Archives: Expert Predictions

It is unproven that the current technology will survive in a competitive but unregulated environment, with uncoordinated routing policies and global network management being just two of the major issues here. Furthermore, while frequently comments are being made where the publicly available monthly increases in traffic figures would not justify moving to T3 or even gigabit-per-second networks, it should be pointed out that monthly figures are very macroscopic views. Much of the Internet traffic is very bursty and we have frequently seen an onslaught of traffic towards backbone nodes if one looks at it over fairly short intervals of time. I am not sure whether the amount of research and development efforts on the Internet has increased over time, less even kept pace with the general Internet growth (by whatever definition). I do not believe that the Internet is a finished product at this point of time and there is a lot of room for further evolution.

For some years now we have been painfully aware of the scaling problems of the Internet, and since 1982 have lived through a series of mini-disasters as various limits have been exceeded. We have been saying that “getting big” is probably a more urgent (and perhaps more difficult) research problem than “getting fast,” but it seems difficult to persuade people of the importance of launching the kind of research program we think is necessary to learn how to deal with Internet growth. It is very hard to figure out when the exponential growth is likely to stop, or when, if ever, the fundamental architectural model of the Internet will be so out of kilter with reality that it will cease be useful. Ask me again in 10 years.