> but I certainly can't imagine trying to do a company that solves this problem. or I should say I keep trying to and just seeing failure.

Yep, I don't think a system for this is something you can sell by itself, unless you're selling mainframes. You'd need to be selling an application that needs the system to run.

I don't really know what kind of application really needs SSI clustering though. I've used clustering in a few different domains, but never really felt like SSI would be a clear win.

Maybe it's chicken and egg though? If SSI clustering was more available, would applications that really leveraged it arise?

The process migration + use spare capacity on the corporate network case feels potentially compelling, but only with the right kinds of workloads ... and that would be hard to sell.