Welcome!

Related Topics: Microservices Expo, Java IoT, Open Source Cloud, Containers Expo Blog, Machine Learning , @CloudExpo

Microservices Expo: Article

Search for Energy Efficient Servers Leads Ex-Weatherman to Build-a-Blade

Mix and Match Mini-ITX Blades Fit the Task and Lower the Energy Bill

The Next Blade Revolution Begins
Open platforms have always meant more cost savings and greater flexibility in business computing. In the ‘80s, proprietary desktops gave way to clones, and the ‘90s saw proprietary servers and workstations dissolve into off-the-shelf x86 architectures. Today, a handful of "big iron" vendors own the blade market with their proprietary enclosures and restrictive designs...and history is about to repeat itself.

Change in the Wind
In 1978, Anthony Watts was a Purdue-trained TV meteorologist with a background in electrical engineering. By 1985, when Willard Scott was in his prime, Watts invented the first NTSC broadcast encoder for the IBM PC for use in television weather broadcasts. Not content with the then-blazing 6 MHz of IBM AT machines, which could take up to ten minutes to render a single frame, Watts modded the computers with a custom cooling design, allowing them to double their stock speeds, and started using them for processing weather graphics data. His company, IntelliWeather, soon created some of the first-ever PC-based broadcast TV weather systems, and a decade later, he was supplying weather graphics and display solutions to CBS News as well as TV stations around the USA

Over nearly two decades of innovation, IntelliWeather progressed from 16-color displays to today's full-color HD. Whereas it once took minutes to render a frame, today's 30 fps output is done in nearly real-time. The incoming streams of data from NOAA satellite feeds are massive enough to fill eight T1 lines every second. Not surprisingly, it takes a lot of computing power to render so much raw data into forms that broadcasters and scientists can use.

IntelliWeather has its own server farm, and each server tends to have its own job. Some do pre-processing, some render, and so on. The workflow is linear from incoming satellite feed through processing and on to another server farm in Sacramento that distributes finished data to television stations. As the data load increases, both in input and output, Watts and IntelliWeather continually need more processing capability and more servers.

Slicing the Power
Through eBay in 2008, Watts connected with a movie production company doing CGI that no longer needed an entire rack of Intel 1U rendering servers. Watts purchased the whole stack, installed them, and everything was fine because initial utilization of the new machines was fairly low. However, by the summer of 2010, every server was running nearly at capacity around the clock, each one continuously pulling about 180W. The more heat the servers generated, the more air conditioning had to be used. Warm season power bills just for this server stack were hitting $3,000 per month-no small expense for a small company.

Like so many other SMBs and small enterprises, IntelliWeather needed a better way to scale its computing capabilities while taking a leap in power efficiency. At the same time, it needed a better answer as to how it should dispose of existing servers that had reached their end of life. Donating that end of life technology to Computers For Classrooms was fine, but perhaps there was a better long-term approach.

In recent years, the rise of blade servers addressed some of Watts's needs but not enough of them. He investigated many of the blade options from top name manufacturers. Like all blade offerings, they offered the ability to start with one server in an enclosure and add more blades as needs dictated. In terms of footprint, the blade systems were more space-efficient than usual rackmount servers. However, every blade solution IntelliWeather examined was proprietary, requiring the vendor's own motherboards for that particular blade platform for any upgrading or replacements. Furthermore, the amount of energy savings advertised was not in line with Watts's needs.

So Watts did what any former electrical engineer and hardware hacker would do. He built what he wanted from scratch, just like he did for broadcast TV display systems.

Better with Build-a-Blade
First, Watts knew that different processing tasks require different types of server capabilities. The heavy lifting of rendering might benefit most from a cutting edge Xeon or Core i7 processor, but a server tasked with downloading from a low-speed, secondary satellite channel needs nothing more than a budget-friendly VIA C7. In traditional blade systems he examined, it was impossible to accommodate such diversity.

Second, to make systems upgradeable for the long-term, form factors are needed. An ATX desktop PC chassis purchased 15 years ago is still compatible with any ATX or microATX motherboard sold today because ATX is a widely adopted open standard. Yet such standards have never existed in the world of blade servers.

Third, even though big name blade systems advertise highly integrated power efficiency, energy savings gained through integration can be more than tossed away by requiring higher-consuming components than needed for the tasks at hand. Why require a 120W TDP processor on a blade when a 20W chip will serve equally well for much less money (both up front and ongoing)? Furthermore, the internal AC power supplies used in conventional blade systems are inherently less efficient than DC options. Studies have shown that data centers can realize power-saving improvements of over 28% by switching from AC to DC power distribution. Similar benefits can be realized at the rack and system level from making similar changes. Using DC power for computers isn't new; every notebook PC does it. But until now, the application to blade systems has been limited. With the popularization of green technology and demanding better energy efficiency, there has been a renewed interest in DC power systems.

IntelliWeather, branding its broadcast hardware as ITWorks, spent two years designing and refining its new Build-a-Blade product. Quite simply, Build-a-Blade is a 6U enclosure that can fit up to nine blades. Each blade is designed to fit any Mini-ITX or Thin Mini-ITX motherboard and up to six 2.5" storage drives, or a single 3.5" drive. Mini-ITX is a standard open form factor, originally designed by VIA in 2001, that is only gaining in popularity as the move for smaller, more energy-efficient systems continues.

Each Build-a-Blade tray uses a 12VDC power input port that links back to a dedicated DC "brick" on the enclosure's communal power supply tray. If a PSU ever goes bad, the user simply unplugs the appropriate brick from the tray, fastens down a new one in its spot, and the maintenance is complete. There's no complex disassembly involved, as in some other blade designs. Further, the DC power port enables these systems to be fueled by solar or wind power (with appropriate battery backup). Target applications might be in remote telecommuncations or mobile scenarios wherein a number of computers are needed, such as a mobile command center.

The final Build-a-Blade product cut IntelliWeather's $3,000 power bill down to less than $1,000. The stack of nine 2U servers that consumed 18U of rack space and 1080W now takes 6U and sips a mere 198W. With so much less power and heat waste, as well as an optimized 454 CFM airflow system, Build-a-Blade is also substantially quieter than the prior systems, which is valuable in smaller businesses where people spend all day working near their servers.

ITWorks now offers Build-a-Blade in configurations ranging from  a starter DIY enclosure with one or more blades, to a fully configured system with nine blades. Common management tools based on IPMI or Intel's AMT are readily available and fully compatible with any installed Thin/Mini-ITX motherboards supporting those features. Build-a-Blade also recently launched a 4U eight blade system, using the new Thin Mini-ITX form factor. Depending on the configuration, some of these blades have a total power dissipation of less than 15 watts each.

The first PC "clones" appeared in 1982, and they signaled the end of IBM's proprietary grip on the PC market. Build-a-Blade will do the same for the blade market, helping to bring costs down, promote radical energy savings, and give customers much better return on their investment because they'll be buying exactly what they need and reusing their hardware for many more years to come.

More Stories By Pat Meier-Johnson

Pat Meier-Johnson is a long-time contributor to the digital industry with a specialty in mobile technology. Pat produces the Connected Traveler Technology Showcase and is president of Pat Meier Associates, a PR and media production company specializing in technology and travel.

Latest Stories
"NetApp's vision is how we help organizations manage data - delivering the right data in the right place, in the right time, to the people who need it, and doing it agnostic to what the platform is," explained Josh Atwell, Developer Advocate for NetApp, in this SYS-CON.tv interview at 20th Cloud Expo, held June 6-8, 2017, at the Javits Center in New York City, NY.
The explosion of new web/cloud/IoT-based applications and the data they generate are transforming our world right before our eyes. In this rush to adopt these new technologies, organizations are often ignoring fundamental questions concerning who owns the data and failing to ask for permission to conduct invasive surveillance of their customers. Organizations that are not transparent about how their systems gather data telemetry without offering shared data ownership risk product rejection, regu...
Bill Schmarzo, author of "Big Data: Understanding How Data Powers Big Business" and "Big Data MBA: Driving Business Strategies with Data Science," is responsible for setting the strategy and defining the Big Data service offerings and capabilities for EMC Global Services Big Data Practice. As the CTO for the Big Data Practice, he is responsible for working with organizations to help them identify where and how to start their big data journeys. He's written several white papers, is an avid blogge...
When building large, cloud-based applications that operate at a high scale, it's important to maintain a high availability and resilience to failures. In order to do that, you must be tolerant of failures, even in light of failures in other areas of your application. "Fly two mistakes high" is an old adage in the radio control airplane hobby. It means, fly high enough so that if you make a mistake, you can continue flying with room to still make mistakes. In his session at 18th Cloud Expo, Le...
When talking IoT we often focus on the devices, the sensors, the hardware itself. The new smart appliances, the new smart or self-driving cars (which are amalgamations of many ‘things'). When we are looking at the world of IoT, we should take a step back, look at the big picture. What value are these devices providing. IoT is not about the devices, its about the data consumed and generated. The devices are tools, mechanisms, conduits. This paper discusses the considerations when dealing with the...
Machine learning has taken residence at our cities' cores and now we can finally have "smart cities." Cities are a collection of buildings made to provide the structure and safety necessary for people to function, create and survive. Buildings are a pool of ever-changing performance data from large automated systems such as heating and cooling to the people that live and work within them. Through machine learning, buildings can optimize performance, reduce costs, and improve occupant comfort by ...
"Our strategy is to focus on the hyperscale providers - AWS, Azure, and Google. Over the last year we saw that a lot of developers need to learn how to do their job in the cloud and we see this DevOps movement that we are catering to with our content," stated Alessandro Fasan, Head of Global Sales at Cloud Academy, in this SYS-CON.tv interview at 20th Cloud Expo, held June 6-8, 2017, at the Javits Center in New York City, NY.
René Bostic is the Technical VP of the IBM Cloud Unit in North America. Enjoying her career with IBM during the modern millennial technological era, she is an expert in cloud computing, DevOps and emerging cloud technologies such as Blockchain. Her strengths and core competencies include a proven record of accomplishments in consensus building at all levels to assess, plan, and implement enterprise and cloud computing solutions. René is a member of the Society of Women Engineers (SWE) and a m...
Containers and Kubernetes allow for code portability across on-premise VMs, bare metal, or multiple cloud provider environments. Yet, despite this portability promise, developers may include configuration and application definitions that constrain or even eliminate application portability. In this session we'll describe best practices for "configuration as code" in a Kubernetes environment. We will demonstrate how a properly constructed containerized app can be deployed to both Amazon and Azure ...
Business professionals no longer wonder if they'll migrate to the cloud; it's now a matter of when. The cloud environment has proved to be a major force in transitioning to an agile business model that enables quick decisions and fast implementation that solidify customer relationships. And when the cloud is combined with the power of cognitive computing, it drives innovation and transformation that achieves astounding competitive advantage.
"Cloud computing is certainly changing how people consume storage, how they use it, and what they use it for. It's also making people rethink how they architect their environment," stated Brad Winett, Senior Technologist for DDN Storage, in this SYS-CON.tv interview at 20th Cloud Expo, held June 6-8, 2017, at the Javits Center in New York City, NY.
Poor data quality and analytics drive down business value. In fact, Gartner estimated that the average financial impact of poor data quality on organizations is $9.7 million per year. But bad data is much more than a cost center. By eroding trust in information, analytics and the business decisions based on these, it is a serious impediment to digital transformation.
The cloud competition for database hosts is fierce. How do you evaluate a cloud provider for your database platform? In his session at 18th Cloud Expo, Chris Presley, a Solutions Architect at Pythian, gave users a checklist of considerations when choosing a provider. Chris Presley is a Solutions Architect at Pythian. He loves order – making him a premier Microsoft SQL Server expert. Not only has he programmed and administered SQL Server, but he has also shared his expertise and passion with bu...
Bill Schmarzo, author of "Big Data: Understanding How Data Powers Big Business" and "Big Data MBA: Driving Business Strategies with Data Science" is responsible for guiding the technology strategy within Hitachi Vantara for IoT and Analytics. Bill brings a balanced business-technology approach that focuses on business outcomes to drive data, analytics and technology decisions that underpin an organization's digital transformation strategy.
Digital Transformation: Preparing Cloud & IoT Security for the Age of Artificial Intelligence. As automation and artificial intelligence (AI) power solution development and delivery, many businesses need to build backend cloud capabilities. Well-poised organizations, marketing smart devices with AI and BlockChain capabilities prepare to refine compliance and regulatory capabilities in 2018. Volumes of health, financial, technical and privacy data, along with tightening compliance requirements by...