HPET broken on Dell 1950's?

I have an old Dell 1950 that I've rescued from Linux and tossed a copy of -STABLE on it, but am seeing a constant 0.5 load average. With the system completely idle, and kern.eventtimer.timer=LACPI, the load drops to the expected value of zero.

This feels like it should be an FAQ, but short of noting that the load is non-zero, is there a programatic way to determine if the event timer is "broken?" The system was functioning just fine, but it always had a constant load even when doing absolutely nothing. ?

FreeBSD ops05.internal 9.1-PRERELEASE FreeBSD 9.1-PRERELEASE #3: Tue Jul 24 17:56:59 UTC 2012 root@xxxxxxxxxxxxxx:/usr/obj/usr/src/sys/GENERIC amd64

kern.eventtimer.et.HPET.flags: 3
kern.eventtimer.et.HPET.frequency: 14318180
kern.eventtimer.et.HPET.quality: 450
kern.eventtimer.et.HPET1.flags: 3
kern.eventtimer.et.HPET1.frequency: 14318180
kern.eventtimer.et.HPET1.quality: 440
kern.eventtimer.et.HPET2.flags: 3
kern.eventtimer.et.HPET2.frequency: 14318180
kern.eventtimer.et.HPET2.quality: 440
kern.eventtimer.choice: HPET(450) HPET1(440) HPET2(440) LAPIC(400) i8254(100) RTC(0)
kern.eventtimer.timer: HPET
kern.timecounter.tc.HPET.mask: 4294967295
kern.timecounter.tc.HPET.counter: 749769877
kern.timecounter.tc.HPET.frequency: 14318180
kern.timecounter.tc.HPET.quality: 950
kern.timecounter.hardware: HPET
kern.timecounter.choice: TSC(-1000) ACPI-fast(900) HPET(950) i8254(0) dummy(-1000000)
dev.hpet.0.%desc: High Precision Event Timer
dev.hpet.0.%driver: hpet
dev.hpet.0.%location: handle=\_SB_.HPET
dev.hpet.0.%pnpinfo: _HID=PNP0103 _UID=0
dev.hpet.0.%parent: acpi0




--
Sean Chittenden
seanc@xxxxxxxxxxx




Attachment: signature.asc
Description: Message signed with OpenPGP using GPGMail