Why Is Storage Hardware Sprawl Worse Than Ever?

Once thought eliminated through storage networking via storage consolidation, storage hardware sprawl is worse than ever. As we discussed in our  webinar, “How To Stop Storage Hardware Sprawl“, there are several reasons for this. First, there are more workload types today, each with its own unique I/O requirement. Second, there are more storage system types, ranging from all-flash arrays to server side networks powered by flash, hybrid arrays, scale-out NAS, object storage systems and of course, legacy disk storage arrays. The impact of this sprawl is increased storage cost and more difficult storage management. Can storage hardware sprawl be eliminated or at least reduced?

The Good Old Days

Click To Watch On Demand

Click To Watch On Demand

In the middle part of the last decade (2003-2006) storage systems had reached a point where a single system could be counted on to fulfill the majority of the storage capacity and performance demand that an environment had. Most if not all of the servers connected to the storage system were running dedicated applications, each with dedicated I/O channels. These storage systems virtualized their underlying capacity so that all the drives in the system where available to the connecting servers. Even though these drives offered essentially the same level of performance, having all the drives assigned to all the servers helped keep performance acceptable. The capacity assigned to each of those servers was thinly provisioned and many of the systems were “unified”, providing both file and block services. In short, IT life was good, it just wasn’t very efficient.

The Era of Do More With Less

Around 2006 virtualization began to move out of the shadows of the IT test and development lab and into production. Suddenly, each physical server was no longer dedicated to one application but ran dozens of workloads, all sharing its single connection. Server virtualization, except for the storage part, worked so well we looked beyond servers and thought about virtualizing desktops to reduce the cost of end-user support. At the same time, those end users were creating millions and millions of files that all needed to be stored and shared. Finally, new workloads started to appear that dealt with business analytics where billions of very small files needed to be analyzed and categorized. Suddenly, more data than ever was being created and all of it needed to be stored, potentially forever.

The goal of most of these initiatives was to do more with less and with the rise in compute power and the potential of virtualization these goals made sense. The resulting virtualization initiatives found an accomplice in flash memory which could easily respond to the massively random I/O workloads that virtualization was creating. Storage media went from the slowest thing in the infrastructure to one of the fastest. This enabled the dozens of virtual servers (or thousands of desktops) on a physical host, the scanning of billions of files rapidly and to scaling of databases to new user count levels.

Unfortunately, on the way to doing more with less, all of these initiatives, while they may have reduced server hardware sprawl, have led to storage hardware sprawl. In part two of this column, we discuss how storage hardware sprawl has gotten worse, how flash storage actually let us down and how we can start to fix it.

In the meantime, sign up for our on-demand webinar “Stopping Storage Hardware Sprawl” and join experts from Storage Switzerland and Coho Data as we discuss what storage hardware sprawl is, why it’s getting worse and most importantly, how it can be stopped. As always we have most of the webinar time set aside for questions and answers so you can hear from other users on what their storage hardware sprawl problems are.

Also remember that by registering for one of Storage Switzerland’s webinars you gain access to our over 60 on-demand webinars featuring top CEOs and the Storage Switzerland analyst team discussing topics like: all-flash arrays, deduplication, SSDs, software-defined storage, backup appliances, data protection, object storage, cloud storage and storage networking. Many of these webinars also feature exclusive white papers that are only available to webinar attendees.

Click To Register For Our On-Demand Webinar
Click To Watch On Demand

Click To Watch On Demand


Twelve years ago George Crump founded Storage Switzerland with one simple goal; to educate IT professionals about all aspects of data center storage. He is the primary contributor to Storage Switzerland and is a heavily sought after public speaker. With over 25 years of experience designing storage solutions for data centers across the US, he has seen the birth of such technologies as RAID, NAS and SAN, Virtualization, Cloud and Enterprise Flash. Prior to 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
2 comments on “Why Is Storage Hardware Sprawl Worse Than Ever?
  1. […] As we discussed in our last column “Why Is Storage Hardware Sprawl Worse Than […]

  2. […] Click here to read the whole article storageswiss.com […]

Comments are closed.

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

Join 22,245 other followers

Blog Stats
%d bloggers like this: