Momentum is a powerful force, and momentum coupled with synergies cannot be denied.
Today IBM is announcing their entry into the Container Data Center space. Starting with their newly released iDataPlex high density server product, and riding the wake of Microsoft’s widely publicized embracing of Data Center Containers, the recipe was there for a product combining the two concepts.
iDataPlex is a water cooled system of very high density computing which is said to squeeze twice as many servers as conventional systems into the same amount of floor space while reducing power demand by as much as 40 percent. This is a solution in demand by a wide range of business applications, and tracks the trend of massive utility computing platforms in the implementation phases across the globe.
Now we also have the decision by IBM to configure 40 foot containers with iDataPlex infrastructure. The trend is now undeniable, with product releases over the past months
from Verari, Rackable, Sun, et. al.,… and the high profile deployments using these solutions.
I think that the Container Data Center concept holds a lot of potential for a number of reasons. This potential is reflected in the needs I’ve seen in the Clients we serve in our consulting firm.
Modularity is one dimension of this potential. Our Clients are often planning the construction of a data center facility to accommodate long term business growth. Data centers are expensive enough, let alone building excess capacity that is not participating in revenue generation. The application of Containers facilitates an option to grow incrementally, and could reduce a large amount of planning risk.
Real Estate is another dimension. The concept of Containers gives an out-of-the-box option to plan for land without the traditional data center building. This could have a significant favorable impact on the construction budget in some cases.
Another dimension is Disaster Recovery. The Container option may be an attractive fit for many enterprise DR scenarios. For many enterprises, DR is not an inherent service that exists from the moment the Business application lights up for users. Sadly, it is often a separately funded risk mitigation project well after the fact. A Container based solution may offer options that are favorable in terms of implementation time as well as for operational costs.
A few years ago, I was tasked with addressing Business Continuity and Disaster Recovery options for Home Depot stores that were at risk for weather-related outages (ie, hurricanes in Florida and the US Gulf Coast). At that time, I collaborated with Intel, HP, Wolf Coach, and Cisco to create a straw-man design for a relocatable data center. That data center was, for that application, quite small in terms of quantity of equipment and compute capacity. I’m certainly not claiming to have birthed the Container Data Center concept, mind you, but rather adding the perspective of mobility and temporal deployments of “contained” data processing footprints.
The Container implementations in the news are largely for high profile data center projects, that would get press coverage whether using Containers or not. If you have an experience with Container Data Centers I’d greatly welcome the feedback.
