[ntp:questions] Building FreeBSD V8.0 kernel for PPS
cswiger at mac.com
Thu Apr 15 21:07:03 UTC 2010
On Apr 14, 2010, at 9:51 PM, unruh wrote:
>> Kernel PPS_SYNC discipline is capable of providing around +/- 120 nanosecond accuracy.
>> While an ethernet packet containing NTP timestamps might well fire off an interrupt from the NIC, not only is the network ISR a lot more complicated and slower than fielding an interrupt from the serial or parallel port, there's also no guarantee that ntpd running in userland will immediately receive and process this information. For another thing, modern NICs tend to do some degree of interrupt mitigation, which adds delay.
> No I meant serial or parallel port interrupts. The standard drivers for
> these will process the interrupts and you can time stamp them.
Timestamp using what?
If you truly have a local timesource which is more accurate than the PPS signal, of course you should use it, but none of the clocks found on standard x86 hardware are going to be anywhere close. The point of the PPS kernel discipline is to compare your less precise local clock to a more precise, interrupt-driven signal, and fine-tune the adjtime()/adjtimex()/etc adjustments being made to a greater level of accuracy than is possible to obtain from userland.
More information about the questions