I just stumbled upon the web site for a research project called Open Cirrus, aimed at developing open source "cloud computing" infrastructure. It is a collaboration between HP, Intel, Yahoo!, and a number of academic institutions. The web site is terrible, but there is a set of interesting presentations given at a recent workshop. The most interesting is one from Andrew Chein, the VP of research at Intel, titled "Seizing the Open Source Cloud Stack Opportunity." The presentation seems to argue that we really need some common consensus on the software infrastructure (a "unified" stack). The presentation points out that there are a huge number of projects all duplicating the same functionality, and we really need only one or two pieces of software for each piece of the stack (monitoring, job scheduling, etc.). This is music to my ears, since I have been frustrated by this same problem in my own work. For the moment, Open Cirrus seems to be using the following stack: Tashi for virtual machine job management, Ganglia for monitoring, then a variety of other layers on top, primarily Hadoop related. At this point, I don't really care what people choose, as long as the resulting "unified stack" is widely adopted.