From Static to Dynamic

Arthur Cole

Arthur Cole spoke with Bob Quinn, founder, chairman, CTO, 3Leaf Systems.

Cole: We're hearing a lot about the dynamic data center these days. How close are we to finally breaking down the old silo architecture?

Quinn: We are getting closer every day. From a technology standpoint, the pieces are falling into place. Switch latencies are approaching memory access times, OS software is increasingly adept at claiming or giving up resources while they are running, hypervisors are becoming mature, and core hardware technologies are incorporating hardware support for key parts of the software stack that need to be accelerated. But like anything new, there is an adoption curve, so some customers or market segments will have the motivation to jump on this faster than others. The leaders here are the younger companies, as exemplified by the Web 2.0 group, who have grown up around x86 servers and use these exclusively throughout -- leading to essentially no silos.

"There are many components to the dynamic data center, including the networking, storage and server infrastructures."

Bob Quinn
3Leaf Systems

Cole: How does the new Dynamic Data Center platform help bring that about?

Quinn: There are many components to the dynamic data center, including the networking, storage and server infrastructures. By "dynamic," 3Leaf Systems means the run-time ability of an OS to expand across multiple server blades, boxes or racks, or shrink to fractions of a blade down to the core level of a processor. 3Leaf Systems technologies enable enterprises to treat x86 servers as building blocks and coalesce them into contiguous pools of CPU, memory and storage that can span across multiple physical machines and be allocated or de-allocated as needed. This will enable customers to build dynamic "systems" of any configuration, and flexibly push and pull specified resources across silos on-the-fly and without rebooting. 3Leaf Systems' hardware approach helps minimize latency and maximize bandwidth, making it useful for a wide range of workloads. Such a capability in turn enables a dynamic data center by creating an infrastructure that provides more agility and flexibility for efficient workload management and capacity planning at the data center level.

Cole: Is there a danger that enterprises could tear down their resource silos only to find themselves locked into vendor or platform silos? What is the industry doing to ensure interoperability across platforms?

Quinn: Vendor lock-in is mostly visible for application vendors. Essentially, hardware is commoditized and is no longer a barrier to changing vendors. System software is also getting there. The industry has already voted with its pocketbook, and technologies such as x86, Windows, Linux, Ethernet, Flash, etc. are standard technologies that are here to stay. That means there will continue to be a lot of attention paid to keeping them interoperable and co-deployable. But customers want their standard technologies to do more for them, and this is where some level of innovation and customization will come into play. If a vendor provides a unique value-add to the server infrastructure, such as our Dynamic Data Center technologies, then it will be left to the customer to decide if that is creating value or creating vendor lock-in. The 3Leaf Dynamic Data Center technology will be available from the leading OEMs -- meaning that high-value systems can be created from high-volume servers provided by different vendors, with interoperability guaranteed by design.

Add Comment      Leave a comment on this blog post

Post a comment





(Maximum characters: 1200). You have 1200 characters left.



Subscribe to our Newsletters

Sign up now and get the best business technology insights direct to your inbox.


Resource centers

Business Intelligence

Business performance information for strategic and operational decision-making


SOA uses interoperable services grouped around business processes to ease data integration

Data Warehousing

Data warehousing helps companies make sense of their operational data