Will it Compose?

Will it Compose?


will it compose - Composable infrastructureHappy 2019 and welcome to the new DriveScale blog! The composable infrastructure market is taking off, and with this momentum, we see new perspectives, players, and solutions. With this in mind, we’ve designed a theme for 2019 called “Will It Compose”. We plan to take a comprehensive view of the composable infrastructure landscape and share our knowledge on composable architectures, resources, standards and solutions for big data analytics, AI/ML, NoSQL/NewSQL and MPP databases, and of course, containers and Kubernetes. Watch for some fun quarterly surprises along the way as we create “Composability Awards” and “Most Likely to Compose” profiles.

Our bloggers are long-time tech leaders, Tom Lyon (also a DriveScale founder), Brian Pawlowski and Denise Shiffman. Please check out their bios and reach out to us to share topics you’d like to see covered.

What Is Composable Infrastructure?

Here we have 2 words which each have a lot of meanings, so let’s start by narrowing down each.  

Infrastructure is a very subjective word. One man’s ceiling is another man’s floor. We use ‘infrastructure’ to refer to the hardware IT resources in a data center – servers, switches, and storage.  Below this level are things like racks, power, and cooling. Above this level are things like hypervisors, operating systems, subnets, storage “volumes”, etc.

‘Composable’ here is a modifier to the word infrastructure.  Composition is a process which creates composite systems from component elements.  So with our definition of infrastructure, Composable Infrastructure means hardware IT resources for application deployment which are created from component elements.

Fabrics are what tie together components into useful composite elements.  It used to be the case that fabrics within a box could be much faster, cheaper, and simpler than any kind of external fabric or network, but that is rapidly changing.  Not only is the fabric technology improving, but it’s also true that the component elements are becoming more much fabric-friendly. Programmable fabrics allow the dynamic connection and reconnection of components so that configurations can be changed as desired.

So why is Composable Infrastructure a thing?  Traditionally, only manufacturers could create hardware IT elements – by designing motherboards, assembling components, wrapping them in sheet metal, and selling them in pre-defined configurations.  In turn, this meant that the IT purchasers could only define their systems at the time of purchase. With Composable Infrastructure, systems can be defined as needed by the IT user. This leads to far-reaching operational advantages and cost savings.

What do you get as a result of composing?  There are 3 choices – servers, network, or storage.

At DriveScale, we are focused on composing servers, specifically commodity servers using commodity components with commodity fabrics, i.e., Ethernet.  And we do it at scale. We’re not interested in onesie-twosie “pet” servers. We’re helping the companies managing hundreds, thousands, and tens of thousands of servers as “cattle”.

Stay tuned for our next segment where we introduce our Composability Scorecard.

About the Author:

Tom Lyon is a computing systems architect, a serial entrepreneur and a kernel hacker. Prior to founding DriveScale, Tom was founder and Chief Scientist of Nuova Systems, a start-up that led a new architectural approach to systems and networking. Nuova was acquired in 2008 by Cisco, whose highly successful UCS servers and Nexus switches are based on Nuova’s technology. He was also founder and CTO of two other technology companies. Netillion, Inc. was an early promoter of memory-over-network technology. At Ipsilon Networks, Tom invented IP Switching. Ipsilon was acquired by Nokia and provided the IP routing technology for many mobile network backbones. As employee #8 at Sun Microsystems, Tom was there from the beginning, where he contributed to the UNIX kernel, created the SunLink product family, and was one of the NFS and SPARC architects. He started his Silicon Valley career at Amdahl Corp., where he was a software architect responsible for creating Amdahl’s UNIX for mainframes technology. Tom holds numerous U.S. patents in system interconnects, memory systems, and storage. He received a B.S. in Electrical Engineering and Computer Science from Princeton University.

Leave A Comment