Cisco just announced their brand new hyper-converged solution Cisco Hyperflex. In this post I want to share some of the “must know” around it.
What is Cisco Hyperflex?
Cisco HyperFlex is a flexible, scalable, enterprise hyper-converged solution. It combines software-defined networking and software-defined computing from Cisco UCS with the storage features of Cisco HyperFlex HX Data Platform Software to provide a single distributed data store. It is available with the VMware vSphere Hypervisor and delivers a unique way to build up a software defined datacenter.
How the Cisco Hyperflex architecture looks like?
In Cisco HyperFlex Systems, the data platform spans three or more Cisco HyperFlex HX-Series nodes to create a highly available cluster. Each node includes a Cisco HyperFlex HX Data Platform controller that implements the distributed file system using internal flash-based SSD drives and high-capacity HDDs to store data. The controllers communicate with each other over 10 Gigabit Ethernet to present a single pool of storage that spans the nodes in the cluster. Nodes access data through a data layer using file, block, object, and API plug-ins. As nodes areadded, the cluster scales linearly to deliver computing, storage capacity, and I/O performance.
The Cisco HyperFlex HX Data Platform controller handles all read and write requests for volumes that the hypervisor accesses and thus mediates all I/O from the virtual machines. The data platform implements a log-structured file system that uses a caching layer in SSD drives to accelerate read requests and write responses, and a persistence layer implemented with HDDs.
Hyperflex leverages Cisco UCS!!!
The new Hyperflex solution is using Cisco UCS C- and B-series as the hardware layer to run on. With every Hyperflex installation you will get a pair of Cisco 6200 Fabric Interconnects to use service profiles for all assigned nodes. By using this profiles you can make sure that every node configured in the same way and in case of a failed node it is very easy to replace it. The Cisco UCS management handles all of a cluster’s hardware management functions and is accessible through a VMware vSphere plug-in, providing a single point of control.
The new Hyperflex nodes are called HX220c and HX240c.
By combining a existing Cisco UCS system with Hyperflex you can leverage the new storage layer and use existing B-Series blades to add more compute power. A whole solution could look like the following:
Additional Hyperflex features you should know
Furthermore the new solution offers a couple of enterprise datacenter features like the integration into Cisco Application Centric Infrastructure, Deduplication, Compression, Thin Provisioning, Snapshots and Cloning capabilities.
Technical details around the Hyperflex nodes:
I will definitely check this new solution more in depth within the next couple of week and working on blog posts and also Veeam related tests and papers. So stay tuned for it.
Check out my other post on how Veeam fits into the HyperFlex solution here.
The information’s are based on the “Next-Generation Data Platform for Hyperconvergence” Whitepaper from Cisco, the “Cisco HyperFlex Systems” at-a-glance overview and my own experience.