For some the biggest buzz word so far in 2009 is “cloud”, for Cisco it’s “unified”. Today Cisco announced a new server centric strategy which is underpinned by the use of a “unified computing” methodology. This new unified approach to computing represents a radical shift in how we as an industry both visualize and manage a modern virtualized data center.
For Cisco Unified Computing seems to be an overarching mantra being applied to the broader management of data center resources (compute, storage, and network elements) through a singular virtualized point of interaction. In a sense they are attempting the unification of the the entire infrastructure stack in what some are calling a unified infrastructure fabric.
By being a new player to the server industry, Cisco’s approach to a Unified Computing System is an opportunity to completely reimagine the way we look at enterprise computing. Within this new vision for the data center is an integrated management platform that combines what they describe as a “wire once” unified fabric and API which utilizes a standards compliant computing platform. Cisco’s platform has the potential to uniformly interact with all layers of the enterprise computing stack while reducing the overall management costs. Given the macroeconomic factors of the current market, cost saving will certainly be an important area of differentiation. The stated goal is to cut the total cost of ownership by 20 percent in capital expenses and up to 30 percent in operating expenses, this in itself will be more important then any data center flexibility in the short term.
What’s been exciting for us at Enomaly is envisioning the potential for a singular infrastructure abstraction that can encompass the entire infrastructure stack as well as emerging cloud centric technologies through a unified application interface (API). At Enomaly we have been saying this for awhile and fully believe that this model represents the future of computing. The capability of easily combing and assembling all the various pieces within an ever changing virtualized infrastructure provides a tremendous opportunity to adapt legacy, single tenant environments with the new reality of a multi vendor cloud centric world. In this new model Cisco seems to grasp that computing is no longer limited to a single data center or application provider, but instead companies need to navigate a hybrid computing environment that may include local & remote resources, trusted & untrusted, yet are still expected to maintain consistent security, availability and uptime.
This approach allows a series of virtual applications that act as a set of application building blocks that can be easily managed and adjusted through a consistent and unified computing fabric. In this new adaptive data center model what is acting as an application server today may be a network switch or load balancer tomorrow. In a nut shell is what the vision for a unified computing and is the new reality facing all data center hardware & software vendors in the very near future.
Through my work with the Cloud Computing Interoperability Forum (CCIF) I know first hand the effort that Cisco has been doing to create an open platform that makes extensive use of existing industry standards. I believe that Cisco fully understands that to be successful in the current environment they must embrace open reference models, and standardized API’s. This will be an integral aspect in ensuring a compatible, interoperable as well as portable application centric infrastructure now and in the future.
What virtualization & cloud computing has done to the IT industry is open its eyes to the potential for the unification of application & infrastructure stacks. These two traditionally separate components are now starting to morph into each other. In the near term it may start to become very difficult to see where your application ends your infrastructure begins, unified computing will be at the heart of solving this problem.