Interesting analysis of linux kernel threading by IBM

[James A Simmons]

> The patch is coded for 2.3.5 until 2.3.20.

I still like to see it. Post it again. I just don't want to go searching
threw the linux archives for it. 

> When I speak about number of processes I speak as loaded testing processes, 
> not runqueue processes.

Okay. 
 
> Even in my test the average number of runnable is from 15 to 35.
> And remember that my patch has no optimization for CPU cache lines, etc..
> I think that supplied with that kinds of optimizations the results will be 
> even better the ones I measured.

Right. I love to see the results on my machine :)  

> I'm interested in the measuring system implemented by IBM coz I've not spent 
> a lot of time in my testing console.
> IBM guys also have my patch from 2-3 months ago.

Cool. I seen a post about LTT. Time to take a look at it.

Codito, ergo sum - "I code, therefore I am"
James Simmons                                                      (o_
fbdev/gfx developer                                      (o_  (o_ //\
http://www.linux-fbdev.org                              (/)_ (/)_ V_/_
http://linuxgfx.sourceforge.net




-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo en vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/