Re: [tcpm] TCP tuning

[Joe Touch <touch at ISI.EDU>]

Kacheong Poon wrote:
> On 02/ 4/10 12:33 AM, Joe Touch wrote:
> 
>> I'm curious about the tests described. 200ms seems very high for an RTT.
>> Even over a cell wireless link (3G), I see latencies that are typically
>> half that. I wonder what the improvement is for a 50-80ms RTT.
> 
> 
> I suspect that it depends on how your view of Internet is.  From where
> I am physically located, RTT to my company's internal network is
> around 200ms.  It is the normal RTT I live with for doing my day to
> day work.  I hope folks won't take a "country-centric" view on Internet
> traffic.  People all over the world are communicating with each other.
> The Internet is really not that "small..."

Agreed. The point is to what extent TCP is modified for fractional
benefits for specific communities. TCP is "optimized" to always work,
but not to work especially well in any particular environment.

Joe

Attachment: signature.asc
Description: OpenPGP digital signature