Hi All We needed to invest in new NTP servers and we've decided to make them available to the NZ sysadmin community to use as well. This is not an open public service as we have to have a minimal AUP to stop the servers being overwhelmed but you should find you can use them for pretty much all you need without contacting us. The servers use GPS as their primary time sources and have rubidium oscillators for stability if the GPS signal is lost. There's a web site that explains everything here: http://ntp.net.nz/ cheers Jay -- Jay Daley Chief Executive .nz Registry Services (New Zealand Domain Name Registry Limited) desk: +64 4 931 6977 mobile: +64 21 678840
On 3/09/2010, at 4:08 PM, Jay Daley wrote:
to stop the servers being overwhelmed
I was about to tell you about A.B.'s work, but I suspect that you already are talking to him about it when I look on the software/hardware/standards page. I note that there are three servers - I am surprised that there is not a fourth to allow for redundancy. Is that a cost decision? Looks like a good project anyway! It'll be good to have some time servers that are formally publicly available and maintained - I never have been sure of the state of the ihug/massey/waikato/etc. NTP servers that I've configured boxes to use in the past. -- Nathan Ward
On 3/09/2010, at 4:24 PM, Nathan Ward wrote:
I note that there are three servers - I am surprised that there is not a fourth to allow for redundancy. Is that a cost decision?
I've always understood that three is enough for redundancy. The client can tell when one goes awry by comparing with the other two. Admittedly if one goes down then the client can't tell that but we can pursue that logic ad infinitum no matter how many servers there are. Do you see it differently? And yes, cost was a notable factor. cheers Jay
Looks like a good project anyway! It'll be good to have some time servers that are formally publicly available and maintained - I never have been sure of the state of the ihug/massey/waikato/etc. NTP servers that I've configured boxes to use in the past.
-- Nathan Ward _______________________________________________ NZNOG mailing list NZNOG(a)list.waikato.ac.nz http://list.waikato.ac.nz/mailman/listinfo/nznog
-- Jay Daley Chief Executive .nz Registry Services (New Zealand Domain Name Registry Limited) desk: +64 4 931 6977 mobile: +64 21 678840
I think the issue is that with 3 clocks, if 1 fails, you are left in a
situation where NTP can't tell which remaining clock to trust.
I'd also be interested to know precisely where the servers are physically
connected. While NTP is really very good at dealing with latency, it can't
deal with asymmetry in the forward and return paths (it assumes one way
delay = 0.5xRTT). I'd be curious to see how many people have symmetric
routes to the servers.
In any case, I think it's a great move guys, and should be applauded. I have
recently been playing with NTP and determining how accurately NTP over
symmetric links matches GPS time and was pleasantly surprised by how close
we could get. (Short story - a few tens of microseconds)
Cheers - N
On 3 September 2010 16:51, Jay Daley
On 3/09/2010, at 4:24 PM, Nathan Ward wrote:
I note that there are three servers - I am surprised that there is not a fourth to allow for redundancy. Is that a cost decision?
I've always understood that three is enough for redundancy. The client can tell when one goes awry by comparing with the other two. Admittedly if one goes down then the client can't tell that but we can pursue that logic ad infinitum no matter how many servers there are.
Do you see it differently?
And yes, cost was a notable factor.
cheers Jay
Looks like a good project anyway! It'll be good to have some time servers
that are formally publicly available and maintained - I never have been sure of the state of the ihug/massey/waikato/etc. NTP servers that I've configured boxes to use in the past.
-- Nathan Ward _______________________________________________ NZNOG mailing list NZNOG(a)list.waikato.ac.nz http://list.waikato.ac.nz/mailman/listinfo/nznog
-- Jay Daley Chief Executive .nz Registry Services (New Zealand Domain Name Registry Limited) desk: +64 4 931 6977 mobile: +64 21 678840
_______________________________________________ NZNOG mailing list NZNOG(a)list.waikato.ac.nz http://list.waikato.ac.nz/mailman/listinfo/nznog
If you're needing that level of resolution surely you need to be running your own clocks not trusting the rest of the world?
MMC
On 03/09/2010, at 2:28 PM, Neil Gardner wrote:
I think the issue is that with 3 clocks, if 1 fails, you are left in a situation where NTP can't tell which remaining clock to trust.
I'd also be interested to know precisely where the servers are physically connected. While NTP is really very good at dealing with latency, it can't deal with asymmetry in the forward and return paths (it assumes one way delay = 0.5xRTT). I'd be curious to see how many people have symmetric routes to the servers.
In any case, I think it's a great move guys, and should be applauded. I have recently been playing with NTP and determining how accurately NTP over symmetric links matches GPS time and was pleasantly surprised by how close we could get. (Short story - a few tens of microseconds)
Cheers - N
On 3 September 2010 16:51, Jay Daley
I note that there are three servers - I am surprised that there is not a fourth to allow for redundancy. Is that a cost decision?
I've always understood that three is enough for redundancy. The client can tell when one goes awry by comparing with the other two. Admittedly if one goes down then the client can't tell that but we can pursue that logic ad infinitum no matter how many servers there are. Do you see it differently? And yes, cost was a notable factor. cheers Jay
Looks like a good project anyway! It'll be good to have some time servers that are formally publicly available and maintained - I never have been sure of the state of the ihug/massey/waikato/etc. NTP servers that I've configured boxes to use in the past.
-- Nathan Ward _______________________________________________ NZNOG mailing list NZNOG(a)list.waikato.ac.nzmailto:NZNOG(a)list.waikato.ac.nz http://list.waikato.ac.nz/mailman/listinfo/nznog
On 3/09/2010, at 4:58 PM, Neil Gardner wrote:
I think the issue is that with 3 clocks, if 1 fails, you are left in a situation where NTP can't tell which remaining clock to trust.
I'd also be interested to know precisely where the servers are physically connected. While NTP is really very good at dealing with latency, it can't deal with asymmetry in the forward and return paths (it assumes one way delay = 0.5xRTT). I'd be curious to see how many people have symmetric routes to the servers.
We should be able to add what you need to the web site without giving away the exact physical location. Jay
In any case, I think it's a great move guys, and should be applauded. I have recently been playing with NTP and determining how accurately NTP over symmetric links matches GPS time and was pleasantly surprised by how close we could get. (Short story - a few tens of microseconds)
Cheers - N
On 3 September 2010 16:51, Jay Daley
wrote: On 3/09/2010, at 4:24 PM, Nathan Ward wrote:
I note that there are three servers - I am surprised that there is not a fourth to allow for redundancy. Is that a cost decision?
I've always understood that three is enough for redundancy. The client can tell when one goes awry by comparing with the other two. Admittedly if one goes down then the client can't tell that but we can pursue that logic ad infinitum no matter how many servers there are.
Do you see it differently?
And yes, cost was a notable factor.
cheers Jay
Looks like a good project anyway! It'll be good to have some time servers that are formally publicly available and maintained - I never have been sure of the state of the ihug/massey/waikato/etc. NTP servers that I've configured boxes to use in the past.
-- Nathan Ward _______________________________________________ NZNOG mailing list NZNOG(a)list.waikato.ac.nz http://list.waikato.ac.nz/mailman/listinfo/nznog
-- Jay Daley Chief Executive .nz Registry Services (New Zealand Domain Name Registry Limited) desk: +64 4 931 6977 mobile: +64 21 678840
_______________________________________________ NZNOG mailing list NZNOG(a)list.waikato.ac.nz http://list.waikato.ac.nz/mailman/listinfo/nznog
_______________________________________________ NZNOG mailing list NZNOG(a)list.waikato.ac.nz http://list.waikato.ac.nz/mailman/listinfo/nznog
-- Jay Daley Chief Executive .nz Registry Services (New Zealand Domain Name Registry Limited) desk: +64 4 931 6977 mobile: +64 21 678840
Thankyou sir!
As noted by Matthew, anyone needing that level of resolution should be doing
it themselves, but I'd love to see how a real world NTP implementation on
the network here in NZ stacks up against local GPS unit so every little bit
of info helps.
Cheers - N
On 3 September 2010 17:16, Jay Daley
On 3/09/2010, at 4:58 PM, Neil Gardner wrote:
I think the issue is that with 3 clocks, if 1 fails, you are left in a situation where NTP can't tell which remaining clock to trust.
I'd also be interested to know precisely where the servers are physically connected. While NTP is really very good at dealing with latency, it can't deal with asymmetry in the forward and return paths (it assumes one way delay = 0.5xRTT). I'd be curious to see how many people have symmetric routes to the servers.
We should be able to add what you need to the web site without giving away the exact physical location.
Jay
On 09/03/2010 04:58 PM, Neil Gardner wrote:
I think the issue is that with 3 clocks, if 1 fails, you are left in a situation where NTP can't tell which remaining clock to trust.
Don't forget that there's still the atomic clock at the Measurement Standards Laboratory, which most ISPs use. It's also a non-GPS source, which means if the GPS system ever goes insane, you've got an alternate source. See http://msl.irl.cri.nz/services/time-and-frequency/ntp-server-information (That said, I do recall the MSL servers running three minutes fast not that long ago ...) I think between the two systems, that's a pretty robust time system for syncing up a stratum 2 server. -- don
I remember much debate on this back in the early eighties when we were doing work on Triple Modular Redunancy at Newcastle. Well actually I've forgotten most of it but people might like to look at this link as a starting point. http://en.wikipedia.org/wiki/Byzantine_fault_tolerance
On 09/03/2010 04:24 PM, Nathan Ward wrote:
Looks like a good project anyway! It'll be good to have some time servers that are formally publicly available and maintained - I never have been sure of the state of the ihug/massey/waikato/etc. NTP servers that I've configured boxes to use in the past.
Well I can speak for Massey's; ntp.massey.ac.nz is a round-robin for ntp1.massey.ac.nz and ntp2.massey.ac.nz both are available via IPv4 and IPv6 and both are stratum 2 available for public use. We require no notification of use they are there as a public service. -- =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= Glen and Rosanne Eustace, GodZone Internet Services, a division of AGRE Enterprises Ltd., P.O. Box 8020, Palmerston North, New Zealand 4446 Ph: +64 6 357 8168, Fax: +64 6 357 8165, Mob: +64 27 542 4015 "A Ministry specialising in providing low-cost professional Internet Services to NZ Christian Churches, Ministries and Organisations"
participants (7)
-
Andy Linton
-
Don Stokes
-
Glen Eustace
-
Jay Daley
-
Matthew Moyle-Croft
-
Nathan Ward
-
Neil Gardner