2012 Trend: Virtualized Migration of Storage
by Hu Yoshida on Dec 20, 2011
The number of applications that are consolidated onto a SAN attached storage frame has increased dramatically with the adoption of virtual servers. This is making it increasingly more difficult to migrate the data when the storage system needs to be refreshed. The quantity of data is in the tens or even hundreds of TBs, which will take days or weeks to physically move from one storage frame to another. What is even more impactful is the number of applications, which have to be stopped while the data is moved and then restarted when that move is complete.
There may be more than 100 applications on a large storage system, which makes it nearly impossible to stop them all for an extended period of time to complete the migration. Typically this is done by scheduling a few applications for migration each weekend until all the applications are migrated over a period of months. During this time there are the power and cooling costs for two storage frames, one of which is probably has expensive maintenance, as well as software license, and other operational costs. David Merrill has done studies which show that the burdened cost of migration can be $7,000 to $10,000 per TB, which is about the same as the cost of acquisition.
The time to complete a migration can be greatly reduced through the use of storage virtualization. During a scheduled down time you can stop the applications for a short time while you insert a storage virtualization platform between the host servers and the old storage system. Once that is done you can reassign the LUNs, rezone the SAN and restart the applications while the movement of the data takes place in the background. Many storage virtualization users have done this type of migration in a weekend.
While this type of storage migration does take an outage in order to insert the storage virtualization platform, the storage that sits behind it can be migrated to the next generation storage system without an outage.
But what happens when the storage virtualization system has to be refreshed? Today you can do it in the same manner that you virtualized your other storage. You either virtualize the new virtualization system behind the old one and move the data or virtualize the old one behind the new virtualization system. This will still take an outage. Many of our customers have used this technique to migrate from USP to USPV, and then ultimately to VSP.
In 2012, you will see storage virtualization vendors enable the upgrade of storage virtualization systems without an outage. This will further reduce the cost of storage migration by eliminating the need to disrupt the application. But you can’t take advantage of this unless you install the initial storage virtualization platform.
For Hu’s other 2012 trends, visit this bit.ly bundle: http://bitly.com/vXGP2T
Comments (2 )
It is an important point you make that storage virtualization enables new ways of managing storage while tying together processes (migration) as well as removing the closely coupled connection between applications and hardware (virtualization).
What I see as the greatest obstacle is the unwillingness of (compute) virtualization vendors to address storage head on. The result is a stalled project when storage becomes the bottleneck. The good thing is that storage virtualization can save the project, but it should have been considered from the beginning.
I’d be interested to learn how you engage a sales person who obviously is turning a blind eye to storage in order to close a virtualization deal.
Håkan Söderbom | Director Alliances | DataCore Software
I think that is starting to change as virtualization vendors like VMware, start to unload more work to the storage system through interfaces like VAAI. In the beginning, the server virtualization vendors treated storage as commodity and tried to do copies, moves, and thin provisioning with software, but as the number of virtual machines exploded, they realized that offloading some of this work would help them increase their scalability. I think it is now the non virtualization storage vendors who may be the greater obstacle. They continue to sell two controller modular storage into server virtualization environments on the basis of lower cost. Unfortunately, these large server virtualization systems need high availability enterprise storage that can be pooled together through storage virtualization to support the growth requirements of virtual servers today.