I must admit (shamefully) that I am running FreBSD inside Microsoft Virtual Server 2005 for some hosting business that I am doing. I noticed early on that I was seeing weird problems with the clock in the virtual machine. I scored this tidbit after a bunch of time on Google that worked forby adding adding ‘kern.hz=100′ to /boot/loader.conf. Read more to see the entire thread I grabbed of Google..

4.x and 5.x run smoothly in this virtual environment, but CURRENT
spends 20-30% of CPU time in the “swi4: clock sio” thread.
Moreover, CPU idle time data look really weird. Neither tweaking
kern.timecounter.hardware nor disabling ACPI seems to affect that.

The respective lines in the output from “top -S” reads:
11 root 171 52 0K 8K RUN 4:10 130.18% 130.18% idle
28 root -32 -151 0K 8K *Giant 0:09 31.15% 31.15% swi4: clock sio

Were there any attempts to investigate this singularity?

Date: Tue, 01 Mar 2005 17:01:27 +0100
To: Yar Tikhiy
Yar Tikhiy writes:

> 4.x and 5.x run smoothly in this virtual environment, but CURRENT
> spends 20-30% of CPU time in the “swi4: clock sio” thread.
> Moreover, CPU idle time data look really weird. Neither tweaking
> kern.timecounter.hardware nor disabling ACPI seems to affect that.

try adding ‘kern.hz=100′ to /boot/loader.conf.