Re: Re: dmesg timestamps vs uptime

[Yaroslav Halchenko <debian@onerussian.com>]

Hi Ben,

Thanks -- that is a nice pointer (i.e. /proc/sched_debug), but I still
can't match everything up in my mind... could you gimme a little hint?

I guess the .clock (in sched_debug) is the interesting one, but it
doesn't match up to the "time" reported by the kernel...

$> sudo tcpdump -i bond0 -tt -vvv -n "(dst host raider or src host raider)" -s 192  | head -3; dmesg | tail -1;  grep -e 'now' -e '\.clock' /proc/sched_debug ; echo -n "date :";  date +'%s.%N'; echo -n "uptime:"; cat /proc/uptime
1235620965.207560 IP (tos 0x0, .....
...
[259941.257724] device eth1 left promiscuous mode
now at 250362660.852703 msecs
  .clock                         : 250362660.973307
  .clock                         : 250362661.008877
....
date :1235620965.387909070
uptime:250362.67 232514.99

so indeed /proc/uptime is close (or is) what is in .clock in sched_debug,
but how could I get those 259941.257724? I am sorry if that is
something obvious and RTFM

-- 
Yaroslav Halchenko
Research Assistant, Psychology Department, Rutgers-Newark
Student  Ph.D. @ CS Dept. NJIT
Office: (973) 353-1412 | FWD: 82823 | Fax: (973) 353-1171
        101 Warren Str, Smith Hall, Rm 4-105, Newark NJ 07102
WWW:     http://www.linkedin.com/in/yarik