Within the past four years, hyperconvergence came about as a ground-up rethinking of all the services that comprise the data center. Hyperconvergence brings together existing storage, compute, and network switching products into a pretested, prevalidated offering sold as a single solution. With a focus on the virtual machine or workload, all the elements of an HCI (hyperconvergence infrastructure) support the virtual machine (VM) as the basic construct of the data center.
Hyperconvergence bridges the gap between the public cloud and private data center environments, making it easy to scale resources as required by business demands. At the same time, an HCI provides data protection, VM mobility, high availability, data efficiency and cost efficiency.
Drawbacks of Early HCI Solutions
Early hyperconverged systems created a simplified, distributed computing model that combined x86-based servers with software-defined storage. It was a good start, but many solutions suffered multiple shortcomings, such as:
- They treated networking as an afterthought. Specifically, first-generation HCI systems didn’t include integrated network fabric, and they didn’t support software-defined networking (SDN), which meant network resources had to be configured manually, and it limited the deployment and expansion process.
- They were based on rack server appliances. Anyone trying to scale computing and storage without getting boxed in by fixed ratios had to overprovision components, which led to unnecessary expenditures.
- They didn’t support independent resource scaling. Each compute, storage and networking resource had to be scaled simultaneously.
- They lacked compatibility with data platforms. Many data platforms are set up to work with over-the-counter file systems that weren’t intended to play nice with hyperconvergence platforms. So, without essential features such as integrated data services and data optimization functions (e.g., deduplication and compression), severe performance trade-offs occurred.
- They had limited support. For the most part, only virtualized environments and a limited number of hypervisors offer support for first-gen hyperconverged products.
How Cisco HyperFlex Surpasses Legacy HCI Systems
Within the past couple of years, however, the HCI market has exploded and has become highly competitive, too. Industry analyst firm Gartner projects, for example, the HCI market will reach $5 billion by 2019. Cisco HyperFlex Systems, a joint development comprising the integration of Cisco UCS (Unified Computing System) servers with HCI data platform software from Springpath, surpasses legacy HCI Systems in several ways. First, Cisco HyperFlex is powered by the next-generation Cisco HX Data Platform, which delivers simplified data management, continuous data optimization, dynamic data distribution and self-healing resiliency. Cisco HyperFlex Systems also are designed to support virtualized (VMware vSphere), containerized and bare-metal environments, and they offer independent scaling (i.e., pay as you grow) of compute, storage performance and storage capacity.
Before attempting to sell and implement HCIs, however, solution providers need to have fully trained technical teams and sales teams. At Ingram Micro, we have a dedicated storage and converged architecture (CA) team to assist partners with these needs, including several CA experts who can help with sales enablement and technical requirements. Contact your Ingram Micro account representative to schedule a two-day test drive workshop at a Cisco office near you.