When you move from physical to virtual desktops, you are at the same time moving from a distributed to a centralized storage environment. Chances are very good that most of the storage devices attached to your current physical desktops are IDE-based storage. Your centralized storage, however, will be based on enterprise-class storage, not only because you will need that to support the scalability you require, but for a number of other operational reasons that have to do with performance, high availability, recoverability, and manageability.
IDE-based storage is widely available for roughly 10 cents/GB through retail outlets like Fry's. Enterprise-class storage is going to raise the cost per GB of storage a minimum of 30x if youre looking at SATA based storage, and as much as 100x if you're looking at FC-based storage that supports critical centralized storage functionality like high performance caches, sharing, multi-path I/O, and disk-based snapshots. You can't create the centralized data store you need for VDI projects without using enterprise-class storage technology. Therefore, you will need to factor in the necessary additional costs when budgeting for your VDI storage platform.
As if paying a lot more per GB for your storage isn't bad enough, you are also going to need more of it. If your administrators use their experience configuring storage on physical servers to estimate their requirements in VDI environments, you will generally be surprised to find that you need to purchase 30-50 percent more storage to meet your performance requirements.
Why does this happen? Basically, the I/O patterns generated in VDI environments, where you may have 50-70 virtual desktops, each with their own individual I/O streams, running on a single physical server, end up being significantly more random and significantly more write-intensive than they are in physical environments as you write them down through the hypervisor and out to disk. Spinning disk performs at its worst in very random, very write- intensive environments, with the slowdown being worse the more random and write-intensive they are. For a given performance requirement (e.g. I/O's per second or IOPS), the storage configuration that met your needs on a dedicated application server will appear to run at least 50 percent slower in a VDI environment, and often much more. As administrators add more hardware (e.g. more disk spindles, solid state disk, etc.) to get back to their original performance target, the costs mount. You may meet your performance goals before you run out of storage budget, or you may not, but either way, you end up spending a lot more on storage than you probably originally planned.
If you're like most IT shops, at least part of the reason you're looking at VDI is to decrease the management and administrative costs associated with tasks like patch management, upgrades, and enforcing some level of standardization in the desktop tool sets. Moving to a centrally-managed environment where virtual desktops are served out on demand can make a huge impact here, but storage administration is almost always an area where costs increase.
Realize that you're moving from a physical desktop environment where you probably weren't managing storage much (if at all) to one where you now have IT resources in a centralized location managing that same capacity on enterprise-class storage. There is no doubt that there are benefits to that in terms of meeting performance requirements, enforcing security, and providing recovery for perhaps critical corporate assets, but there is clearly an additional cost here where there may have been none before.
On top of this, you will be incurring additional management overhead against a baseline storage capacity that can easily be 30-50 percent larger than it was before (when you weren't managing it). Backup is a case in point. You probably weren't backing up your desktop storage before, and it's unlikely that end users were backing it up either. By centralizing it, you can ensure that it is regularly backed up by skilled administrators. You might have had 10TB that you weren't backing up before, and now may have 13-15TB being backed up. You'll need to factor in the additional costs of this secondary storage required to support data protection operations.
At this point it should be pretty clear that you are going to have to do some significant thinking about how you manage storage in your VDI environments if you are going to keep costs under control. Once you have storage under the central control of skilled administrators, there are a number of technologies you can bring to bear to reduce your overall storage requirements. These include, but are not limited to, virtual storage architectures that increase the IOPS per disk spindle by 3x - 10x, storage capacity optimization technologies like thin provisioning and data deduplication that can save up to 90 percent on capacity requirements, scalable snapshots technologies that enable the high performance sharing of common data, and the use of storage tiering to craft the most cost-effective combination of storage technologies to meet performance requirements.
Understanding how best to leverage these storage technologies to minimize the size of the storage configurations needed to meet your VDI performance requirements is the best way to keep your overall storage costs down. And that can go a long way to re-balancing the cost structure so that VDI projects can return a positive ROI.
Eric Burgener is VP of Product Management at .