Adrian Chadd wrote: > On 1 October 2011 15:21, Jayachandran C. <jchan...@freebsd.org> wrote: > >> I would like to understand this, reverting r216862 would take out the >> critical_enter() and cpu_idleclock() which would keep the timer >> interrupts coming is as usual, this should not affect the event timer. > > I haven't verified that mav's timer stuff does the correct thing by > configuring the clock timer to occur every 1000hz in this instance. I > kinda hope so.
When setting kern.eventtimer.idletick=1, you were effectively disabling cpu_idleclock()/cpu_activeclock() and you've properly received about 1127 timer interrupts per second (mix of 1000 of hz and 127 of stathz). Also when CPU is busy or has high interrupt/context switch rate, that happen automatically, so it definitely works. If you are talking about programming hardware timer for periodic 1000Hz rate, it doesn't happen automatically, because I doubt benefits it gives worth strict aliasing of hardclock() and statclock() it causes. If you like, you can do it manually via kern.eventtimer.periodic=1. -- Alexander Motin _______________________________________________ svn-src-head@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/svn-src-head To unsubscribe, send any mail to "svn-src-head-unsubscr...@freebsd.org"
