[ntp:hackers] NIC knacks

David L. Mills mills at udel.edu
Sun Feb 10 21:08:13 UTC 2008


Guys,

Here is a snip from a memo I am writing. I read it again and am puzzled 
about the apparent conclusion that the incidental delay of each 
transceiver - transmit and receive - is 50 us. That sound really high 
and implies a huge number of machine cycles. Is there a driver/NIC 
expert onboard that has insight?

As an example of current practice, NTP servers macabre and mort are 
identical Intel Pentium clones running FreeBSD and synchronized to a GPS 
receiver. The servers share a lightly loaded 100-Mb switch; the GPS 
receiver is connected by fiber repeaters and another 100-Mb switch. Each 
server shows offsets of about 25 us relative to the other and the GPS 
receiver. Each server shows roundtrip delays of about 140 us with the 
other. Note that only 40 us (four LAN hops) can be accounted for on the 
wire, with the remaining 100 us split between the two transceivers.

Dave


More information about the hackers mailing list