On Tue, 2003-07-22 at 14:03, David Boyes wrote: > However, all you're doing is statistically selecting between a number of > fixed-speed pipes. The actual transmission of the packet occurs at the speed > of the selected pipe. Your speed increase is only proportional to a > percentage of the number of links in the bundle due to additional > transmission opportunities.
OK. But it *does* help. Some. > Packet arrival (and thus path selection) is > self-similar, not Poisson distributed. Different problem. Well, now, that's open to debate. As Bill Bitner would say, "it depends." But yes, I'll grant that, in general, for most common cases of Internettish traffic, packet arrival more closely matches a fractal, self-similar distribution than a Poisson distribution. > I wonder if the multilink PPPoE code would work over the s/390 Ethernet > implementation. That might do the trick. Beware. There, there be tentacles. Adam
