[Iccrg] Question on RFC 2988 - TCP Retransmission timer

[Lars Eggert]

Hi,

On 2007-9-20, at 0:58, ext Sushant Rewaskar wrote:
> We passively analyze more than 2.8 million real world connections  
> using a
> very detailed passive analysis tool named TCPdebug
...
> Based on our experiments we have identified several changes to TCP  
> like -
...
> (ii) Reduce minimum retransmission timeouts to 200ms or lower

did any of these traces include GSM or UMTS access links? Because  
they have transmission delays that can be significantly higher than  
200ms.

This is the first few lines of a quick traceroute I took just now  
over my UMTS link:

# traceroute 128.9.160.161
traceroute to 128.9.160.161 (128.9.160.161), 64 hops max, 40 byte  
packets
  1  213-161-41-72 (213.161.41.72)  245.816 ms  223.566 ms  197.966 ms
  2  213-161-41-82 (213.161.41.82)  207.938 ms  230.286 ms  230.970 ms
  3  rl032002.radiolinja.fi (213.161.32.2)  236.970 ms  229.547 ms   
225.996 ms
...

GSM is much worse.

Lars
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 2446 bytes
Desc: not available
Url : http://oakham.cs.ucl.ac.uk/pipermail/iccrg/attachments/20070920/204febd3/smime-0001.bin