Liquorix 3.8 Kernel Has Some Performance Wins Over Linux

[not.sure]

I have been using it recently due to bug in original Debian kernel, which was fixed in 3.8, but Debian is still on 3.2,

You could also use 3.8 from experimental.

[Kano]

If you use Kanotix you can even use kernel 3.9 with wheezy

[cfeck]

If it is supposed to be measuring desktop performance...

...then it should use benchmarks that measure latency. For example, try copying a 4 gigabyte file and start firefox at the same time, and measure how long it needs before firefox is fully usable.

http://www.google.com/search?q=high+io+wait+kernel+bug

[Zan Lynx]

What About Latency?

What about measuring things that matter for a desktop and gaming machine such as worst frame performance and input-to-response latency, especially worst-case latency?

There's not much that is more annoying than typing in a text editor or word processor and having everything freeze solid for two seconds because a large disk job started running in the background.

[brosis]

You could also use 3.8 from experimental.

Liquorix is rather stable, desktop-optimized and easy to install. So, no, I couldn't.

[ext73]

Venture to say that I think ... my kernels - particularly i7 [for Sandy and Ivy Bridge] and Brazos [for AMD Athlon II from up] line will be faster, and far more responsive - especially under a load of 100% for each thread / core processor - than Steven kernels. Of course, it must be emphasized that Steven kernels are really good - btw I in recent years do not use BFS and BFQ.

Regards

[timofonic]

Venture to say that I think ... my kernels - particularly i7 [for Sandy and Ivy Bridge] and Brazos [for AMD Athlon II from up] line will be faster, and far more responsive - especially under a load of 100% for each thread / core processor - than Steven kernels. Of course, it must be emphasized that Steven kernels are really good - btw I in recent years do not use BFS and BFQ.

Regards

Can you specify what kernels are "yours"?

[smitty3268]

Looks like linux truly is superior to windows that never had this problem....

What are you talking about, Windows XP was notorious for that problem. They have seemed to solve it with Vista/7, though.

[ext73]

Can you specify what kernels are "yours"?

Hi, "my" in the sense - my configuration and compilatiion + a few modifications sources [made to build was possible] and e.g patch to removal of info: fast tsc failed. So ... for example, running a version of Brazos:

AMD APU E-350-1

AMD APU E-350-2

AMD APU E-350-3

Ubuntu.pl/e X t 7 3 kernels

our script - NeteXt'73

Greetings

[coder111]

Please mesure LATENCY when benchmarking Liquorix!

Hi,

All these benchmarks show is that there are no major performance regressions in Liquorix.

This kernel is LATENCY optimized. It is supposed to have better LATENCY than other kernels. Michael, can you please stop doing only throughput oriented benchmarks for desktop kernels and add some latency benchmarks?

This is very embarrassing. And it's the 2nd time Phoronix screws up like this and puts benchmarks that have little relevance. Don't get me wrong. I love Phoronix and I read it almost daily, but I'd like to see it get better and to stop doing embarrasing things like this article.

--Coder