I knew we were on to something good when a customer told me “This is so easy, it’s CTO proof.”
Early in the business, I was talking to a front-line server admin who had found that Cisco UCS made server deployment so reliable, automated and simple that he was convinced even his CTO could pull it off without breaking anything. The enthusiasm was real, and infectious, and it changed the face of the data center market.
Thinking back five years to March of 2009, when Cisco introduced UCS, the economy was still spiraling into the worst recession of our lifetime. IT budgets were being slashed. Many wondered if it was the right time for Cisco to enter a new market with deeply entrenched competitors.
In the decade leading up to 2009, computing innovation had stalled. The incumbents still had tunnel vision on the power and cooling challenges that arose out of multi-core processing in the mid-2000’s. Innovation was essentially focused on mechanical packaging: blade servers for mainstream IT and “skinless” boxes for the hyperscale crowd. Overlooked was the real problem for the vast majority of customers: operational complexity. Remember that server virtualization was rapidly spreading in nearly every data center. Again, this was originally a response to a hardware problem: processor utilization; but as everyone recognized the operational benefits, virtualization was taking hold very fast. As was cloud. Combine all this with the disaggregation of data storage from the server, which had already moved out onto the network as NAS and SAN many years before, and you had a perfect storm of complexity threatening to outpace the capacity of many IT organizations. The individual technologies in the data center were not overwhelmingly complex but tying them all together, into a system where you could land and scale an application in a very secure and available way, became the all-consuming job of the customer. Collectively, the industry had failed. In 2009, more than ever, customers needed something to help them slash OPEX in the data center and free people up to face the challenges of the day. This was the innovation vacuum that UCS had been designed to fill.
Think of UCS as the Turducken of the data center: the sum is much, much greater (and tastier) than the parts. A lot of true innovation has gone into UCS in the areas of server I/O and in fundamental advancements to server management technology. The latter is especially critical, because what is often overlooked in virtualization and cloud discussions is the underlying issue of deploying, managing and scaling the physical infrastructure itself (details, details…) The advent of UCS completed the total abstraction and automation of hardware in crucial ways that hypervisor and cloud technology still can’t acheive on their own. API-controlled data center hardware is a foundational element of modern IT innovation, and UCS started it all. This may be Cisco’s greatest contribution to the industry and charted the course for Cisco ACI in the broader data center.
Cisco’s not stopping. In the intervening five years, new innovation opportunities have appeared. Most recently, the addition of flash systems to Unified Computing in the form of UCS Invicta, which opens up a whole new chapter for what customers will be able to achieve with the System. UCS Director is taking on a pivotal role for automation across Cisco solutions and the integrated infrastructures that we construct with our storage partners. The future is so bright, our partners need sunglasses.
The team has put together this interactive timeline that commemorates many of the milestones in the first five years of UCS. Looking back over it, I can only feel proud and humbled to be associated with the team here at Cisco, our technology and channel partners, and most importantly with our customers, who have clearly proven that UCS was (and is) the right solution at the right time.