RE: Throughput [7:57158]

2002-11-09 Thread s vermill
Cliff Cliff, You are correct that the simple "file size * 8 / BW" isn't always appropriate. I would venture to say that at 64 kbps, you aren't likely to have many of the below problems, but it's good to have an understanding of the issues regardless. 1. RTT: In all likelihood, we're dealing with

RE: Throughput [7:57158]

2002-11-11 Thread Priscilla Oppenheimer
Cliff Cliff wrote: > > Dear all, > > One of our customer want to know the simply way to calculate > the throughput in their link. Calculating throughput can be difficult. Your customer should measure actual throughput for a typical case, using a protocol analyzer or one of the many other tools f

RE: Throughput [7:57158]

2002-11-11 Thread Cliff Cliff
HI All, Thx for your reply and I really appreciate your explaination. I know that my customer is very difficult to use the whole BW in the high delay time environment. But I need to tell him what's the max throughput. So that's why I need to tell him how they can do in their computer / network

RE: Throughput [7:57158]

2002-11-11 Thread Priscilla Oppenheimer
The default window size for modern implementations of TCP on modern operating systems is bigger than 4080 bytes anyway. No change will probably be necessary. The window size varies as clients and servers ACK data, but it should start out at 8192 or greater, depending on the OS. Are you wondering a