Take the 2-minute tour ×
Unix & Linux Stack Exchange is a question and answer site for users of Linux, FreeBSD and other Un*x-like operating systems.. It's 100% free, no registration required.

I am running a wireless network having Linux(fedora 17) at sender end.We decided TCP_veno is most useful for my network,so we are using it as default congestion control algorithm.Still, We are not getting better results.Please suggest some other possible problems that our network might have, and we decided to make txqueue length of 5000.

share|improve this question
    
To answer the question in the title: level 1 latency (whether due to propagation delays or channel congestion). –  Michael Kjörling Apr 12 '13 at 8:54
    
@MichaelKjörling-So, could you suggest any particular method that can reduce channel congestion. ? –  darklord007 Apr 12 '13 at 9:42
1  
Are you taking into account that the minimum phsically possible latentcy for a request and response to travel through a satellite is about 500 ms? –  depquid Apr 12 '13 at 12:31
    
"Wireless or Sate-lite networks?" This is really two different questions. Which one is causing the problem? If both, then you should split this into two questions and provide more details for each. Also, how you are you measuring "results" and what do you expect them to be? –  depquid Apr 12 '13 at 13:22
    
Its basically a wireless network.And we are measuring results in the terms of throughput, RTT and latency. Results that we found till now are very unsatisfactory.We also check our network configurations and they are fine.Problem is in the End user stack (for my case sender side protocol stack). –  darklord007 Apr 15 '13 at 5:32
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.