Hyperconverged infrastructure

Historically, to keep pace with the growth of business applications and the terabytes of data they generate, IT resources were deployed in a silo-like fashion. One set of resources has been devoted to one particular computing technology, business application or line of business. These resources support a single set of assumptions and cannot be optimized or reconfigured to support varying usage loads.

The proliferation of IT sprawl in data centers has contributed to rising operations costs, reducing productivity, and stifling agility and flexibility. Maintenance and operations can consume two-thirds of an organization’s technology budget, according to a 2009 InformationWeek survey of executives in 500 companies with annual revenue over $250 million.^[2] That leaves just a third of the budget for new IT initiatives. This ratio prevents IT from supporting new business initiatives or responding to real application demands.

A converged infrastructure addresses the problem of siloed architectures and IT sprawl by pooling and sharing IT resources. Rather than dedicating a set of resources to a particular computing technology, application or line of business, converged infrastructure creates a pool of virtualized servers, storage and networking capacity that is shared by multiple applications and lines of business.

Converged infrastructure

Converged infrastructure is a way of structuring an information technology (IT) system which groups multiple components into a single optimized computing package. Components of a converged infrastructure may include servers, data storage devices, networking equipment and software for IT infrastructure management, automation and orchestration.

Hyperconverged infrastructure (HCI) is a software-defined IT infrastructure that virtualizes all of the elements of conventional “hardware-defined” systems. HCI includes, at a minimum, virtualized computing (a hypervisor), a virtual SAN (VSAN) (software-defined storage) and virtualized networking (software-defined networking). HCI typically runs on commercial off-the-shelf (COTS) servers.

Differences

The primary difference between converged infrastructure (CI) and hyperconverged infrastructure is that in HCI, both the storage area network and the underlying storage abstractions are implemented virtually in software (at or via the hypervisor) rather than physically, in hardware. Because all of the software-defined elements are implemented within the context of the hypervisor, management of all resources can be federated (shared) across all instances of a hyper-converged infrastructure.