Managers of industry-standard, system-based data centers have dreams of moving beyond a static environment. They imagine what it would be like if their data center did the following six things that a dynamic data center does:
1. If it automatically found unused, and therefore wasted, resources on a moment-to-moment basis. Included on this list of unused and wasted resources are systems, software, storage and networks.
2. If it automatically repurposed those resources in a coordinated, policy-based fashion in order to make the most optimal use of them. High-priority tasks would be given resources first.
3. Once repurposed, the data center resources would automatically be assigned to useful tasks.
4. Each workload would be provided with the resources it needed without being able to interfere with or slow down other tasks.
5. Unneeded resources would be freed up so that they could be powered down to reduce power consumption and heat generation if the organization so desired. These resources could be powered back up, provisioned for the tasks at hand and put to work as needed later.
6. New resources would need to be added only when currently available resources were really exhausted.
What's clear is that everything must adapt in real time, in a coordinated way--otherwise problems are simply being shuffled about rather than being solved.
How to achieve your dreams of a dynamic data center
Over the past few years, virtualization and automation products have become available for industry-standard systems, operating systems and applications. It is now possible for an organization to work with a "logical" or "virtual" view of resources. This logical view is often strikingly different than the actual physical view.
What does this really mean? System users may see a single, physical computer as if it were many different systems running different operating systems and application software. Or they may be presented the view that a group of systems are actually a single computing resource. Other virtualization technology may allow individuals to access computing solutions with devices that didn't exist when developers created an application. It may also present the image that long-obsolete devices are available for use in the virtual environment, even though none are actually installed.
In the end, the appropriate use of these layers of technology offer organizations a number of benefits. These benefits include improved levels of scalability, reliability and performance, far greater agility than possible in a physical environment, and more optimal use of hardware, software and staff resources. This requires IT decision makers to think beyond the server to achieve broader goals.
There have been many successful implementations of this type of virtualization using products from several suppliers. There are products available that act as an operating environment for the whole data center. Resources are discovered automatically and can be automated to meet the organization's own service level objectives and policies.
IT managers who find themselves forced to grapple with the issues mentioned in this article would be well-advised to learn more about how products of this type could help them meet their objectives, while lowering their overall costs of computing though the deployment of a dynamic data center environment.