On Sun, 8 Nov 1998 [EMAIL PROTECTED] wrote:
> Switching CPU is bad for cache utilization. But the scheduler has some
> bias that makes the kernel favour keeping a process on the same cpu. You
> can try to increase the value in ...linux/include/asm/smp.h:
> #define PROC_CHANGE_PENALTY 20 /* Schedule penalty */
> Setting this to eg. 100 should make the process less prone to switching CPU.
> Tell us how it works for you. It seemed to work for me.
Now using 100 but it doesn't seem to change anything for me...
What are the bounds and the purpose of the value? Is 100 very high (like
percentage) or is the upper limit 255, 64k or 2/4G?
CPU usage is as follows:
cpu 112316 782
cpu0 45755 313
cpu1 66561 469
i.e., not equal but also not bound to one CPU alone.
Winschdawos,
- Matthias
--
Der Wein mit der Pille ist in dem Becher mit dem F�cher.
-----------------------------------------------------------------------------
