Virtualization – The Next Generation

There are a number of case studies that show that server virtualization and consolidation provides significantly higher utilization of assets. Cost savings occur not only due to direct equipment costs, but also due to savings in software licensing costs, rack space and data center usage and power. Over 75% of large enterprises now use at least some method of server virtualization in their data-centers.

On the client too, desktop virtualization eliminates the need for testing a home-grown application for compatibility and qualification with a number of desktop operating systems, and makes desktop OS migration significantly easier due to fewer dependencies on additional application development and testing efforts.

However, the ever-increasing drive towards more efficient computing organizations will undoubtedly take enterprise IT computing to the next steps in virtualization – where computing, storage and networks are all able to anticipate and re-configure themselves according to demand for specific computing resources.

Dynamic provisioning – where a virtual server is configured as needed, will enable IT managers in capacity planning using averages and medians instead of peaks in usage – which typically occur less than 10 hours in a year. For instance, additional e-commerce virtual servers would be instantiated dynamically on Black Friday, which usually sees the highest sales in a calendar year, and additional customer service virtual servers would be provisioned automatically to handle returns after new year for an e-commerce business.

Demand Orchestration - Additionally, business process configuration and management software will also be intelligent enough to orchestrate demand to balance the need to maintain business SLA's and optimal efficiency. For instance, a line of business file export could be configured to run any time between 12am and 4am, and will be scheduled intelligently between those times by a scheduler using historic data. Intelligent scheduling of computing demand will enable higher utilization due to more uniform usage.

Exciting times are ahead for IT efficiency in general, with virtualization evolving to squeeze more out of infrastructural investments.

Consolidate or go for grid of cheap servers?

Most fortune-500 companies have already done some consolidation. The benefits of server consolidation have been huge - the tens or hundreds of servers, each with different patch levels and service contracts contributing to low utilizations have been replaced by a few high-end servers. Nicholas Carr, in his blog asks if the server industry will suffer as a result of higher CPU utilization (resulting either from virtualization or consolidation)?

SAP's Charles Zedlewski provides a good counterargument, why the server industry will be ok after all.

The real metrics that organizations should consider are
1. Costs per processing unit,
2. Volatility of computing demand.

In the long term, enterprises of the future will go with a limited number of highly consolidated servers running some virtualization software, yielding about 60%-70% in utilization, with additional computing power available on-demand to run complex statistical and marketing programs, provided by OEM vendors like Sun, IBM or other providers using generic hardware.

I wouldn't be too worried about any drastic reduction in computing demand, simply because firms would (hopefully) buy this additional lower cost processing capacity to make better business decisions. The only server manufacturers who would truly go away are server divisions or companies that make expensive, generic hardware (Dell, HP?).

Space and power - the drivers for hardware design

Once upon a time, hardware and software costs were a significant portion of a company's IT budget. As costs of harware and software reduced, companies are more concerned about data-center costs, which are now a significant portion of IT budgets. Some of these costs are also incurred by other departments in the company, and facility managers have to take these factors into account when desgning a data-center.

Data-center costs are - real estate costs, power costs for HVAC and computer equipment.