Primary Storage's Three FacesPrimary storage has three faces. There is active data and inactive data; both of these data sets actually consume space, which we can compress and then remove. Then there is the third face, with the capacity that is allocated but not in use. Each needs to be handled in a different way.
Primary storage has three faces. There is active data and inactive data; both of these data sets actually consume space, which we can compress and then remove. Then there is the third face, with the capacity that is allocated but not in use. Each needs to be handled in a different way.The conventional wisdom on optimizing active data was to leave it alone. The problem is that active data, even though it is not the majority of data being consumed on primary storage (typically 80%+ is inactive), can still be reduced and optimized. Inline compression solutions like those from Storwize can provide a 60% reduction in primary storage space used while delivering little to no performance impact.
Since today these solutions tend to work on CIFS or NFS file shares, this technology is especially important to customers that have a lot of data on NAS devices like those from NetApp, ONStor, or EMC. This is important because this type of customer tends to not only use their NAS devices for file data but also for NFS-mounted databases (such as Oracle) and they use them for NFS storage of VMware VMDK images. Inline compression can provide a relatively simple way to reduce your primary data footprint by 60% or more.
In parallel with inline, companies should address primary storage's second face, inactive data, by considering archiving, which requires developing a process around data management. This is not the huge undertaking that it has been in the past. Disk-based archives like those from Permabit, Bycast, or Nexsan greatly simplify the process of moving data to a secondary storage platform.
For this process to work you need to first understand what data you have. Using a storage knowledge tool like Tek-Tools' Profiler or Aptare's StorageConsole, you can get a vendor's independent understanding of what your data inventory looks like. This inventory and data understanding is also critical after reduction and migration. When these optimization steps are complete, you will have a significant amount of free space available. Understanding how to redistribute the remaining active load can lead to increased performance and, believe or not, power savings by being able to turn shelves of drives off. Tools like these are critical in maximizing your storage cost-cutting efforts.
Once you understand what you have, you can then decide on what you should move it to and how you should move it. We have discussed the various migration options in prior entries.
The final face of primary storage is storage that is allocated but not in use. This area can not be moved or compressed because there is nothing there. It is being reserved, just in case it is needed. The problem is that disk drives are not wine; they do not get more expensive with age, they get cheaper. An allocated but empty drive is a loser. It costs you more to buy it than it would the day you actually needed it and during that time it has been costing you space, power, and cooling.
Allocated storage can all be addressed by intelligent storage systems that can take advantage of thin provisioning.
To understand more about primary storage optimization, register for our Webinar.
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.