Hyperconverged Infrastructure HCI
Hyper Converged Infrastructure (HCI) combines servers and storage into a distributed infrastructure platform, creating flexible building blocks through intelligent software to replace the traditional infrastructure consisting of separate servers, storage networks and storage arrays. More specifically, it combines commercial data center server hardware with locally attached storage devices (spinning disks or flash memory) and is supported by a distributed software layer to eliminate common pain points associated with legacy infrastructure.
The birth of hyperconvergence
Data center infrastructure has been designed around SAN storage since the 1990s to protect data and support critical databases, and became common with the explosion of virtualization in the early 2000s.
But as organizations became more dependent on technology, traditional SAN-based infrastructure no longer met IT needs. It was complex, cumbersome, and didn't scale as flexibly or efficiently as IT teams needed to keep up with changing business priorities.
The world’s largest networking companies faced the limitations of legacy infrastructure long before the broader market emerged and developed distributed systems technology to address the challenges of scalability, reliability, and operational efficiency.
In 2009, engineers at several of these web-scale companies realized that the technologies they had developed to solve their own operational challenges were applicable to the entire market. Bringing these technologies to the reality of enterprise computing required a new approach, and the concept of HCI was born.
Today, HCI has become the infrastructure of choice for companies that want to stay competitive and evolve as the technology landscape changes. While the exact date and person who coined the term hyperconvergence is still debated, Nutanix was the first technology company to bring a dedicated HCI product to market in 2011, called Complete Cluster.
How does hyperconvergence work?
HCI converges the entire data center stack, including compute, storage, storage networking, and virtualization. More specifically, it combines commodity data center server hardware with locally attached storage devices (spinning disks or flash), supported by a distributed software layer to eliminate common pain points associated with legacy infrastructure. Complex and expensive legacy infrastructure is replaced by a distributed platform running on industry-standard commodity servers, enabling enterprises to precisely tune their workloads and flexibly scale as needed. Each server (also called a node) contains an x86 processor with SSDs and HDDs. The software running on each node distributes all operating functions across the cluster to achieve superior performance and elasticity.
Hardware platform configurations can adapt to any workload by independently scaling various resources (CPU, RAM, and storage), and can be equipped with or without GPUs for graphics acceleration. All nodes include flash to optimize storage performance, and all-flash nodes provide maximum I/O throughput and minimum latency for all enterprise applications.
In addition to the distributed storage and computing platform, the HCI solution also includes a management pane that allows you to easily manage HCI resources from a single interface. This eliminates the need to set up separate management solutions for servers, storage, storage networks, and virtualization.