my 4.1 and 4.2 machines are -stable, and all are running i386, clearly. My surprise and question was all in the fact that this changed from 4.1 to 4.2, and WHY it changed from 4.1 to 4.2. Otto Moerbeek has already explained that there was a change in the timecounter code, and your addition puts the rest in clear light and verifies that there is no change possible for getting the performance back.
-SD On Fri, Mar 14, 2008 at 10:03 PM, Stuart Henderson <[EMAIL PROTECTED]> wrote: > Whichever timer hardware your system is using (you can see with > 'sysctl kern.timecounter') seems a bit on the slow side, my 1200MHz > X40 runs your test program in 2.9s. > > $ sysctl kern.timecounter > kern.timecounter.tick=1 > kern.timecounter.timestepwarnings=0 > kern.timecounter.hardware=ICHPM > kern.timecounter.choice=i8254(0) ICHPM(1000) dummy(-1000000) > > Have you compared bsd with bsd.mp? We don't even know what code you > run, or what hardware you have, there's no dmesg... > > As an aside, tc_init(9) is a good starting point if you want to > learn about the timecounter code.
