[ntp:questions] 1Gb/s network issues - was: Re: OT: GPS18x LVC failure

Unruh unruh-spam at physics.ubc.ca
Mon Oct 12 22:44:52 UTC 2009


"David J Taylor" <david-taylor at blueyonder.not-this-part.nor-this.co.uk.invalid> writes:

>"Unruh" <unruh-spam at physics.ubc.ca> wrote in message 
>news:FhJAm.47784$Db2.22788 at edtnps83...
>[]
>>>Most interesting, Bill.  Mine is a relatively cheap and cheerful device
>>>from Netgear (GS608):
>>
>>>  http://www.netgear.co.uk/ethernet_network_switch_gs605.php
>>
>>>so whether being very simple and unmanaged is likely to mean that it's
>>>performance is better or worse I leave to speculation or measurement!
>>
>> Ours are top of the line 32 port Cisco switches (University)

>To clarify; those are the ones with the poor performance?

Yes. You can see the effect at
www.theory.physics.ubc.ca/chrony/chrony.html
The roundtrip and offset is plotted there. It used to be that they were all like
monopole or dilaton (.14ms roundtrip, and .01ms offset--consistant-- getting their
time from string, the ntp refclock-- plugged into the same switch monopole has a
100Mb card ( and is a 300MHz machine) while dilaton has a Gb card and is a 2.4GHz
machine. 
It is just bizzare.




More information about the questions mailing list