[ntp:questions] ntpd wedged again

A C agcarver+ntp at acarver.net
Sat Feb 11 09:21:13 UTC 2012


So ntpd has been behaving reasonably well with the snprintf fix.  I had 
good results with only internet servers.  My PPS and SHM refclocks were 
set to noselect.

I removed the noselect on the PPS refclock and left flag3 set to zero 
(no kernel discipline).

Everything seemed fine and then:

> Sat Feb 11 01:12:10 PST 2012
>      remote           refid      st t when poll reach   delay   offset  jitter
> ==============================================================================
> x127.127.22.0    .PPS.            0 l    -   16  377    0.000  -111.40 351.464
>  127.127.28.0    .GPSD.           4 l   49  128  377    0.000  -14655. 2814.64
>  169.229.70.201  169.229.128.214  3 u  103  512  377   39.347  -9274.2 6597.61
>  72.14.179.211   127.67.113.92    2 u   79  512  377   57.746  -14699. 10685.0
>  24.124.0.251    132.236.56.250   3 u  521  512  377   77.930  -9835.0 7451.10
>  130.207.165.28  130.207.244.240  2 u  153  512  377   79.131  -9155.6 6554.15
>  131.144.4.10    130.207.244.240  2 u  142  512  377   86.537  -9102.3 6526.3

This occurred very suddenly (over the course of only 30 seconds).  The 
clockstats show the offset wandering in cycles going up to 1 second and 
down to -1 second.  This happened within a few hours of starting ntpd 
with the PPS enabled.

I'm not sure what happened.  But when I restart ntpd:

11 Feb 09:17:17 ntpd[6823]: 0.0.0.0 c61c 0c clock_step -16.611482 s
11 Feb 09:17:01 ntpd[6823]: 0.0.0.0 c615 05 clock_sync

and the offsets calm down (this is just moments after restarting the 
jitter and offsets are continuing to drop down to their former values of 
about 1-2ms or better):
>      remote           refid      st t when poll reach   delay   offset  jitter
> ==============================================================================
> x127.127.22.0    .PPS.            0 l   12   16   17    0.000  -27.265  16.503
>  127.127.28.0    .GPSD.           4 l   75  128    1    0.000  -16595.   0.122
>  69.65.40.29     209.51.161.238   2 u    2   64    1   74.261  -16.396   2.797
> +169.229.70.201  169.229.128.214  3 u   37   64    1   37.577  -33.420  12.747
> *198.137.202.16  69.36.224.15     2 u   35   64    1   36.607  -32.686  12.116
>  130.207.165.28  130.207.244.240  2 u    9   64    3   77.754  -20.400  11.968
>  131.144.4.10    130.207.244.240  2 u    9   64    3   85.509  -17.853   7.143

The actual PPS signal coming into the system is extremely stable.  The 
jitter remained below 100us for several days straight (reported by 
clockstats while PPS was in noselect).



More information about the questions mailing list