March 29, 2016
On March 1, 2016 Cisco Systems published a blog post announcing the release of Cisco’s hyperconverged infrastructure solution, the HyperFlex. Cisco is heralding it as the next generation of hyperconverged infrastructure and a representation of “true hyperconvergence.”
Whether or not Cisco is overstating their case, the HyperFlex has some attractive benefits worth paying attention to.
Converged vs. Hyperconverged Infrastructure
On this blog, we have often described converged infrastructure products like the FlashStack, SmartStack, and FlexPod as complete data-center-in-a-box solutions, but hyperconverged infrastructure better fits that description.
Whereas converged infrastructure is a preapproved, pretested collection of individual components—Cisco UCS servers, Nexus switching, and a storage array—that can all be used independently from each other, hyperconverged infrastructure is a single device. You cannot “remove” the storage from a hyperconverged solution. It is inexorably tied to the rest of the box.
Hyperconverged solutions do not scale like other data center approaches. Because all components are combined into one device, purchasing that same SKU multiple times to scale isn’t much different than the days before server virtualization. Instead, hyperconverged solutions scale through the creation of “nodes.”
The Cisco HyperFlex System
Like other hyperconverged infrastructure solutions, the HyperFlex combines compute, storage, and switching into a single box.
Hardware Inside: The HyperFlex is made from Cisco Unified Computing System (UCS) servers, Intel Xeon processors, software defined storage, and software defined networking (SDN) using Cisco Application Centric Infrastructure (ACI).
- Cisco ACI: Cisco ACI empowers IT administrators to achieve great visibility, control, and automation within their network. Using advanced Nexus switches and the Application Policy Infrastructure Controller (APIC), you can create network priority policies, apply them to one or more virtual machines (VM), and enforce those policies moving forward. Cisco has described it as the next generation of SDN as well.
Scalability: The solution is scaled through the purchase of nodes in their HX200 series.
- Cisco HyperFlex HX220c M4 Node: At the smallest size, the HX220c holds 7TB of storage with 2 Intel Xeon E5 2600 v3 processors.
- Cisco HyperFlex HX240c M4 Node: The next step up expands storage and to 29TB, but has the same processors installed.
- Cisco HyperFlex HX240c M4 Node with Cisco UCS B200 Blade-Series Servers: Cisco’s third option supplements the compute power by bundling a UCS blade server with it, thereby doubling the processor power.
Federated Storage: Because storage in a HyperFlex deployment is software defined, it is federated as well. This means that the various hard disk drives (HDD) and solid state drives (SSD) in the environment are all combined into a seamless pool of resources. The HyperFlex itself serves as the brain of this multi-array pool.
Data Optimization: The HyperFlex will continuously seek out ways to optimize the stored data. Through deduplication strategies and inline compression, the HyperFlex can reduce storage consumption by up to 80%.
Like what you read?
About Mindsight
Mindsight, a Chicago IT services provider, is an extension of your team. Our culture is built on transparency and trust, and our team is made up of extraordinary people – the kinds of people you would hire. We have one of the largest expert-level engineering teams delivering the full spectrum of IT services and solutions, from cloud to infrastructure, collaboration to contact center. Our highly-certified engineers and process-oriented excellence have certainly been key to our success. But what really sets us apart is our straightforward and honest approach to every conversation, whether it is for an emerging business or global enterprise. Our customers rely on our thought leadership, responsiveness, and dedication to solving their toughest technology challenges.
For Further Reading