[c-nsp] TCP ZeroWindow

[Lincoln Dale]

Troy Davis wrote:

>On Tue, Aug 30, 2005 at 01:58:36AM -0500, "Cheung, Rick" <Rick.Cheung at nextelpartners.com> wrote:
>  
>
>>	I have an isolated network, with a Redhat 2.4 box on one end,
>>connected to a 3640 (12.3.15) with an x-over, bridging its FE0/0 with
>>the PPP Multilink (bundle of 8 PTP T1s), connected to another 3640 with
>>a unix type box, also with an x-over.
>>
>>	The response times from Mu1 to Mu1 is around 50ms. However, file
>>    
>>
>
>Is that reasonable latency for its physical path?  Packet serialization
>time is inconsequential here, even on a single T1, so the rest is latency.
>Depending on cable route, 50 ms RTT would be 1000+ miles as the crow
>flies.
>  
>
i'm not sure if that is an end-to-end ping of the end devices or a ping 
of the remote side of the PPP bundle..
but if its pinging the remote-side of the ppp bundle note that its not 
really a valid test of latency for a variety of reasons.

also, serialization latency is still relatively high on a T1.
a 1024-byte packet has a serialization delay of 5.3 msec out of one router.

assuming a round-trip that is already >10msec just on serialization..

of course, any form of congestion means that you have 'n x 
serialization_latency' where n is # of output queue-depth..

depending on how that T1 is provisioned & where it goes to, it may well 
be that there are multiple serialization-delays in the path ..



cheers,

lincoln.

>  
>