[182420] in North American Network Operators' Group
Re: Speaking of NTP...
daemon@ATHENA.MIT.EDU (Matthew Huff)
Thu Jul 16 15:43:46 2015
X-Original-To: nanog@nanog.org
From: Matthew Huff <mhuff@ox.com>
To: Tony Hain <alh-ietf@tndh.net>
Date: Thu, 16 Jul 2015 19:43:41 +0000
In-Reply-To: <048001d0bffc$fea25660$fbe70320$@tndh.net>
Cc: nanog2 <nanog@nanog.org>
Errors-To: nanog-bounces@nanog.org
Thanks. We have always had a few outliers, but we have never had a large nu=
mber of external NTP have a consistent offset, and not one as big as 10ms. =
Something changed last Friday, probably at some peering point that caused t=
he issue. Maybe a symmetric path got created to route around some outage. M=
aybe some MPLS circuit got introduced into the mix that hides the underlyin=
g path/latency. Glad to know someone else has seen something like this.
Our 3 NTP servers that sync from external sources have at least 5 upstream =
stratum 1 servers and are peered to each other . They have settled on a se=
nse of time that is good within +/i 1 msec of our strata 1 clocks, so all i=
s good, but it was a stage occurrence after we had been good for so long. E=
ach of our servers are clients of our 2 x strata 1 servers and 3 x strata 2=
NTP servers. They all look good now.
=20
> On Jul 16, 2015, at 3:24 PM, Tony Hain <alh-ietf@tndh.net> wrote:
>=20
> I have had a consistent 10ms offset on a set of servers for the last 5 ye=
ars. After extensive one-way tracing, it turns out there is a 20ms asymmetr=
y "within" the Seattle Westin colo between HE & Comcast, causing all the IP=
v6 peers appearing over the HE tunnel to be 10ms offset from everything els=
e. There may be other instances of indirect peering causing a static asymme=
tric path delay, and NTP will report that as an offset of half of the diffe=
rence.=20
>=20
> Tony
>=20
>=20
>> -----Original Message-----
>> From: NANOG [mailto:nanog-bounces+alh-ietf=3Dtndh.net@nanog.org] On
>> Behalf Of Rafael Possamai
>> Sent: Thursday, July 16, 2015 8:53 AM
>> To: Matthew Huff
>> Cc: nanog@nanog.org
>> Subject: Re: Speaking of NTP...
>>=20
>> Depending on how exactly you have these servers configured with relation
>> to one another, small variations from one single source can be augmented
>> down the line.
>>=20
>> https://en.wikipedia.org/wiki/Propagation_of_uncertainty
>>=20
>>=20
>>=20
>> On Mon, Jul 13, 2015 at 8:17 AM, Matthew Huff <mhuff@ox.com> wrote:
>>=20
>>> We have 5 NTP server: 2 x stratum 1 rubidium oscillator time servers
>>> with GPS sync, and 3 servers running NTP 4.2.6p5-3 synced to external
>>> internet based NTP stratum 1 servers. We monitor our NTP environment
>>> closely, and over the last 10+ years, normally all of our NTP servers
>>> are sync'ed within
>>> +/- 2 msec. Starting last Friday, we started seeing some remote NTP
>>> +servers
>>> with GPS reference consistently offset by 10 msec.
>>>=20
>>> Any one else seeing this?
>>>=20
>>> ----
>>> Matthew Huff | 1 Manhattanville Rd
>>> Director of Operations | Purchase, NY 10577
>>> OTA Management LLC | Phone: 914-460-4039
>>> aim: matthewbhuff | Fax: 914-694-5669
>>>=20
>>>=20
>=20
