How do you build out a new data center physical infrastructure?
Under the best of circumstances, building out new data center capacity is complex, expensive, time consuming and fraught with risk. Experts, engineers and consultants are needed for everything from designing the building shell, planning power and cooling systems, to commissioning. These are just the major categories. Think about the expertise needed to manage all the details that cascade from them!
If you are responsible for a small to mid-sized data center you may be faced with doing more of this yourself given the available resources. Increased complexity makes it difficult to find and retain people who possess all the essential skills needed to design and integrate the power, cooling, racks, cabling and other components necessary to complete the build correctly, and on-time. Taking on the coordination of the build-out in addition to normal responsibilities can be overwhelming.
The level of detail needed to ensure that all these elements work together can be overwhelming. One aspect that often gets overlooked is the physical infrastructure. There is a range of expertise required to ensure that these elements are integrated properly with each other to ensure optimum performance. Overlook any of the myriad details that need to be considered such as how in-row cooling units mate with cabinets, or how the cable pathway needs to be routed and supported, or how power is distributed to cabinets while the build-out is underway, and there can be significant delays and additional costs as the issues get worked out.
In an effort to reduce this complexity, many companies are investigating integrated data center infrastructure solutions that incorporate power, cooling and physical infrastructure components into a module with predetermined capacity. There are many advantages to this approach. Typically, integrated infrastructure allows companies to grow data center capacity in a modular fashion, enabling them to deploy new capacity faster and defer capital investment while safeguarding network reliability and uptime.
We have identified three typical integrated infrastructure deployment approaches taken by customers.
First is the build-it-yourself approach. This will get you what you need with significant autonomy, however only the largest companies typically have the resource expertise on power, cooling and infrastructure design skills required to do it this way.
The next choice, single supplier, is popular today because the relationship is easier to manage. But there is a significant risk of vendor lock-in and inflexibility. For instance a single supplier cannot — will not — customize an integrated solution to the customer’s specific requirements, nor will it include all elements. Most single source suppliers provide power, cooling and racks but do not include other aspects such as cabling, cable management or pathways that are typically part of a full integration. This can leave the data center manager with a physical infrastructure that does not meet desired capacity or performance requirements, especially as applications and network requirements continue to evolve from 10-40-100GbE environments. Few companies find that one-size-fits-all solutions work best.
The third approach, best of breed, appeals to companies that want the most advanced capabilities in all areas. Unlike the build-it-yourself approach, the data center manager relies on the expertise of individual suppliers to do the integration. Initially this may seem ideal however it is a headache to integrate disparate elements and manage multiple vendors. All too often, companies that choose best of breed don’t realize up front the interdependencies of functionality, long-term costs and impact on operational risk, leading to time and cost overruns.
So how are you building out your new physical infrastructure? Come back next week for Part 2 to find out about Panduit’s Integrated Infrastructure Solution.