The 'So What' Of The Software-Defined Data Center

The concept of the software-defined data center (SDDC) rose to prominence during VMworld 2012, with VMware touting it as the next big leap forward in IT management. With VMworld 2014 just weeks away, the SDDC has turned out to be a very big deal.

The term refers to abstraction of software from hardware for efficiency, thereby reducing complexity. More specifically, it means an IT facility where the networking, storage, CPU and security are virtualized and delivered as a service. Furthermore, the provisioning and operation of the entire infrastructure is entirely automated by software. This integration and automation brings everything in the infrastructure together and allows for a high degree of flexibility.

SDDC in the marketplace
More and more companies are setting up data centers or thinking of data centers in the "software-defined" way. A few examples of how people are defining it and doing things in the SDDC space include what VMware and Cisco are doing.

VMware says the mobile cloud era presents new challenges. To meet this challenge, IT organizations need to virtualize the rest of the data center so all infrastructure services become as inexpensive and easy to provision and manage as virtual machines. The answer is the SDDC: the ideal architecture for private, public, and hybrid clouds. VMware offers several options for implementing the SDDC architecture in a private data center, as a private cloud or hybrid cloud. 

SDDC can be implemented all at once, but is typically done in phases, where compute, network and storage resources are used to deliver abstraction from hardware, pooling and automating all of those data center activities. In addition, a key feature of the SDDC is automating the management of resources, so that policy-based management of compute, storage and networking are simplified.

Cisco developed the Cisco Open Network Environment (ONE) for network programmability, which is intended to solve traditional data center limitations. An entry on the Cisco blog states one of the strategies is to "build scalable multi-tenant cloud infrastructures with operational experience between physical and virtual." In layman's terms, this allows data center managers to set policies that can reorder network traffic based on users, applications, and even specific devices.

Evolution of SDDC
This rising popularity of the SDDC and its uptake in the enterprise means related concepts have begun to appear to abstract additional data center functions from hardware. For example, software-defined networking, mentioned above, has gained popularity as an approach in which networking control is decoupled from hardware and controlled by a software application.

Because many IT organizations are becoming comfortable with the concept -- and implementation -- of SDDC, the adoption of other software-defined data center concepts is growing. One new approach to data protection in the data center is software-defined disaster recovery, or SDDR. SDDR represents complete hardware abstraction, meaning disaster recovery is now no longer tied to hardware.

Typical array-based replication solutions are LUN-based and volume oriented, and become inefficient in virtualized environments, where virtual servers are in motion and are not directly aligned to a specific hardware resource. SDDR divorces disaster recovery from the storage layer. Allowing for replication can get super-granular, and even protecting one virtual machine is possible.

One of the key factors driving SDDR is cost reduction. We've had customers reduce LUN count and cut their storage footprint by 40% by switching to SDDR. This is simply done by replicating in the virtual layer itself, as opposed to replicating LUNs. Customers no longer need one-to-one matching environments at their target, or replicated site.

To be specific, implementing the concept of SDDR extends the benefits of virtualization, such as flexibility and granularity, to disaster recovery. The management of DR is also greatly improved, as SDDR incorporates replication and recovery of multiple sites and can be initiated and maintained from one central location.

Individual virtual machines or entire virtualized data centers can now be moved to and from any physical location, either to avoid disasters or as part of scheduled data center relocations. SDDR is also a great entry point for companies that possibly have never considered cloud-based services before because of the significant savings in capital and operational costs using SDDR to replicate to a cloud or hosted environment.

Overall, the primary benefit of software-defined functions is that the person managing the data center can more efficiently utilize resources while providing better service to the company. Software-defined anything also makes both providing and consuming services better because it removes the dependency on hardware, supports multiple sites, streamlines management, and leverages virtualization to its fullest extent.

Ultimately, the industry is finding out through this software-defined movement that hardware is a commodity and the days of tying any data center application to hardware are over.