Why is Software Defined Storage Failing to Consolidate Storage?

After enterprises decide not to use the storage mainframe described in our last blog they often next investigate software-defined storage (SDS) as a means to consolidate their storage and reduce storage costs. With SDS, consolidation occurs at the storage software layer so that all storage features, as well as storage management, are controlled through the SDS’ interface.

The Advantages of SDS for Storage Consolidation

On the surface, it seems that SDS is an ideal way to consolidate storage. Unlike the storage mainframe, SDS provides flexibility in hardware selection. IT can use SDS to manage both an all-flash array (AFA) and a hard disk-based flash array. The execution of various storage services is the same across any storage system that the SDS solution controls. For example, a snapshot is taken the same way, with the same commands whether it is on the AFA or the hard-disk-based array.

Where SDS Fall Short for Consolidation

Traditional SDS solutions fall short in helping customers achieve full consolidation of their environments. The first shortcoming of consolidating with SDS is that each SDS solution is specialized in a particular area of storage. There are SDS solutions for primary storage, SDS solutions for hyper-convergence, SDS solutions for secondary storage, SDS solutions for object storage, and SDS solutions for backup storage. There are even SDS solutions that only work in the cloud. Considering that most organizations need more than one type of storage, the requirement for an SDS solution for each storage type immediately breaks the SDS storage consolidation effort.

The second shortcoming is the costs of the typical SDS solution. While these SDS solutions can use commodity hardware to help lower costs, the SDS software itself is quite expensive. Most of the licensing models require a large upfront purchase based on capacity. If the organization for some reason needs to downsize its capacity, because of an archiving effort, for example, most SDS companies won’t allow the organization to reduce their purchase commitment other than in support renewal costs.

A final challenge is that most SDS solutions are not efficient with their use of the storage hardware. They don’t take full advantage of today’s multicore processors, and they don’t deliver the raw performance of the underlying storage media. It is not unusual for a single SSD drive to support more than one hundred thousand IOPS. However, most SDS solutions can only extract 10% or less of that number from the drives.

The primary reason for this is that most SDS solutions run on top of another operating system, either Linux, Windows or a hypervisor like VMware or Hyper-V. Not only does the organization need to manage multiple SDS solutions they also need to buy more storage hardware to get the needed performance.

Another reason for the lack of performance efficiency is that SDS vendors tend to focus on delivering a broad feature set, instead of optimizing performance. In some ways, flash media has made developers lazy, and they assume that the media solves all performance problems. In reality, the opposite is occurring. Flash is exposing inefficiencies in the software. Storage software is the performance bottleneck in most storage infrastructures.

Conclusion

When comparing SDS to the storage mainframe, most IT professionals see it as a step in the right direction because of its hardware flexibility. Upon further inspection however they find that the shortcomings rule it out for any serious storage consolidation effort. While some of these IT planners go with the storage mainframe concept, most stay with a fragmented storage infrastructure that delivers the per workload performance the organization wants although it is inefficient and still complex to manage.

In our next blog we’ll look at how IT can take the next step and move beyond SDS to universal enterprise storage software. In the meantime register for our on demand webinar “Designing a Storage Consolidation Strategy for Today, the Future and the Cloud” to get a deeper dive into the various storage consolidation strategies an how to select the right one for your organization.

Sign up for our Newsletter. Get updates on our latest articles and webinars, plus EXCLUSIVE subscriber only content.

George Crump is the Chief Marketing Officer at VergeIO, the leader in Ultraconverged Infrastructure. Prior to VergeIO he was Chief Product Strategist at StorONE. Before assuming roles with innovative technology vendors, George spent almost 14 years as the founder and lead analyst at Storage Switzerland. In his spare time, he continues to write blogs on Storage Switzerland to educate IT professionals on all aspects of data center storage. He is the primary contributor to Storage Switzerland and is a heavily sought-after public speaker. With over 30 years of experience designing storage solutions for data centers across the US, he has seen the birth of such technologies as RAID, NAS, SAN, Virtualization, Cloud, and Enterprise Flash. Before founding Storage Switzerland, he was CTO at one of the nation's largest storage integrators, where he was in charge of technology testing, integration, and product selection.

Tagged with: , , , , , , , , , , , , , ,
Posted in Blog

Enter your email address to follow this blog and receive notifications of new posts by email.

Join 25,553 other subscribers
Blog Stats
  • 1,906,076 views
%d bloggers like this: