Description of problem:

In both top and ps, the watchdog/1 process shows up with utterly
ridiculous cpu time. For example here is what ps says on a newly
booted system:

[tom@zooty ~]$ ps f -u root
  PID TTY      STAT   TIME COMMAND
 2520 ?        S      0:00 hald-runner
 2548 ?        S      0:00  \_ hald-addon-input: Listening on /dev/input/event2 
 2554 ?        S      0:00  \_ /usr/libexec/hald-addon-cpufreq
 2619 ?        S      0:00  \_ hald-addon-storage: polling /dev/sr0 (every 2 sec
 2631 ?        S      0:00  \_ hald-addon-storage: no polling on /dev/fd0 becaus
    2 ?        S<     0:00 [kthreadd]
    3 ?        S<     0:00  \_ [migration/0]
    4 ?        S<     0:00  \_ [ksoftirqd/0]
    5 ?        S<     0:00  \_ [watchdog/0]
    6 ?        S<     0:00  \_ [migration/1]
    7 ?        S<     0:00  \_ [ksoftirqd/1]
    8 ?        S<   21114574:23  \_ [watchdog/1]
...

Version-Release number of selected component (if applicable):
kernel-2.6.27-0.297.rc5.git2.fc10.x86_64

How reproducible:
Every time I run ps or top I see the silly time info.

Steps to Reproduce:
1. see above
2.
3.
  
Actual results:

ridiculous time for watchdog/1

Expected results:

Time very near zero in a newly booted system.

Additional info: