[e2e] Simple Question on TCP Window Size

Guo, Liang guol at cs.bu.edu
Tue May 8 11:53:39 PDT 2001


Please refer to:

[FHP00] A Comparison of Equation-Based and AIMD Congestion Control. 
    Sally Floyd, Mark Handley, and Jitendra Padhye.
    May 2000. Preliminary version. (postscript, gzipped postscript, PDF). 

http://www.aciri.org/tfrc/


On Wed, 9 May 2001, Jeong-woo Cho wrote:

> 
> 
>  Hi, everyone.
> 
>  TCP reduces its window size (cwnd) to half of current cwnd when it detects loss via triple duplicate acknowlegements. So, I define the reduction ratio of current TCP as 1/2. I can guess that if reduction ration is smaller, network would be more stable. But, I think that if we set reduction ratio a little higher than current value 1/2, unfairness between UDP and TCP would decrease.
> 
>  Why don't we set the reduction ratio a litter higher?
> 
>  Is there any research related to this topic? Is there any detailed analysis on the reduction ratio?
> 
>  Thanks for reading.
> 
> 
> 
> ----------------------------------------------------------------------
>  Cho, Jeong-woo
>  
>  Communication and Information Systems Laboratory
>  Dept. of Electrical Engineering and Computer Science
>  Korea Advanced Institute of Science and Technology(KAIST)
>  373-1 Kusong-dong, Yusong-gu, Taejon 305-701, Korea
>  
>  TEL: +82-42-869-8067 (ex.107) FAX: +82-42-867-0550
>  E-mail: ggumdol at comis.kaist.ac.kr
> ----------------------------------------------------------------------
> 
> 




More information about the end2end-interest mailing list