[time-nuts] Re: NTP via Passive Optical Network (PON)

Fri Jul 25 09:48:00 UTC 2025

Hello

here is a machine on a GPON network in a france suburban area :

ntpq -c lpeers
 Â Â Â Â remote Â Â Â Â Â Â Â Â Â Â refid Â Â Â Â Â st t when poll reach Â Â delay Â Â offset 
 Â jitter
============================================================================== 

0.debian.pool.n .POOL. Â Â Â Â Â Â Â Â Â 16 p Â Â Â - Â Â 64 Â Â Â 0 Â Â Â 0.000 Â Â Â 0.000 
 Â Â 0.001
1.debian.pool.n .POOL. Â Â Â Â Â Â Â Â Â 16 p Â Â Â - Â Â 64 Â Â Â 0 Â Â Â 0.000 Â Â Â 0.000 
 Â Â 0.001
2.debian.pool.n .POOL. Â Â Â Â Â Â Â Â Â 16 p Â Â Â - Â Â 64 Â Â Â 0 Â Â Â 0.000 Â Â Â 0.000 
 Â Â 0.001
3.debian.pool.n .POOL. Â Â Â Â Â Â Â Â Â 16 p Â Â Â - Â Â 64 Â Â Â 0 Â Â Â 0.000 Â Â Â 0.000 
 Â Â 0.001
+195-154-185-215 109.190.177.205 Â 2 u Â 322 1024 Â 377 Â Â Â 2.798 Â Â Â 0.246 
 Â Â 0.110
+meshflow.net Â Â Â 5.196.160.139 Â Â Â 3 u Â Â 70 1024 Â 377 Â Â Â 6.172 Â Â -0.233 
 Â Â 0.417
-time.cloudflare 10.20.8.5 Â Â Â Â Â Â Â 3 u Â Â 77 1024 Â 377 Â Â Â 3.373 Â Â -0.429 
 Â Â 0.374
+passion.bitschi 192.168.4.3 Â Â Â Â Â 2 u Â 108 1024 Â 377 Â Â Â 7.065 Â Â Â 0.298 
 Â Â 0.267
-45.13.105.44 (m 230.226.69.180 Â Â 3 u Â 504 1024 Â 377 Â Â 16.239 Â Â -1.823 
 Â Â 0.648
*dns.freewebworl .PPS. Â Â Â Â Â Â Â Â Â Â Â 1 u 1017 1024 Â 377 Â Â 12.033 Â Â Â 0.176 
 Â Â 0.164

Here is a machine on "black fiber" in paris center

ntpq -c lpeers
 Â Â Â Â remote Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â refid Â Â Â Â Â st t when poll 
reach Â Â delay Â Â offset Â Â jitter
======================================================================================================= 

0.debian.pool.ntp.org Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â .POOL. Â Â Â Â Â Â Â Â Â 16 p Â Â Â - Â 256 
 Â Â Â 0 Â Â 0.0000 Â Â 0.0000 Â Â 0.0001
1.debian.pool.ntp.org Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â .POOL. Â Â Â Â Â Â Â Â Â 16 p Â Â Â - Â 256 
 Â Â Â 0 Â Â 0.0000 Â Â 0.0000 Â Â 0.0001
2.debian.pool.ntp.org Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â .POOL. Â Â Â Â Â Â Â Â Â 16 p Â Â Â - Â 256 
 Â Â Â 0 Â Â 0.0000 Â Â 0.0000 Â Â 0.0001
3.debian.pool.ntp.org Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â .POOL. Â Â Â Â Â Â Â Â Â 16 p Â Â Â - Â 256 
 Â Â Â 0 Â Â 0.0000 Â Â 0.0000 Â Â 0.0001
+ciran28.fr Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 134.59.1.5 Â Â Â Â Â Â 3 u Â Â 49 Â Â 64 
 Â Â Â 7 Â Â 3.1525 Â -2.0954 Â Â 1.4904
+bethany.fangfufu.co.uk Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 192.171.1.150 Â Â Â 2 u Â Â 54 Â Â 64 
 Â Â Â 7 Â Â 5.9604 Â Â 0.0356 Â Â 1.2179
#x.ns.gin.ntt.net Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 129.250.35.222 Â Â 2 u Â Â 52 Â Â 64 
 Â Â Â 7 Â 90.8017 Â -7.5388 Â Â 1.2852
+vps-mrs1.orleans.ddnss.de Â Â Â Â Â Â Â Â Â Â Â Â Â Â 145.238.80.80 Â Â Â 2 u Â Â 52 Â Â 64 
 Â Â Â 7 Â 11.9088 Â -0.6803 Â Â 1.1795
*dns.freewebworld.fr Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â .PPS. Â Â Â Â Â Â Â Â Â Â Â 1 u Â Â 50 Â Â 64 
 Â Â Â 7 Â Â 9.9991 Â -1.0038 Â Â 1.1328
+web1.ciran28.fr Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 82.64.45.50 Â Â Â Â Â 2 u Â Â 52 Â Â 64 
 Â Â Â 7 Â Â 2.5726 Â -1.3235 Â Â 1.5186
+time.cloudflare.com Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 10.25.8.4 Â Â Â Â Â Â Â 3 u Â Â 50 Â Â 64 
 Â Â Â 7 Â Â 2.0753 Â -1.6802 Â Â 1.2405
#82-64-81-218.subs.proxad.net Â Â Â Â Â Â Â Â Â Â Â 131.188.3.222 Â Â Â 2 u Â Â 53 Â Â 64 
 Â Â Â 7 Â 12.3248 Â -0.1797 Â Â 1.3448
+ns1.univ-montp3.fr Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 145.238.80.80 Â Â Â 2 u Â Â 51 Â Â 64 
 Â Â Â 7 Â 13.7076 Â -1.0098 Â Â 1.1377
+vps-761b8f12.vps.ovh.net Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 129.134.28.123 Â Â 2 u Â Â 51 Â Â 64 
 Â Â Â 7 Â Â 5.9942 Â -1.5038 Â Â 1.1760
+op.success.ovh Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 193.190.230.37 Â Â 2 u Â Â 50 Â Â 64 
 Â Â Â 7 Â Â 5.3664 Â Â 0.0757 Â Â 1.1355
#45.90.162.253 Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 195.13.1.153 Â Â Â Â 3 u Â Â 51 Â Â 64 
 Â Â Â 7 Â 23.0761 Â Â 9.3761 Â Â 0.8971
2001:41d0:801:2000::acb Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â .INIT. Â Â Â Â Â Â Â Â Â 16 u Â Â Â - Â Â 64 
 Â Â Â 0 Â Â 0.0000 Â Â 0.0000 Â Â 0.0001
2001:41d0:8:7a7d::1 Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â .INIT. Â Â Â Â Â Â Â Â Â 16 u Â Â Â - Â Â 64 
 Â Â Â 0 Â Â 0.0000 Â Â 0.0000 Â Â 0.0001
2001:41d0:701:1100::1ecc Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â .INIT. Â Â Â Â Â Â Â Â Â 16 u Â Â Â - Â Â 64 
 Â Â Â 0 Â Â 0.0000 Â Â 0.0000 Â Â 0.0001
h2.ncomputers.org Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â .INIT. Â Â Â Â Â Â Â Â Â 16 u Â Â Â - Â Â 64 
 Â Â Â 0 Â Â 0.0000 Â Â 0.0000 Â Â 0.0001
+ntp1.omdc.pl Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 210.100.177.101 Â 2 u Â Â 47 Â Â 64 
 Â Â Â 7 Â Â 6.0255 Â -0.7889 Â Â 1.0913
+109.190.177.205 Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â .PPS. Â Â Â Â Â Â Â Â Â Â Â 1 u Â Â 49 Â Â 64 
 Â Â Â 7 Â 10.1852 Â -1.0822 Â Â 1.0509

I have no conclusion.

With fast 10GPON I am not sure that the TDM latencies are significant 
compared to frame processing at the network nodes.

APTP link to a machine known to be on a network without jitter is 
probably required to check for this accurately.

Is such a thing available somewhere? We can do some tests if that's easy 
to setup.

Sebastien

On 24/07/2025 01:25, Kapp, Francois B. via time-nuts wrote:
> I was wondering if anyone has measured, or has seen results of measurements of the effect of a passive optical network on time transfer over NTP (or PTP). Intuitively, the fact that return communications are time division multiplexed should insert some jitter in the round trip time - any pointers to more concrete information?
> _______________________________________________
> time-nuts mailing list --time-nuts at lists.febo.com
> To unsubscribe send an email totime-nuts-leave at lists.febo.com