IBM flash array strategy mastermind talks tech + market trends | #IBMedge
Woody Hutsell had seen technologies come and go in the 14 years he’s been in the memory industry, but the underlying focus on enabling faster data access never changed. The former Texas Memory Systems (TMS) executive, who joined Big Blue following its acquisition of his old company to spearhead product strategy for the newly absorbed unit, told SiliconANGLE at last month’s IBM Edge summit that flash is a continuation of a trajectory that traces all the way back to the early days of RAM.
“At the time, why would somebody pay $5,000 a gigabyte? Because it could truly transform their business, it would allow them to pursue things or implement strategies or support customer workloads they never could before. And now with the cost of flash declining so dramatically, we can support that many more customers and have a much broader impact,” Hutsell tells theCUBE hosts John Furrier and Dave Vellante.
Although it’s still considerably more expensive than disk on paper, he says that the economics of solid-state memory have improved to the point that it’s now only marginally less cost-effective than mechanical storage when used in performance-intensive environments. The benefits are more than worth the added cost.
Flash can handle far greater I/O operations per second than disk with lower latency and using considerably less power and space, a combination that is making the technology increasingly popular among large organizations seeking to speed up mission-critical applications that have historically relied on hard drives for data storage. That shift in spending is disrupting the high-performance disk array, or “tier 1”, market.
“The tier 1 market is reorganizing because the people who gotten into tier 1 have done it for a variety of reasons: some may have got in in for performance reasons, some for storage services and some for centralization,” Hutsell says. “What is already happening today is those who got in for performance reasons are already moving off to all-flash appliances.”
IBM now focused on services
IBM is now focusing its efforts on bringing the next segment, the services-oriented group, aboard the flash bandwagon. To that end, the company had married its FlashSystem line of appliances with its field-hardened SAN Volume Controller storage virtualization stack to deliver advanced services like snapshotting, replication and data reduction.
The offering, better known as SVC, constitutes the foundation of Big Blue’s platform strategy heading into the software-defined data center. “The strategy today is to take advantage of our very mature software stacks so there’s no strong incentive to develop something new because the things we have today are already proving to have very low overhead when mixed with flash systems,” Hutsell details.
IBM’s approach of bundling SVC with its appliances represents the polar opposite of “Server SAN,” a term coined by Wikibon to describe a category of commodity-based storage architectures in which the management mane is entirely decoupled from the underlying infrastructure. The model is based on on a pool of direct-attached storage (DAS) devices, like PCIe flash cards, connected by a high-latency fabric such as InfiniBand.
Server SAN has been used to great success by Internet giants such as Google, Facebook and Amazon, but according to Hutsell, software-only management leaves much to be desired when it comes to flash. Specifically, he says that detaching certain data services from the storage layer comprises the responsiveness of solid-state memory, which SVC supposedly avoids.
The perks of software-defined architecture
One of the main advantages proponents of software-defined architectures claim over proprietary appliances like the kind IBM sells is the ability to scale more cost-effectively, functionality that makes it easier to keep up with the rapid growth of data . But Hutsell says that his company has got that covered too.
“We’ve been on a very aggressive roadmap when it comes to new flash NAND generations. Each of those generations is resulting in a doubling of NAND flash density, and that in turn means we are able to deliver solutions with higher capacity per rack unit,” he details. He predicts that the number of use cases for flash will grow as this trend continues and shift CIOs’ perception of the technology from an application accelerator to a fully-capable replacement for tier 1 storage.
Feature image courtesy IBM
A message from John Furrier, co-founder of SiliconANGLE:
Your vote of support is important to us and it helps us keep the content FREE.
One click below supports our mission to provide free, deep, and relevant content.
Join our community on YouTube
Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.
THANK YOU