Data centers

12:16 PM
Bill Kleyman
Bill Kleyman
Commentary
Connect Directly
Facebook
Twitter
LinkedIn
Google+
RSS
E-Mail
50%
50%

Converged Infrastructure: 3 Considerations

If you're looking at a converged platform as a way to increase data center efficiency, here are three factors to keep in mind.

The data center is under more pressure than ever as cloud computing, IT consumerization, and business demand for efficiency and scalability continue to grow. Today, one-to-one mapping of applications and resources has become the norm. The converged infrastructure model offers a way to meet these new demands with better management and distribution of resources.

Not only does converged infrastructure unify numerous core business functions into one IT platform, it redesigns how workloads are assigned to resources in a truly virtualization-ready environment. Nutanix, Cisco (with UCS), HP, Scale Computing, and many others are among those offering converged infrastructure.

Here are three factors to weigh when considering a converged platform:

1. Everything under one roof. In some cases, it really is everything: network, storage, compute, management and more. The ability to house everything under one intelligent hardware plane has quite a few benefits. Resources are directed optimally, you have direct visibility into the entire stack, and you create very powerful, cloud-ready distributed platforms.

While having everything under one roof can be a great thing, don’t forget that there really isn’t much of a mix-and-match that can happen here. You’ll always get better usability from homogenous systems. Still, as these platforms open up, having a Nutanix perform one function while a UCS platform performs another is quite possible. To make it happen, look for third-party management tools to give you complete, agnostic visibility.

2. They’ve got APIs. Heck yeah they do! You can integrate with cloud orchestration tools, storage platforms, various cloud models, management tools and so much more. The cool factor is that these APIs are continuously being developed for even better infrastructure interconnectivity.

When you use these APIs, make sure they work. In some cases, they're openly developed APIs, while in others they’re designed to work only with similar technologies. If you’re planning on using a hypervisor orchestration tool, for example, make sure you’re able to manage your resources just the way you need to.

[Read how future data center designs need to leverage open infrastructure, software-defined technologies, and automation in "Why The Next-Generation Data Center Needs To Be Agnostic."]

3. Not all converged infrastructure systems are created equal. In general, these systems are multi-purpose platforms. For example, deploy a small Nutanix box at a branch office and you’re pretty much done as far as compute requirements. Then, couple that with a powerful follow-the-sun data center model while using the UCS platform, which can span the globe. These systems can be used for VDI, application delivery, hosting, and much more. The really amazing part is that they scale up and down very quickly. Hardware and service profiles allow you to provision resources with a click of a mouse.

However, keep in mind that not all converged infrastructure platforms are created the same or even for the same purpose. Ever hear of HP’s Moonshot platform? Here’s a chassis that shares power, cooling, management and fabric for 45 individually serviceable hot-plug server cartridges. It's particularly suitable for running cloud-based applications capable of handling a large number of parallel, task-oriented workloads. But you certainly wouldn’t want to put a large number of VDI users on this type of server environment.

Here’s the point: When you look for a converged platform, know that there can be some pretty big differences as far as use cases and design.

As you design your next-generation data center model, understand that there are many systems and optimization tools available to make your life a bit better. Whether it’s optimizing network traffic, or better utilization of storage, there are solid use cases for a variety of different platforms. They key is understanding use cases and the impact on the end user. As always, whatever infrastructure you decide to deploy, always consider security, efficiency, the impact on your business, and how your technology will help you users be even more productive.

Bill is an enthusiastic technologist with experience in datacenter design, management, and deployment. His architecture work includes large virtualization and cloud deployments as well as business network design and implementation. Bill enjoys writing, blogging, and educating ... View Full Bio
Comment  | 
Print  | 
More Insights
Hot Topics
10
Fall IT Events: On The Road Again With 10 Top Picks
James M. Connolly, Editor in Chief, The Enterprise Cloud Site,  7/29/2014
7
Have You Hugged Your Sysadmin Today?
Susan Fogarty, Editor in Chief,  7/25/2014
3
Cisco Ships APIC Controller, Reveals ACI Pricing
Marcia Savage, Managing Editor, Network Computing,  7/29/2014
White Papers
Register for Network Computing Newsletters
Cartoon
Current Issue
2014 Private Cloud Survey
2014 Private Cloud Survey
Respondents are on a roll: 53% brought their private clouds from concept to production in less than one year, and 60% ­extend their clouds across multiple datacenters. But expertise is scarce, with 51% saying acquiring skilled employees is a roadblock.
Video
Slideshows
Twitter Feed