[ntp:questions] Network problems affecting NTP
Eugen COCA
ecoca at eed.usv.ro
Fri Jul 1 06:06:38 UTC 2011
Due to a network problem on our provider, the packets were routed on a
different path than usual yesterday, for several hours. This period,
NTP displayed wrong offsets:
+GPS_NMEA(1) .GPS. 0 l 16 16 377 0.000
0.001 0.002
ptbtime1.ptb.de .PTB. 1 u 4 64 377 64.545
-4.450 0.140
ntps1-1.cs.tu-b .PPS. 1 u 49 64 357 65.944
-4.335 0.223
ntp-p1.obspm.fr .TS-2. 1 u 27 64 377 68.793
-4.233 0.034
GPS-1.MIT.EDU .GPS. 1 u 53 64 377 155.543
-4.491 1.779
oPPS(1) .PPS. 0 l 9 16 377 0.000
0.001 0.002
ntp1.usv.ro .PPS. 1 u 14 64 377 0.290
0.016 0.006
ntp2.usv.ro .PPS. 1 u 4 64 377 0.229
0.017 0.027
ntp3.usv.ro .PPS. 1 u 5 64 377 0.269
0.023 0.026
-ptbtime2.ptb.de .PTB. 1 u 51 64 277 64.426
-4.276 0.190
-ntp0.rrze.uni-e .GPS. 1 u 29 64 377 55.088
-4.486 0.039
+ntp1.oma.be .PPS. 1 u 64 64 377 63.900
-4.257 0.509
-time-a.nist.gov .ACTS. 1 u 11 64 373 204.117
16.101 49.841
After the problem was solved, the packets were routed on the usual
path. The result is:
+GPS_NMEA(1) .GPS. 0 l 35 64 377 0.000
0.001 0.002
ptbtime1.ptb.de .PTB. 1 u 48 256 377 49.194
-0.021 0.265
ntps1-1.cs.tu-b .PPS. 1 u 69 256 377 50.778
-0.044 0.675
ntp-p1.obspm.fr .TS-2. 1 u 15 256 377 53.307
0.242 0.047
GPS-1.MIT.EDU .GPS. 1 u 95 256 377 140.137
-0.414 0.637
oPPS(1) .PPS. 0 l 4 16 377 0.000
0.001 0.002
ntp1.usv.ro .PPS. 1 u 31 64 377 0.198
0.000 0.003
ntp3.usv.ro .PPS. 1 u 50 64 377 0.175
-0.002 0.004
ntp4.usv.ro .PPS. 1 u 56 64 377 0.198
-0.020 0.005
ptbtime2.ptb.de .PTB. 1 u 187 256 377 49.320
0.028 1.192
ntp0.rrze.uni-e .GPS. 1 u - 256 377 39.578
-0.073 0.028
ntp1.oma.be .PPS. 1 u 184 256 377 48.966
0.068 0.124
time-a.nist.gov .ACTS. 1 u 249 256 377 147.557
2.230 2.364
One may observe the delays were also affected during this interval.
Also, the time information served to clients was affected, the
pool.ntp.org monitoring system confirmed the delay -
http://www.pool.ntp.org/scores/80.96.120.252. It is obvious that a
server synchronizing only with Internet sources will be in error as
there is has no way to determine the problem. Can someone explain this
behavior ?
More information about the questions
mailing list