Academic and scientific research often involves the construction of mathematical and numerical models to solve scientific and engineering problems. Traditionally, these complex and intensive computational models have been implemented on super computers or high-performance computing (HPC) infrastructure. These models are difficult to setup and operate, and can create a painful experience for researchers who often have to wait in a long line to use their university’s super computing infrastructure, whether it’s for a few hours or a few days.
There are some in the hardware community that question the value of the Open Compute Project and believe that it represents a “race to the bottom” from a hardware design standpoint. These people seem to feel that any distinctive, interesting or innovative design principles will be pushed away due to competitive risks favoring something that solves for only the most basic or rudimentary requirements. I completely disagree with this sentiment.
Open-sourced hardware is hard. Open sourced software is more accessible for people to contribute to: a person can go grab the software out of the repository and work on it at night or the weekend and then run the commits up. There is a different kind of commitment to produce a something that is a physical resource or a device. It is sometimes confusing how people can get involved to shape this environment; however, it is fundamentally important for people’s voices to be heard.
Here at Rackspace we view OpenStack as the operating system of the cloud. We believe that the openness and large community that has developed around OpenStack provides value for consumers by empowering them with flexibility and optimization options. Consumers can use OpenStack to power an on premise cloud or a cloud hosted by a provider.
The Open Compute Project is working hard to generate and develop a leadership stance on environmental stewardship. Facebook, one of the founders of Open Compute, has made significant accomplishments by establishing industry leading Power Usage Effectiveness (PUE) metrics (the ratio of the power delivered to a facility that is available for servers to consume).
Rackspace is involved with the Open Compute Project on a number of different activities. One of my main purposes right now is to help shape the Open Compute environment to insure that designs are optimized for our customers. This includes developing rack designs; making sure that the Open Rack project provides the necessary resilience and flexibility; shaping the motherboard designs to ensure that the I/O attributes are in place to provide the connectivity resources that we need; and more.
The Facebook-founded Open Compute Project opens up the hardware specs for servers and datacenters – the physical components of the infrastructure stack. It’s an ambitious project that takes the concepts of open source software and applies it to the hardware space.
It has been just over a year since Facebook shook up the server hardware and data center industry by releasing its custom high efficiency infrastructure designs to the world. Rather than simply showcase its accomplishments, the Facebook team chose to formulate a new open source project seeded with the results of its efforts. Thought leaders including Johnathan Heliger, Frank Frankovsky, Yael Maguire, Amir Michael, Gio Coglitore and others rallied efforts producing design specifications and forming a collaborative working community of consumers and contributors that would ultimately culminate in the creation of the Open Compute Foundation, an entity to manage the Open Compute Project (OCP).