2.5.70 kernel initial tests

[HornGábor]

Hi!

As i read the main areas of the development of the 2.5.x series were the
following:

- O(1) scheduler, so the runtime of the scheduler algorithm is
independent of the number of the running processes (unlike in 2.4.x)
- vm implementation (2.4.x is messy, now it uses an rmap solution)
- thread handling (importnat, and it developed VERY much)
- smp capabilites (2.4.x again is a joke compared to 2.5.x in this area)
- preemptiv kernel (2.4.x needed a patch for it)
- block device system optimization (it was another HUGE work, and is
responsible for all the harddisk etc handling...)
- alsa (which is now said to be significantly better than oss by experts
like A'rpi @ mplayer)
- better vm/vfs cooperation

All these areas r very important! 2.4.x had a 'working' solution for
them (except preempt and O(1)) while 2.5.x has a highly optimized, clean
solution...

As i read the 2.5.x performs much better mainly under heavy
circumstances (huge memory, much processes, high load), and i have to
say my impression was exactly that :)

bye, hirisov

On Fri, 2003-05-30 at 12:49, Chris wrote:
> .
> .
> .
> > So all i can say to the new kernel is WOW! I'll do the same test w/
> > apache1 vs apache2 (w/ both of the kernels, hehe :), i'm interested if
> > there's a noticable differnece between them. 
> > 
> > Hope u don't mind i pasted those long tables, but they speak more clear
> > than any words imho :)
> > 
> > bye, hirisov
> > 
> > 
> 
> Interesting :)
> Any reason for this?
> 
> Greetz
> Chris
> 
> _______________________________________________
> Lunar mailing list
> Lunar at lunar-linux.org
> http://lunar-linux.org/mailman/listinfo/lunar
-- 
Horn Gábor <Horn.Gabor at aktiv.co.hu>