Reading Time: 3 minutes

Scale Computing is an international company, with the HQ at Indianapolis and several offices worldwide (Silicon Valley, London, Paris, Toronto, Dubai). Their HC3® platform is an hyperconverged solution that can be used for small- and medium-sized businesses but also in some enterprise departments with a simple (and different) approach to virtualization and storage.

I’ve wrote about their solution one year ago (see the post Scale Computing make virtualization simple (and different)), and was interesting met them during the last A3 Communications Technology Live!

Scale Computing integrates storage, servers, and virtualization software into an all-in-one hardware+software appliance based system that is scalable, self-healing and as easy to manage as a single server.

Scale Computing’s HC3 virtualization platform is a complete ‘data center in a box’ with server, storage and virtualization integrated into a single appliance to deliver simplicity, availability and scalability at a fraction of the cost of similar solutions.

There are three different type of appliances with different compute and storage size:

  • HC100: where each nodes has 4 cores, 32 GB RAM and 4 Enterprise SATA disks (2TB, 4TB, 8TB)
  • HC200: where each nodes has 6 cores, 64 GB RAM and 4 SAS disks (10k or 15k rpm, with sizes 2.4TB, 3.6TB, 4.8TB, 7.2TB)
  • HC400: where each nodes has 12 cores, 128GB RAM and 8 SAS 10k disks (4.8TB, 9.6TB, 14.4TB)

Each nodes has 2×1 Gbps or 2x10Gbps NIC cards (HC400 has only 10 Gbps NICs) and you can start to build your high availability cluster from 3 nodes and scale as you need.

The interesting aspect is that also the virtualization stack is included in the appliance, buy using a customized version of KVM. In this way all is simple and integrated and included with the appliances.

You cannot change the hypervisors (like with Nutanix Acropolis that can replace the KVM part with VMware vSphere or Microsoft Hyper-V), but the intent is to have an integrated and simply solution for the SMB market with companies with 5-30 servers.

For this reason actually flash or hybrid solution are not covered with the existing appliances and replications across node is just like a RAID10 across the network. In the futures there can be some interested in features like hybrid flash or erasure coding.

Also the existing deployments confirm that SMB user cases are the most typical: 1,000+ Clusters, 3,500+ Systems, that means mainly a 3-4 nodes cluster (considering that 3 is the minimum).

Moving to the enterprise require more integration (possible with API, but not enough), a complete certification of product compatibility (like SAP or Oracle, for example), cross hypervisor support and so on… But again is not the main target, at least not yet.

And for sure some improvements are needed for the SMB: for example having a 2 nodes configurations could be really valuable in order to address also the small companies or the remote office / branch office (ROBO) scenarios. On this aspect they are considering to define a new minimum configuration.

Disclaimer: A3 Communications has invited me to this even and they has covered also the travel expenses, but I am not compensated for my time and I’m not obliged to blog. Furthermore, the content is not reviewed, approved or published by any other person than me.