> If you use tunneling as the protocol the real servers can be > located any where and it supports windows or any other > operating system > that you can run the application and that supports TCPIP. > [... snip ...] > I > have tested > having servers in Linux zSeries and Intel and everything > worked fine. I > know I am over simplifying things but it is really not > difficult to setup > and test. Carlos :-)
Doing this on a par with existing Unix or Windows based clustering tools is quite a bit harder than just workload distribution, which is the majority of what LVS can do -- LVS provides services similar to the external CSS boxes. To do more sophisticated clustering, it takes a LOT of hardware resources, and unfortunately, zSeries hardware is still more expensive than the commodity hardware on the discrete systems which makes this a hard sell as a viable solution. The tunneling you mention is *very* processor intensive -- exactly the point I mentioned earlier. Technically it works, but I don't think very many of us can dedicate an engine -- even a lower cost IFL engine -- to layer 2 frame forwarding, and in a significant implementation, it's not unlikely to need that kind of horsepower to keep packets moving. We need some hardware-based acceleration for this function, ASAP. -- db
