Network Computing is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

SSD, Scale-Out Architecture To Grow: Page 2 of 2

Another key trend we'll see during the next few years is the adoption of scale-out architectures, Marko adds. It's not a new concept, but a new generation of products supporting iSCSI, block storage on distributed file systems and cloud stacks that work in what is essentially a distributed file system are coming onto the market to join the NAS-based systems historically associated with scale-out architecture. "I think you're going to see those systems displace some of the big monolithic arrays for many applications, particularly unstructured data and maybe some big data apps like Hadoop and applications that are designed to take advantage or designed to use distributed data. Those can really take advantage of this build as you grow architecture," says Marko.

There is a revival of interest in the scale-out storage model. Traditionally used for file storage, scale-out architectures are no longer just for file systems--or for storage architectures, he says. Several vendors are offering appliances in 2U server form factor that support block file systems using SAN protocols and running local hypervisors for virtual machine workloads. The applications are becoming more diverse as adoption of the model gains a new following.

Other key findings in the report include small and midsize enterprises (SMEs) moving to consolidated storage, a shift that has already taken place at the Fortune 500 level. "We're still seeing that move to shared storage, NAS and SAN. Across all verticals, you're seeing consolidation in RAIDs driven by a number of things," says Marko.

Learn more about Strategy: Hadoop and Big Data by subscribing to Network Computing Pro Reports (free, registration required).