Software defined storage (SDS) promises to abstract storage services from storage hardware, freeing organizations from the “lock” of having to use specific storage hardware. But the price for this “freedom” is imprisonment to a single storage software vendor. While certainly an improvement, it is not the panacea that SDS vendors promote. Open SDS takes data center flexibility to the next step. With Open SDS a customer has not only the flexibility to select the storage hardware they want, they also have flexibility on the software side of the equation. Examples of these more flexible SDS solutions are Red Hat’s SDS solutions CEPH and Gluster.
Flexible storage software is not only good for customers, it is also good for the third party vendors looking to add value to an existing SDS feature set. One can imagine an app store type of concept where Open SDS vendors can present a variety of extensions to the current SDS capabilities. In this scenario everyone wins. The vendor that owns the Open SDS support can offer more reasons for the customer to do business with them, the third party vendors can respond faster to customer needs because they don’t have to recreate an entire storage software stack, and the customer wins because they should see greater variety and innovation in the options available.
Data Reduction for CEPH/Gluster
An excellent example of the innovation that an Open SDS solution can foster is found in Permabit’s recent update of its VDO product. VDO or Virtual Disk Optimizer is a deduplication and compression solution and the latest version of VDO is tested and certified with Red Hat CEPH and Gluster. VDO has been on the market for over five years, and we did an extensive test of the solution a couple of years ago. Thanks to its OEM roots, VDO is potentially the most heavily tested data reduction solution on the market today. To learn more about CEPH and Gluster see our article “Product Analysis: Open Software Defined Storage – Ceph or Gluster?”.
Permabit designed their data reduction solution to provide high performance, so high as to not interfere when used in all-flash configurations. Bringing data reduction to CEPH and Gluster opens up a world of possibilities for data centers. Imagine a CEPH solution with all-flash, or mostly flash, supporting a virtual or containerized environment. Or a Gluster solution running parallel analytics processing on IoT data hosted on flash storage. Both approaches with Permabit VDO will also substantially increase data center density, another win for data center managers! While both CEPH and Gluster have supported flash for a long time, Permabit data reduction technology makes their use much more competitively appealing from a price perspective without impacting performance.
Pricing That Makes Sense
One aspect of third party solutions that usually ruins their adoption is the price. Most of the time these vendors want so much for their solution that IT professionals decide to take a pass. Permabit is a clear exception here. It is pricing the solution at an almost unheard of $199 per 16TBs of data and $3000 for 256TB of data with annual maintenance at the same price points. Using Permabit’s very conservative 2.5:1 efficiency claim, the 256TB license/maintenance costs would then enable 256TB of storage to act like 640TBs of capacity representing 384TBs in savings. Last time I checked you can’t get 384TBs for $3000.
We are not sure who the biggest winner is here. Red Hat, especially as they mature and simplify CEPH/Gluster, have another advantage over many other SDS solutions on the market today. It is now Open and Optimized. Permabit’s VDO at these price points should be an absolute no brainer for CEPH/Gluster customers. And customers are getting more than double their storage, without impacting performance for a fraction of the cost of actually buying it.