Subject: Re: top output -- huh?
To: None <lorenz@phil.uni-sb.de>
From: Markus Kilbinger <kilbi@rad.rwth-aachen.de>
List: port-atari
Date: 07/12/1997 10:44:20
>>>>> "Benjamin" == Benjamin Lorenz <benni@phil.uni-sb.de> writes:

    Benjamin> Huhu!  This is interesting:

load averages:  1.40,  1.77,  1.73
57 processes:  2 running, 55 sleeping
CPU:  1.2% user, 91.7% nice,  7.0% system,  0.0% interrupt,  0.0% idle
Memory: 13M Act 2808K Inact 3952K Wired 1920K Free 24M Swap 96M Swap free 

  PID USERNAME PRI NICE  SIZE   RES STATE WAIT     TIME    CPU COMMAND
12776 benni    105   10 8424K 8560K run   -        1:13 141.68% cc1plus
12705 benni      2    0 2368K 1184K sleep select   0:32  3.74% X


    Benjamin> 141% CPU? Is there a hardware accelerator built in
    Benjamin> NetBSD? ;) Oh, and 0.0% interrupt, this never changes --
    Benjamin> is 0.0 just a dummy value?  And, what is "Wired" memory?

The problem for the utopic cpu load is top's assumption (see source)
kernels clock-rate is 100 Hz (and not HZ=64) though the real hz are
also retrieved from the kernel. So, the cpu load is too high by the
factor (100 / 64).

Markus.