[ntp:questions] Re: time
spam at nospam.com
Wed Nov 30 15:42:19 UTC 2005
So to summarize you guys. I think that you are saying that
ntpd v3 is accurate on a gigabit network that is congested to 5-20ms is
the accuracy is a reasonable expectation. What about IEEE 1588, since this
is also ethernet bases can I get any better time accuracy with that?
"Richard B. Gilbert" <rgilbert88 at comcast.net> wrote in message
news:7sGdnUDrE9TZvhDeRVn-hQ at comcast.com...
> Bjorn Gabrielsson wrote:
>>"Richard B. Gilbert" <rgilbert88 at comcast.net> writes:
>>>>I know about NTP v3 and v4 and use it on some systems. I need a time
>>>>accuracy of < 1 ms.
>>>>I know that the linux os is compiled for something like 1 ms precision
>>>So it can be done. I think that the Motorola GPS has a great deal to
>>>do with it.
>>The motorola should carry you down towards 1us, but K was only asking
>>for a thousand times less accuracy... :-)
>>>clock would be much less stable. 10 ms is about the best accuracy I
>>>would expect from a client synchronized to a server that synchronized
>>>over the internet.
>>Even with a DSL-line - if its not overloaded - sub 1ms is easily
>>attained with good internet servers. Looking at a machine with four
>>external servers, I get see,
>>/usr/sbin/ntpq -c pe
>> remote refid st t when poll reach delay offset
>> LOCAL(0) 18.104.22.168 5 l 25 64 377 0.000 0.000
>> xxx .PPS. 1 u 219 256 377 11.476 -0.235
>> xxx .PPS. 1 u 102 256 377 17.818 -0.140
>> xxx .PPS. 1 u 217 256 377 21.575 0.203
>> xxx .PPS. 1 u 192 256 377 20.889 0.385
>>This machine usually have two GPS-refclocks and they show no
>>systematic offsets wrt the Internet servers.
> Either your internet connection, your internet servers, or both are far
> better than mine. I have broadband cable. My NTP server, Sunblok, uses
> five internet servers in addition to the Motorola GPS reference clock.
> The internet servers show systematic offsets with respect to GPS of +1 to
> +5 ms. There are also seemingly random spikes in the time received from
> the internet servers of +/- 5 to 20 ms. When the GPS is not running, ntpd
> tends to synchronize with a different server every few minutes which does
> nothing for the stability of the clock.
More information about the questions