02 Nov What does ‘Hyperconvergence’ mean, exactly?
Hyperconvergence as a technology is in the buzzword stage, much the way “cloud” was half a decade ago. People want to know about it, and vendors ask whether you’re thinking about it. In the same way the (still) rather ambiguous term “cloud” needs to be defined, the question that is always hovering over HCI (hyperconverged infrastructure) conversations is: “What does ‘hyperconvergence’ mean, exactly?”
At its core, hyperconvergence is a quest for simplicity and efficiency. Every vendor with a hyperconverged platform approaches this slightly differently, but the end goal is always the same: combine resources and platforms that are currently disparate, wrap a management layer around the resulting system, and make it simple. So, what are the disparate resources being combined, and how do HCI vendors make it simple?
Consider an enterprise data center from the past few years, or maybe just poke your head in your own data center. It contains clusters of “compute” (typically x86 server platforms) and one or more monolithic storage arrays. There’s a deduplicating backup appliance, a backup software, a replication platform, and a few WAN accelerators. Hyperconvergence, on the other hand, leverages a return to direct-attached storage (DAS). It uses software to combine varying platforms (compute, storage, backup, multi-site federation, and so on) into one platform.
A common misconception is that ‘hyperconvergence’ means servers and storage in the same box. Pooling that storage is a good example of SDS (Software-defined Storage) which is a part of hyperconvergence, but it is not the whole picture. HCI aims to bring as many platforms as possible under one umbrella, and storage is just one of them.
Once these once disparate systems are owned by the hyperconvergence platform, they’re accessible from the same management interface as all the other systems. Different vendors do this piece differently; it may be a dedicated user interface or it may be a plugin to an existing interface. Whatever the foundation, the end goal is to manage everything (compute, storage, backups, replication, snapshots) from one management interface. This provides the simplicity that an administrator is coming to expect.