The Ripple Effect

Why More Data Centers Will Be Software Defined


A new report projects that the global Software-Defined Data Center (SDDC) market will grow at a 22 percent compound annual growth rate through 2021. The authors, an India-based outfit called Wise Guy Consultants, estimate that the total market size for SDDC goods and services will reach $81.4 billion in the same period.

The reason for the shift to a virtualized data center? Arthur Cole, who covers infrastructure for IT Business Edge, puts it this way: “Organizations of all sizes are starting to view legacy data systems as one of the chief impediments to improved digital services, which themselves are seen as vital for success in the next-generation economy.”

Cole is right. Legacy data systems are comprised of fixed resources and hard-to-scale assets that make it tough to drive up utilization. So a primary goal of SDDCs is to maximize the utilization of resources that would otherwise sit idle for hours, even days on end. To make flexible what is inflexible. To right-size resources to match the workload at hand.

This explains the growing popularity of software-defined storage and software-defined networking, which have introduced the flexibility and utilization that data centers have been lacking in both storage and networking.

But what if those same benefits could be applied to servers? What if right-sizing servers is the next step for IT organizations on the path toward a fully software-defined data center?

The missing piece of the SDDC

Software-Defined Servers are conspicuously absent from the Wise Guy report, ostensibly because they are new where as software-defined storage and networking solutions are known entities. But we expect that will change, and soon, because Software-Defined Servers represent the missing piece of the SDDC. And it’s a big piece at that. Storage and networks are crucial, of course, but servers are at the core of every workload and big data problem, at the core of the data center itself. And with an increasing number of applications written to leverage in-memory computing and analytics, accessing more memory (not to mention cores) should be a fundamental design goal for every SDDC.

As its name suggests, a Software-Defined Server uses software to combine multiple physical computers into one or more virtual systems. In TidalScale’s implementation, each virtual system spans from one server to many, aggregating all the resources of the combined computers, including memory, CPUs and, yes, even affiliated networking and storage. The result is a right-sized server configured and booted on the fly. Using advanced machine learning, TidalScale’s HyperKernel software automatically optimizes Software-Defined Servers, migrating resources within a virtual server to where the application or problem needs them most. And once a workload is completed, users can quickly configure and deploy another Software-Defined Server, or a group of them, to handle the next set of workloads.  Best of all, it’s achieved on commodity hardware and with industry-standard interconnects, and without a single modification to applications or operating systems.

TidalScale’s Software-Defined Server technology has been disruptive enough for us to have been named a Gartner Cool Vendor and an IDC Innovator. We’ve won Red Herring’s Top 100 North America Award. And eWeek has proclaimed our technology “may be the biggest advance in servers since VMware’s virtualization of the Intel IA-32 platform 18 years ago."

With many organizations struggling to get the most value from their existing IT resources while keeping pace with the demands of digital services, TidalScale’s Software-Defined Servers offer a practical and cost-effective way forward.

All this leads us to an inevitable question. If the SDCC market is expected to reach $81.4 billion by 2021 without factoring in Software-Defined Servers, then how much more will it be worth once the market incorporates solutions like the TidalScale HyperKernel?

Only time will tell. But here at TidalScale, we’ll be doing everything we can to ensure that the future of the software-defined data center doesn’t leave servers behind.  

Topics: software-defined server, data center, in-memory computing, software-defined data center, sddc

gartner_cool_vendor_2017.jpg
IDC-Innovator-Logo-2017.png
TidalScale featured in e-week!
TidalScale Red Herring 100 Winner
Gary Smeardon in the Cube Interview