Yesterday we talked about a key challenge for the software defined data center (SDDC) in my blog Should Energy Efficiency Keep you from the SDDC?—the need to maximize energy efficiency by lowering power consumption, Today, I’d like to turn your attention to another critical SDDC challenge, that of increased workload mobility and how to handle it.
A workload is the amount of processing that the computer has been given to do at a given time. It consists of application programming running in the computer and usually some number of users connected to and interacting with the computer's applications. The concept of workload mobility takes this definition one step further by allowing these workloads to be moved virtually between physical locations. Of course, that assumes that the data center in question has implemented virtualization, as would be the case for a SDDC.
But why would workload mobility create a challenge for the SDDC? Well, here’s the thing; with the virtualization in the SDDC there will undoubtedly be increased workload mobility. As those workloads move from one physical location to another, the result could be new problems for the broader network. One of those problems is the lack of visibility into changes made by application and virtualization teams to workloads. And that could be a huge issue; especially if those changes impact the administrator’s ability to manage the network effectively.
In a more traditional data center, one with virtualization, such a scenario wouldn’t occur. That’s because in this case the virtualization is isolated within the network and its performance is confined to its own segment. But that’s not the case for a SDDC. Here, virtualization does affect the broader network and that can make it challenging for network administrators to make sure their SDDC delivers the agility and performance they need.
Can this challenge be overcome? Fortunately, the answer is yes. What’s required is greater communication between the application/virtualization teams making changes to the workloads and the network administrator whose job it is to oversee the entire network. One way to accomplish this is to use some form of automated notification process, one that say, alerts everyone involved when a workload change has occurred and tells them exactly what that change is.
Automated provisioning is another tool that can help the SDDC deal with increased workload mobility. It works by helping to minimize any errors that occur as a result of manual management of processes in the data center.
What’s clear is that migrating from a traditional data center to a SDDC is a big step; one that requires careful forethought and planning. It also requires acknowledgement that while the SDDC boasts a number of highly advantageous benefits, it comes with challenges. Many of these challenges can be addressed, but to do so, you must arm yourself with the proper information and appropriate solutions.
If you’ve migrated to an SDDC and successfully dealt with the challenge of increased workload mobility, drop me a line at [email protected] and let me know what did and did not work for you. In the meantime, check back here for future blog posts on a range of IT-related issues.
This blog is sponsored by Microsoft.
Cheryl J. Ajluni is a freelance writer and editor based in California. She is the former Editor-in-Chief of Wireless Systems Design and served as the EDA/Advanced Technology editor for Electronic Design for over 10 years. She is also a published book author and patented engineer. Her work regularly appears in print and online publications. Contact her at [email protected] with your comments or story ideas.