Maximizing Block I/O Dollars With Thin Provisioning

Getting the most out of every storage dollar is critical in this economy and as we discussed in our last entry, viable options for optimizing file based primary storage are available now but as of yet solutions that can compress and deduplicate block I/O storage are not yet readily available. But all is not lost, there are things you can do to lower your primary storage block I/O costs.The first step of course relates to our last entry, file based data that is on block I/O storage could and should be migrated off to a secondary tier of storage. Beyond moving old data off of primary storage and without the ability to compress or deduplicate block I/O storage, further cost maximization has to come from one of three areas; either reducing the physical drive count, applying the right amount of storage compute power or using more power efficient components, especially drives. The challenge with primary block I/O storage is that you have to maintain performance to the user or customer which may minimize some of the power saving measures you can take.

A potential first step is to be more efficient with how storage is allocated on block I/O by reducing the number of drives and capacity that you need in the first place. The first candidate to help address this is thin provisioning. The idea behind thin provisioning is to only allocate storage as it is needed by the application. Depending on which study you read 25 to 35% of storage is allocated to specific servers but not in use. This is essentially free space that is held hostage by the application and server that the storage is assigned to. It is important to note that this storage area can't be optimized via compression or deduplication, there is not data there to optimize.

Thin provisioning gives you all this wasted capacity back and puts it into a global pool that other servers, with thin provisioned volumes, have access to as they need additional capacity. Before you race out and buy a new storage system that does thin provisioning however, you need to give some thought to the conversion. If you use one of the typical SAN copy utilities to move the data to the new array, you will essentially copy the free space also, eliminating the value of thin provisioning on migrated volumes. As we discuss in our article "Converting from Fat Volumes To Thin Provisioning" there are certain steps to take or capabilities to look for as you move to a thinly provisioned world and so make sure you understand those before you make the jump.

The next area to explore in maximizing primary block I/O storage is to reduce drive count by considering Solid State Disk, which will be the subject of our next entry.

Track us on Twitter: http://twitter.com/storageswiss

Subscribe to our RSS feed.

George Crump is founder of Storage Switzerland, an analyst firm focused on the virtualization and storage marketplaces. It provides strategic consulting and analysis to storage users, suppliers, and integrators. An industry veteran of more than 25 years, Crump has held engineering and sales positions at various IT industry manufacturers and integrators. Prior to Storage Switzerland, he was CTO at one of the nation's largest integrators.