"Wire once and walk away" marks a change in how you run your data center, by creating an infrastructure with a fraction of the typical cabling and management demands. With this approach, the days of filling your data center with physical servers that each have two power supplies, four or more Ethernet cables and multiple fiber connections are over.
The phrase "wire once and walk away" has been around for a while, but technology -- server virtualization, blade servers and converged infrastructure -- has only recently advanced to the point where this approach can become a reality.
Server consolidation through virtualization was the first step in this direction. By running multiple server instances on a single device, you reduced power usage, rack space, cabling demands, cooling requirements and more, which lowered costs. Server virtualization revolutionized data center efficiency, but some hardware manufacturers realized that more could be done.
Next up were blade servers, which were still working to prove their relevance and value, because they required some rethinking of data center design and server management. But when you added the server consolidation benefits of virtualization with the physical consolidation perks of blade computing, things began to click. Still, the "wire once and walk away" approach required more, because blade servers alone didn't offer the technological advances needed to significantly reduce cabling and management overhead.
That brings us to the present and new converged infrastructure products, such as Cisco Systems' Unified Computing System (UCS) and Hewlett-Packard's BladeSystem Matrix. These new technologies combine network and storage communications and take advantage of blade server technologies, bringing about new levels of data center efficiency.
And new management tools allow you to carve up the bandwidth on these systems and allocate it to blades in a very simple manner. Quite literally, once the blade enclosure is racked and cabled, there is no longer a need to physically manipulate anything in the chassis cabling -- the very definition of the term "wire once and walk away."
Skeptics approach converged infrastructure with caution, concerned about the potential learning curve, vendor lock-in and long-term supportability. These concerns are typical with new technologies. HP addresses concerns about the learning curve by making converged infrastructure an optional component of its c-Class blade platform. And Cisco tackles the issue of vendor lock-in by using open standards.
The potential savings and improved management functions of converged infrastructure are very real. You may not find these products in a late-night infomercial, but they are going to change the way you design and manage your data center.
About the expert
Mark Vaughn (MBA, VCP, vExpert, BEA-CA) serves is a consulting principal for data center virtualization with INX, a Houston-based solutions provider. Vaughn has more than 14 years of experience in IT as a Unix administrator, developer, Web hosting administrator, IT manager and enterprise architect. For several years he has focused on using the benefits of virtualization to consolidate data centers, reduce total cost of ownership, and implement policies for high availability and disaster recovery. Vaughn is a recipient of the vExpert award for both 2009 and 2010, and he has delivered several presentations at VMworld and BEAWorld conferences in the U.S. and Europe. Read his blog at http://blog.mvaughn.us/.