Microservers and the hurry-up-and-wait conundrum

Microservers and the hurry-up-and-wait conundrum

Summary: Like most new technologies, the enthusiasm for new developments usually outpaces the revolution. Microservers will play out the same way, but ultimately have a big impact on the data center.


Microservers, designed for specific workloads, low power, and tight spaces, are widely thought to be the future of the data center. The disagreements come when you start talking timelines.

Like most new technologies, the enthusiasm for new developments usually outpaces the revolution. Fifteen years ago, Linux was going to take over the world. Today, Linux is everywhere and no one blinks when a company builds on an open source stack.

Microservers may be the same way. But this revolution will take some time to play out. In our microserver special report, Nick Heath noted that microservers, ARM and Intel-based, are being used for specific workloads such as serving Web content, but enterprises are all about multipurpose computing for a wide range of applications.

In other words, microservers won't be pushing their cousins out the door anytime soon. However, new computing tasks may change that equation. Heath wrote:

The range of workloads handled by microservers is broadening. The first generation was focused on relatively CPU-light tasks, such as serving static elements on web pages, but the second generation employed a wider range of more powerful (but still energy-frugal) SoCs — and, importantly, added support for 64-bit processing and more memory. This expanded microservers' capabilities to tasks such as serving dynamic web elements (those updated by AJAX, for example), serving hosted desktops, and digital signal processing for telcos.

Errol Rasit, research director for data center dynamics at Gartner, said the number of tasks suited to being scaled across microserver clusters would continue to grow as new workloads, such as big data analytics, emerge.

In January, Frank Frankovsky, president of the OCP and Facebook's hardware design lead, said that ARM processors will take over the data center as they rode the microserver wave. He also said his prognostication was a bit optimistic and off six months to a year. Three months have passed since Frankovsky said that and the ARM developments haven't exactly snowballed. He may be off by a few more years.



Download the full research report from Tech Pro Research - Microservers: The newest data center innovation.

There's little doubt, however, that Frankovsky is on to something.

Heath wrote:

The spectrum of workloads that microservers can carry out is increasing, as more enterprises take on tasks that can be distributed across microserver clusters and processed in parallel, such as big data analytics. Microservers also provide an alternate platform for executing specialist jobs previously restricted to high-cost proprietary technology, such as digital signal processing. And as the capabilities of the low-power chipsets underpinning microservers grow, more tasks will become possible using the platform.

Whether ARM, AMD, or Intel lead the microserver charge remains to be seen, but the revolution will happen. It'll just take a bit more time than you thought. IT buyers need to stay on top of microserver developments, experiment when possible and then plot larger installations as workloads evolve.



ZDNet's Monday Morning Opener is our opening salvo for the week in tech. As a global site, this editorial publishes on Monday at 8am AEST in Sydney, Australia, which is 6pm Eastern Time on Sunday in the US. It is written by a member of ZDNet's global editorial board, which is comprised of our lead editors across Asia, Australia, Europe, and the US.

Previously on Monday Morning Opener

Topics: Data Centers, Intel, Servers, ARM

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.


Log in or register to join the discussion
  • Microservers and the hurry-up-and-wait conundrum

    I don't believe you will have to see a "hurry up and wait" scenario on this subject. The hardware is there and relevant. It is the software that needs to "catch up" to make the push into that fray more valid and affordable for scalable operations.

    We've seen this happen time and time again on normal servers and desktop platforms. You have to have the Applications to run for people to be able to justify moving to newer hardware.
  • I think that AMD has a real opportunity here

    If they can get their software off the ground and do more in the hardware arena for SoC setups.... I think multi-processor jaguar boxes could be great investments! Or Jaguar Microservers.... they are quite fast an energy efficient... And Puma+ is coming in the next months.. Puma+ SoC microservers could be very attractive... As it is AM1 should be attractive for server owners... those CPU's are quite fast enough for multiple server applications.