[Most Recent Entries] [Calendar View]
Friday, January 29th, 2016
| Time | Event |
| 1:00p | ICTroom Unchains Capacity from Size in Modular Data Centers
This month, we focus on data center design. We’ll look into design best practices, examine in depth some of the most interesting recent design trends, explore new ideas, and talk with leading data center design experts. After years of designing data centers for customers around Europe, Theo Arendzen and his colleagues realized that no matter how much customization a customer wanted, the fundamental data center design elements just didn’t vary that much from one facility to another. “Most of the topology is based on the same design principles,” he says. “You always come to a more or less standardized solution.” Until about six years ago, ICTroom, the Netherlands-based company where Arendzen oversees engineering and design, built data centers within existing buildings. But when it started receiving its first orders for greenfield developments, the engineers started working on the idea of standardization and modularity. ICTroom wasn’t alone in this realization. Companies like Colt in Europe, or Compass Datacenters, Aligned Data Centers, and IO in the US, also bet their money on the idea that the more you standardize, the faster you can deliver product and save on upfront costs usually sunk in high-capacity facilities that spend long periods of time underutilized. Even Facebook, which builds massive web-scale facilities, has been employing these principles starting with its server farm in Luleå, Sweden. Read more: Modular Cooling System Enables on-Demand Data Center Capacity After designing its first greenfield data center for a service provider named AlphaClouds, a 3MW facility, and a much bigger project for another customer whose name Arendzen could not disclose, ICTroom came up with its first modular product. IMD750 is a whole-package deal – a 750kW data hall with all the necessary cooling and backup power infrastructure that gets quickly assembled on-site on a steel frame. The building shell around it also consists of a steel frame with concrete slabs bolted on. There are three basic modules: the IT module, which includes the raised-floor data hall and the cooling units on top; the power distribution module, which includes UPS units and switchgear; and the primary power module, which has a transformer and a backup generator. There’s enough room for customization, but 80 percent of it is standardized, and Arendzen considers that to be a big advantage, enabling the company to deliver a data center ready for commissioning in 12 to 15 weeks, he says. Here’s a time-lapse video of a data center build ICTroom did for cloud service provider Cegeka: Earlier this month, ICTroom introduced smaller form factors to its product line, adding 250kW and even 50kW options. The idea is to give customers the option to scale in even smaller chunks. Another goal was to make the building itself scalable too, not just the critical power capacity. IMD250, the 250kW option, is built in 36-square meter blocks, so a customer can expand the building size in those increments, independently of IT capacity, which scales in 250kW increments. IMD50 is ICTroom’s micro data center offering, which supports six or so IT racks, complete with UPS and cooling systems. Micro data centers are a relatively recent development, and only a handful of vendors have offerings in this category. These are aimed primarily at companies that either need data center capacity close to end users, such as caching sites, or for companies that don’t have huge data center requirements but cannot outsource the requirements that they do have to commercial colocation or cloud providers. While demand for such small-capacity data centers today is low, it is slowly rising, Arendzen says. Read more: Schneider Targets Edge Computing with New Micro Data Center Portfolio |
| 5:45p | IT Innovators: Making a Career Leap to the Cloud
By WindowsITPro After spending nearly 19 years working in IT operations for local government, Mike Wilcox, from Winston-Salem, North Carolina, left his secure, well-paid job this past summer to dive headfirst into learning, training and building a consulting firm based around the cloud. He refers to his professional transformation as “the perfect timing for a change” and even a “mid-career crisis.” However, when pressed for what really motivated the shift, he says the impending popularity and interest in the cloud—coupled with the fear that this outside interest could soon make his own job obsolete—led him to “retool technically.” Wilcox admits, “we on-premises people are a bit scared of getting our jobs outsourced.” Wilcox recalls one specific scenario in his past job when the light bulb went off in his mind. It helped him realize that the cloud was where he should be headed. “I was preparing a presentation about a systems management software product, and I was having this internal conflict about the importance of the cloud because of my on-premises expertise.” It finally occurred to him that rather than denying or trying to argue the cloud’s prominent role in IT, he should embrace it and immerse himself in getting up to speed. Wilcox decided that he would take the self-teaching route. He enrolled to get his certification and signed on as a Microsoft partner. As soon as he started dabbling in the cloud, he felt “like a frog suddenly realizing the water he is in is getting much hotter and will be boiling soon.” He says the process made it clear to him that the disruption of the cloud will be “as big as the mainframe-to-PC shift and that the time to adoption will be a fraction of what it was for that transformation.” He decided now was a better time than ever to get onboard, and launched his consulting firm, See I.T. Consulting, LLC. Along the way, Wilcox believes that taking certain steps, such as networking, attending industry events and furthering his education, has helped to guide him. Of course, the road hasn’t been entirely smooth. Specifically, coming from an IT ops background, learning how to code was a must. There’s still a learning curve that comes with learning new technologies and launching a startup, but Wilcox says the move has already proven to be worthwhile. “Five years from now, everyone in IT, the entire way we support IT is going to change, and this is going to be as big at the Internet,” Wilcox says. He believes there will be a gaping hole of expertise that even in his former manager role, he would have been required to meet. “I’m just going to jump in with both feet here,” he says. While the path is still unfolding for Wilcox, he says one thing is certain: “Anyone on a mission to make himself more cloud-friendly will inevitably be more attractive to future employers and customers.” Renee Morad is a freelance writer and editor based in New Jersey. Her work has appeared in The New York Times, Discovery News, Business Insider, Ozy.com, NPR, MainStreet.com, and other outlets. If you have a story you would like profiled, contact her at renee.morad@gmail.com. The IT Innovators series of articles is underwritten by Microsoft, and is editorially independent. This first ran at http://windowsitpro.com/it-innovators/it-i |
| 5:49p | Weekly DCIM Software News Update: January 29th Nlyte integrates with Oracle virtualization; Emerson adds 3D cooling management; Indegy says DCIM is not fully protected against attack; Data Center Journal explores the integration of CFD data within the DCIM workflow. Nlyte integrates with Oracle virtualization. Nlyte Software announced full support for VM server virtualization technology from Oracle. The Nlyte Connector for Oracle VM enables customers to align and reconcile resources running across their virtual, logical and physical platforms, which enables IT organizations to view each layer, and the resources being used, in context of other resources present in the data center. Emerson adds data center cooling management in 3D. Emerson announced that it has added 3D visualization capabilities for data center cooling management in the latest release of its DCIM software suite Trellis. The new environmental monitoring and management module is called Thermal System Manager, which tracks the data center’s thermal profile to the device level. DCIM systems not fully protected against attack, says Indegy. Industrial cyber security firm Indegy says that the number of attacks against industrial targets is growing, security is being eroded due to proliferation of Internet-connected devices, and the company is finding little enthusiasm within data centers for additional security at the DCIM level. Indegy makes software that acts as the bridge between customer’s information technology and their operational technology, and notes that few clients are asking to export data to DCIM solutions at the moment. Using CFD alongside DCIM. In part 3 of a series Data Center Journal explores the challenges of properly using CFD in the data center, the complexities of airflow, and how CFD data integrates with DCIM workflow. |
| 7:05p | Data Center Power Outage Brings Down GitHub GitHub, the most popular online repository for open source code and hosting services, went down for two hours Thursday due to a power outage in its primary data center. “A brief power disruption at our primary data center caused a cascading failure that impacted several services critical to GitHub.com’s operation,” Sam Lambert, GitHub’s director of systems, wrote in a status update on the company’s blog Friday morning. “While we worked to recover service, GitHub.com was unavailable for two hours and six minutes.” Read more: Why Should Data Center Operators Care about Open Source? The outage started around 4pm Pacific. The final procedure to fully restore the facility’s power infrastructure was completed Thursday evening. Utility power outages do not bring down data centers in most cases, since these facilities are designed with UPS units, backup generators, and transfer systems that fail over to the generators automatically. When they do happen, power-related data center outages are caused by failure of those backup systems. A recent study by the Ponemon Institute, sponsored by Emerson Network Power, found that UPS failure is the most common cause of data center outages, followed by cybercrime (namely DDoS attacks), human error, and cooling system failure, in that order. Read more: Cybercrime Fastest-Growing Cause of Data Center Outages It’s unclear where San Francisco-based GitHub’s primary data center is. Lambert told us in an earlier interview that the company does not disclose its data center locations. GitHub’s Bare Metal CloudWhat we do know is that it has to expand its data center capacity rapidly to keep up with growing popularity of open source software. “We have a massive intake of new repositories and just new data, so we’re continually expanding our storage infrastructure,” Lambert said. GitHub doesn’t use virtual machines. Instead, it has built a bare-metal cloud, which allows it to provision physical machines the same way cloud VMs are provisioned. “We deploy onto physical machines,” he said. “We have a system internally that allows us to deploy physical machines as the cloud.” The Horror!Effects of the outage were widely felt across startup and enterprise developers around the world, many of whom use GitHub for coding day-to-day. Here is a collection of Tweets from Thursday that illustrate the carnage:
|
| 8:30p | Qarnot’s Home Heating Servers Now Plugged into Data Centers Qarnot Computing has combined its hybrid space heater servers with large centralized computing capacity in data centers around Europe, creating a distributed computing grid that stretches across hundreds of individual homes and several data centers. The French company has teamed up with data center service provider DATA4, which operates 30MW of IT capacity across thirteen data centers in France, Italy, and Luxembourg, to create the system. As part of the partnership, DATA4 has also taken a majority financial stake in Qarnot, the companies announced Friday. Qarnot places its server heaters, called Q.rad, in regular homes, offering residents a free heat source. The company refunds them the cost of electricity Q.rads consume, while renting the computing capacity of the distributed system to clients with high-performance computing needs, such as banking risk calculations, 3D animation, and scientific research. A single Q.rad server can heat a room between 150 and 300 square feet in size, as long as the room meets modern insulation standards, the company claims. It says it has deployed 350 of them. The point is to use computing capacity to reduce carbon emissions that would otherwise be associated with running space heaters. DATA4 is working on another waste heat reuse project, planning to build agricultural greenhouses next to its data center in Paris suburbs that will be heated by exhaust heat from the facility. Now that Qarnot’s Q.rad system is integrated with HPC horsepower in DATA4 data centers, it can take on many more workloads and better handle spikes in demand. It will also offer DATA4’s network and storage services to its clients, while DATA4’s customers will have access to the computing capacity of Qarnot’s residential computing grid. Its new financial stakeholder will also help the company grow and place its “digital heaters” in more homes. The distributed system is managed by Q.ware, Qarnot’s software that manages and distributes loads across the infrastructure. It ensures calculations are distributed optimally across centralized clusters in DATA4 facilities and Q.rad servers in European homes. DATA4 will integrate a Q.ware software layer into its hosting services. |
| << Previous Day |
2016/01/29 [Calendar] |
Next Day >> |