in replacing the stable core of my systems for such a tiny speed boost. I could do just as well by overclocking my CPU 100-200MHz, which would also be more reliable than using an experimental kernel hack.

8. i use Xanmod. you toll me that.

9. I notice very little difference between the experimental kernel and using zen, but I get way better performance and compatibility on laptop using the experimental kernel over the stable kernel in my Manjaro install.

10. Could there be any malware in these kernels? Did anybody check?

11. The real question is Low 0.1% fps

12. I ended up installing Xanmod for my ryzen laptop as a solution to a "CPU leak" I was having for KDE plasma.
    turns out the kernel wasn't the problem, KDE had some messed up config or something that I found a command list that ended up fixing it properly.
    but after installing xanmod I'll probably keep it just because it's a better kernel

13. any updates mr titus on this subject ?

14. I'm learning all this programming stuff through osmosis. Regimented classes are my kryptonite. That being said, I feel really small right now. Hope I can eventually understand all this stuff.

    What I know: Kernels work with compilers. Kernels are closely tied to the OS its being used on.

15. Thanks for the video!! Because I work with pro audio, I was wondering how would Xanmod provide better latency results to record with lower buffer settings and with software monitoring
    Thanks again

16. Hey Chris.. I've an issue that my GPU is Nvidia GTX 1650 Ti 4GB, and I run Manjaro with KDE environment but I can't configure my graphic card. Have you a solution for this?

17. I habe huge problems with lag spikes

18. Nice shirt, I had a laugh there.

19. i wonder how this would be on a cpu heavy game like arma

20. i used both Xanmod & Liquorix with xanmod my cpu uses 5% but my gpu 48 celsius and with liqourix my cpu runs 10% but my gpu runs 40 celsius

21. This is actually something that I am working on right now. So far, I came to the conclusion, that there is no such thing as the perfect generic kernel. Let me explain: Xanmod is the best for my music production and for games. Having said that, the LQX kernel is not far off at all and if it is only about gaming then even the vanilla Arch kernel is looking pretty good. But when I compile stuff or do anything that just requires raw compute power then the best kernel so far seems to be the znver2 from the AUR. See where I am coming from?

    All of the kernels have been compiled by me with rather aggressive custom CFlags in order to try to squeeze the last bit out of the machine. Next in line are the Xanmod-RT and the Xanmod-Cacule, the latter claiming that its CPU scheduler is superior to anything else.

    But I already sense, that I will never find that one perfect kernel that fits it all. But maybe I can at least manage to reduce the amount of them because right now it kinda feels like if I had a dedicated kernel for each application.

22. Kernel 5.7 > have better performance for AMD now

23. Windows users: "I'm waiting for the update process to finish so I can use my computer again…"
    Linux users: "Hey, let's install some of these cool custom kernels to see if I can get more fps in games!"

24. Why would you wear a shirt that says "sudo apt remove sudo"….

25. Would be interesting to throw XOrg vs Wayland into the mix…

26. pleas test new kernel xD

27. Even if i find this video quite interesting i´m pretty sure that you shouldn´t stablish a correspondence between this test and the title of the video, as this is only one test in one specific area. Not enough samples to get a proper conclusion.

28. Benchmark based on one game is not a benchmark

29. Hi Chris. I think that it's essential in such tests to show lowest fps, not only highest and average.

30. After running custom kernels on Ubuntu 20.0.4 my games run much smoother had some driver issues with resolutions on my first install all I had do was uninstall the driver and boot up the free driver than reinstall the non free driver and it worked fine.

31. sudo apt purge sudo

32. good test xD

33. I can`t use virtualbox after install xanmod kernel. Is this normal?

Comments are closed.