[ntp:questions] NTP vs chrony comparison (Was: oscillations in ntp clock synchronization)

Bill Unruh unruh at physics.ubc.ca
Mon Jan 21 17:42:15 UTC 2008

Having run NTP stably now for three days on a machine I previously ran
chrony on , I compared the control of the
clock on that machine with chrony and with ntp (the comparison is obviously
sequential, since both cannot run on the same machine at the same time.)
The chrony run was from Jan 13.5 to jan 18.3 while ntp was from Jan 20.0 to
21.7 during which time ntp was stable and the intial aquisition of lock was

Offset error:
   NTP: Mean=-3.1usec, Std Dev=63.1usec
   Chrony: Mean=-1.5 usec, Std Dev=20.1usec
Rate fluctuation:
   NTP:Mean=25.32  Std Dev=.078 (PPM) 
   Chrony: Mean=25.26 Std Dev=.091 (PPM)

Ie, while the rate might be better controlled by NTP ( although the fact
that the time interval was smaller may mean that this is just a measure of
the natural variation of the clock itself-- since the ntp measurements were
over the weekend, and chrony encompassed the weekdays when the grad
students use the computer) the offset control by chrony was a factor of 3
better than by ntp.  

Note that in each case the server was the same  Linux machine on the same subnet
controlled by a Garmin 18LVC with offset fluctuation of the order of 2usec
controlled by NTP, a modified shm refclock driver and a special purpose written
parallel interrupt driver. The roundtrip time is about .18msec between the
two machines.

More information about the questions mailing list