Cisco entered the Hyperconverged Infrastructure (HCI) Appliance market in March 2016 with their HyperFlex line, using the company’s well-known UCS servers running software from startup SpringPath (which Cisco acquired in 2017). HyperFlex clusters are comprised of at least three hyperconverged nodes and as many as 32 in hybrid or all-flash configurations (but not mixed in the same cluster). Each cluster can support up to 32 UCS Server compute nodes as well, for a total of 64 nodes.
The HX220c and HXAF220c are 1U, single-node appliances that run on Cisco’s M4 or M5 UCS server platforms and support up to 8 HDDs or SSDs in hybrid, all-flash or all-NVMe configurations and Optane cache (M5 only). The HX220c is also available in an “Edge” configuration with a single CPU, three drives and a lower price point.
The HX240c and HXAF240c are 2U, single-node appliances with up to 23 HDDs or 23 SSDs in hybrid and all-flash configurations. The HX240c is also available with the M4 or M5 server platforms. HyperFlex HX Data Platform software runs as a VM on ESXi and Hyper-V hypervisors.
HyperFlex uses a log-structured, distributed file system to create a shared storage pool (and shared cache in hybrid systems) between physical nodes. Incoming data is synchronously mirrored and striped across all nodes in the cluster to satisfy data availability requirements, based on policies set. But rather than relying on data locality to maintain performance, HyperFlex moves data blocks as needed, from all nodes in parallel, to support VM read operations.
Download the full product brief now!