Stop SSD Sprawl

Solid state storage devices are being implemented in servers, networks, and storage systems, leading to sprawl and performance problems in data centers. This has to change.

George Crump

August 21, 2012

3 Min Read
NetworkComputing logo in a gray background | NetworkComputing

Most IT managers and storage administrators have come to embrace solid state devices (SSD) as they look at performance options. Vendors have also embraced this reality and have delivered SSD solutions in almost every imaginable form factor and location in the storage infrastructure. There are multiple in-server SSD solutions, multiple in-network SSD solutions, and multiple in-storage SSD solutions. There are so many performance options we are now seeing them sprawl.

At the Flash Memory Summit we delivered a presentation based on our latest chalk-talk video "Performance Sprawl", which focuses on what is becoming a growing concern in the data center. Performance sprawl occurs when multiple SSD solutions are chosen to fix different performance problems in the enterprise.

Thanks especially to server-based SSDs, performance has become a business unit line item not a storage decision. Of course, the storage team eventually is left managing whatever the business units buy and a performance management nightmare develops. We are seeing an increasing number of data centers that have job titles like "Storage Performance Specialist." This won't scale so something needs to change.

The change will come from "Cross Domain Data Movement." This technology will move data between multiple storage tiers and locations of storage. Data could be moved from hard drive storage to flash on the storage system and then eventually to SSD in the server. Even within the server there may be a desire to have some data on a SATA/SAS-based SSD drive and some data on PCIe SSD.

[ What's next for solid state storage? Read Storage Players Try To Improve Solid State. ]

The challenge is that fully implemented Cross Domain Data Movement will require some time to develop, potentially as much as two years. Of course, the data center will continue to experience data storage performance issues over the next two years, so what's the strategy until then? Triage. Try to pick one solution that will address most of your performance needs for the longest period of time.

If you will have just a few servers that need a performance improvement then SSD inside the server may be ideal. There is also the option of leveraging PCIe in every server and making the storage network a capacity backend for data protection and archive. The economics of this approach may now make sense as PCIe-based SSD continues to come down in price and increase in capacity.

If you have multiple servers or hosts that need performance or if the data needs to be accessed by multiple hosts then an in-network SSD appliance makes sense. Selection will come down to the ones that support the protocol you use (NAS, Fibre, iSCSI). If you are fortunate enough to be ready for a storage refresh, then an All-Flash or Hybrid Flash Storage system may be the ideal platform to build your data center on for the next few years. It may also provide the longest term investment protection allowing you to wait as long as possible for cross domain data movement.

New innovative products may be a better fit for today's enterprise storage than monolithic systems. Also in the new, all-digital Storage Innovation issue of InformationWeek: Compliance in the cloud era. (Free with registration.)

SUBSCRIBE TO OUR NEWSLETTER
Stay informed! Sign up to get expert advice and insight delivered direct to your inbox

You May Also Like


More Insights