calcru: runtime went backwards, RELENG_6, SMP

[Dmitry Morozovsky]

On Sat, 9 Jun 2007, Matthew Dillon wrote:

MD> :Well, I can of course shut the kernel up, but kernel time stability is still my 
MD> :concern. I run ntpd there and while sometimes it seems stable (well, sorta: 
MD> :drift are within several seconds...) there are cases of half-a-minute time 
MD> :steps. 
MD> 
MD>     If you don't want to do that, try forcing the timer to use the 8254
MD>     and see if that helps.  You may also have to reduce the system tick
MD>     to ~100-200 hz.

Does not help either:

ct-new# sysctl kern.clockrate
kern.clockrate: { hz = 200, tick = 5000, profhz = 133, stathz = 26 }
ct-new# sysctl kern.timecounter    
kern.timecounter.tick: 1
kern.timecounter.choice: TSC(-100) ACPI-safe(1000) i8254(0) dummy(-1000000)
kern.timecounter.hardware: i8254
kern.timecounter.nsetclock: 3
kern.timecounter.ngetmicrotime: 6118
kern.timecounter.ngetnanotime: 0
kern.timecounter.ngetbintime: 0
kern.timecounter.ngetmicrouptime: 4741
kern.timecounter.ngetnanouptime: 30
kern.timecounter.ngetbinuptime: 485
kern.timecounter.nmicrotime: 1027
kern.timecounter.nnanotime: 96
kern.timecounter.nbintime: 1123
kern.timecounter.nmicrouptime: 804
kern.timecounter.nnanouptime: 0
kern.timecounter.nbinuptime: 60658
kern.timecounter.stepwarnings: 0
kern.timecounter.smp_tsc: 0
ct-new# ps
calcru: negative runtime of -1322717 usec for pid 4 (g_down)
calcru: negative runtime of -1322717 usec for pid 4 (g_down)
  PID  TT  STAT      TIME COMMAND


Sincerely,
D.Marck                                     [DM5020, MCK-RIPE, DM3-RIPN]
------------------------------------------------------------------------
*** Dmitry Morozovsky --- D.Marck --- Wild Woozle --- marck at rinet.ru ***
------------------------------------------------------------------------