Thursday, December 6th, 2012

Time	Event
1:30p	NextFort Offers Industrial Strength Modules NextFort is offering concrete and steel modules that can house 20 racks each from its new facility in Chandler, Ariz. (Image: NextFort) New players continue to emerge on the data center landscape. The latest is NextFort, which is building a data center in the Phoenix market offering high-security modular designs optimized for private clouds. NextFort is the part of a growing data center cluster in Chandler, Arizona, where its neighbors include Digital Realty Trust and CyrusOne. The company is building a 180,000 square foot facility, with the first phase scheduled to come online in the first quarter of 2013. The company’s design offers a slightly different take on the modular theme. The facility will feature individual suites made of steel and cement, which can house 20 racks and support up to 225 kW of critical load. Each turn-key customer suite will have dedicated mechanical infrastructure, including a rooftop cooling unit. Hardened Modules, But No Roof The suites will be built off a central corridor, but the building will have no roof, with the hardened modules providing all the needed protection from the elements, according to Mark Towfiq, CEO of NextFort. “Our design allows the customer complete control of their suite,” said Towfiq. “It’s a simple, modular design that is reliable and repeatable. Towfiq is a veteran of the data center industry, having founded Intelenet, an Irvine, Calif. business that he sold, bought back, and then sold again. Towfiq started Intelenet in 1994, and sold it to Denver-based telecom FirstWorld Communications in 1999. After reacquiring the Irvine data center in 2002, he sold the company to Latisys in 2007. Towfiq said NextFort is researching several additional markets to expand its concept, but started in the Phoenix area because it is less vulnerable to natural disasters than other markets and power is relatively cheap at about 6.5 cents per kilowatt hour. That’s a fact that has helped drive growth for several Phoenix provider, especially IO (the largest player in the (Phoenix market) , but also Phoenix NAP, Digital Realty and CyrusOne. “Chandler seems like it’s becoming a hub for hosting and colocation,” said Towfiq. “But we all focus on different types of customers.” “Cloud providers have been very interested in our design, and will be one of the biggest core sets of customers,” he added. “We also have large enterprises that are interested in this design for their private clouds, because of the security. When we open, we will have a number of customers in place.” An illustration of the interior of a NextFort module. (Image: NextFort) (Comment on this)
1:38p	Plexxi Launches a Smarter Approach to SDN Networking Networking startup Plexxi has come out of stealth with a new switch (shown above) and software defined networking (SDB) system to simplify network connections. (Image: Plexxi) After a few years in stealth mode, networking specialist Plexxi has officially launched a complete software defined networking (SDN) system. In support of  cloud and virtualized data center networks it is introducing  Plexxi Control and Plexxi Switch 1 products. Based on a concept it calls Affinity Networking, Plexxi’s innovation is in creating the most direct networks by managing traffic between devices based on workload requirements. Plexxi Control is server-based software that dynamically determines the best way to connect devices to satisfy all workload needs. Plexxi also offers a switches that provides low-latency 10Gb and 40Gbps Ethernet connections through a high capacity LightRail optical interface. “We cannot keep throwing capacity at the problem by connecting everything to everything as a single monolithic network,” said Tom Nolle, president of CIMI Corporation,a network consulting firm. “It’s inefficient and cost prohibitive. The solution is creating a new dynamic infrastructure that is created and dynamically formed by the cloud. Plexxi lets the network rise up to meet the cloud.” With SDN-based affinity-driven network orchestration Plexxi Control enables a dynamic fit to the network needs and workloads through advanced algorithms. Using distributed processing at the edge of the network the multi-tier SDN controller provides scale and performance and centralized knowledge for topology planning and optimization. The Plexxi Switch provides the underlying dynamic physical network structure that can implement those fittings exactly as specified – by leveraging high-density optical multiplexing to create simple, single-tier, fully orchestratable networks. The LightRail interconnect system provides 400 Gbps of dynamically assignable core capacity per switch, scaling linearly with each switch, achieving, for example, 100 Tbps in a 250-switch network. “Software defined by itself is meaningless,” said Steve Duplessie, founder and senior analyst at ESG. “Defining application requirements and having infrastructure dynamically adapt to those requirements to guarantee service levels is what matters. The ability to control the outcome is what matters – and you can’t control the outcome unless your underlying infrastructure is smart enough to adapt to changing requirements. That’s probably the number one reason I’m fascinated with the likes of Plexxi. They not only let me build a smarter, much more efficient network, they adapt to guarantee I can accomplish my reason for being – to adapt appropriately to application demands.” In its previous stealth mode Cambridge-based Plexxi raised $48 million in venture financing from Lightspeed Venture partners, Matrix Partners and Northbridge Venture Partners. In the following 1:12 video Plexxi explains affinity networking. (Comment on this)
3:00p	Citrix Manages Enterprise Mobility With Zenprise Acquisition Citrix (CTXS) announced  it has entered into a definitive agreement to acquire Zenprise, a leading innovator in mobile device management (MDM) . The Bring Your Own Device (BYOD) trend has been big in the enterprise, and will continue to grow over the next 12 months. Zenprise meets the IT challenge of managing thousands of devices with a user-centric solution to enable BYOD to work securely.  Together Citrix and Zenprise will provide a single, integrated enterprise mobility product line from a trusted vendor that combines all the power of MDM, with the ability to manage mobile apps and data across any mix of user devices. “Consumerization and BYO have given rise to very difficult challenges for businesses in enabling a productive, mobile workforce while still maintaining tight controls over company information,” said Sumit Dhawan, VP and GM of Mobile Solutions at Citrix. “Zenprise was a clear choice for Citrix, with its leading MDM product, an experienced team, a history of innovation, and a footprint on more than one million devices. With a complete Citrix enterprise mobility solution, customers have all the necessary pieces to manage and secure mobile apps, content and devices.” Citrix intends to integrate the Zenprise solution for mobile device management, with its Cloud Gateway and Me@Work solutions for managing mobile apps and data. This combination delivers a complete stack for enterprise mobility and gives the option of on-premise or cloud solutions. The Zenprise slogan is ‘Putting mobile to work’ – and its success was validated earlier this year, when Gartner positioned Zenprise in the leaders quadrant for Mobile Device Management Software. In a blog post regarding the acquisition Zenprise CEO Amit Pandey said that the company “has been building on its secure device lifecycle management platform to help organizations secure and manage mobile apps and data, and do it in a way that harmonizes IT’s needs with the end-user experience. Last year we were the first MDM vendor to introduce Mobile DLP with secure access to Microsoft SharePoint.” “This combination not only brings together incredibly complementary products, but a shared culture of innovation,” said Waheed Qureshi, Chairman and CTO of Zenprise. “Citrix and Zenprise have each proven their ability to deliver leading offerings in a fast-paced market. Together, we will accelerate our ability to anticipate and exceed our customers’ expectations for world-class enterprise mobility solutions.” (Comment on this)
3:30p	Data Center Containment Provider Due Diligence This is the fifth article in a best practices series on data center energy efficiency through effective airflow management strategies. Containment providers include Eaton, APC, Emerson, Chatsworth, Electrorack, AFCO Systems, Subzero Engineering, and Polargy. When considering containment providers and their solutions, make sure to do your due diligence. Consider the following points during that process: Know your heat containment needs and how much heat you need to manage. Know the thermal profile of all equipment coming into the data center. Know the fire protection codes and how containment will affect these. Know what else the containment strategy will affect. Know how much cooling you need up front and how much to plan for the future. Know what you are supporting today for IT and the business and how business decisions will affect future planning. Link facilities planning to business planning. Know room geometry and the constraints of cold air delivery and hot air removal when planning for containment. Know your space and how well a vendor solution will integrate with the existing racks, whether uniform or non-uniform. Know whether you will have an outage window for installing containment and the risks around production equipment during containment assembly. Next Thursday’s article will cover Data Center Containment Considerations and Recommendations. If you would prefer, you can download the complete Data Center Knowledge Guide to Data Center Containment in PDF form, courtesy of Eaton. (Comment on this)
3:46p	Visualizing Trends in “Energy Per Operation” Winston Saunders has worked at Intel for nearly two decades in both manufacturing and product roles. He has worked in his current role leading server and data center efficiency initiatives since 2006. Winston is a graduate of UC Berkeley and the University of Washington. You can find him online at “Winston on Energy” on Twitter. WINSTON SAUNDERS Intel The fun of being a data nerd is the irrepressible urge to look at facts in different ways on the whim of gaining insights previously not evident. The other day I was thinking about SPECpower data. I wondered if looking at the separate roles of power reduction and time reduction in overall compute efficiency might better convey what was happening. By now you should be familiar with the “Evolution of Energy Efficient Performance,” which reveals trends in server platform energy proportionality as measured by the SPECpower benchmark. You can refer to this chart, if you aren’t familiar with the trend. How Have These Improvements Been Accomplished? What is less obvious are the means by which energy efficiency of computing is improved. To understand this I thought I’d look at the data somewhat differently. Assuming a 10% of peak workload, we can consider the time per operation (which is the reciprocal of operations per second) and the power in the following graph. Energy Efficient Performance. Analysis of data from SPEC.org Each data point is labeled for correspondence to the first figure. What is interesting is the stair-step pattern. From 2006 to 2008, we moved from 65nm to 45nm silicon technology, and, from 2009 to 2010, the change continued downward from 45 nm to 32nm silicon technology. In each case, the time to complete an operation decreased by about half. Complementing that, from 2008 to 2009, and from 2010 to 2012, were significant micro-architecture changes. These resulted in time reductions associated with performance gains, but also significant power reductions. What I like about this graph is the overall improvement in energy efficiency is easily visualized as the product of time and power. These are shown for 2006 and 2012 as the rectangles in the graph. The area of the rectangle is the energy per operation and the impacts of proportional power architecture and performance on overall efficiency are evident. The trend of energy per operation follows a strong trend versus the “system available” date from the SPECpower data. The exponential fit is equivalent to a 41% per year reduction in the energy per operation and about a factor of twenty over the range shown. Imagine if we could tap into that kind of energy reduction per mile driven or lumen generated by a lightbulb. Just to put the energy into a framework, 0.5 milli-Joules is the energy needed to light a 100Watt bulb for about 5 microseconds. Analysis of data from SPEC.org So to summarize, the efficiency of two-socket servers has increased dramatically. The efficiency gains result from the increased performance and energy proportionality of the systems. Transitions in transistor architecture result in large performance gains resulting in a reduction in the time necessary to complete a given workload. Transitions in system architecture also result in performance gains, but in addition lower the power consumption while the operation is being completed. This in some sense “doubles” the efficiency gains expected. This efficiency gain is easily visualized by looking at the time to complete an operation and the power used during that time. Over the last few years, the tremendous focus to improve the efficiency of servers under realistic workload scenarios has resulted in a 40% per year reduction in the energy per operation. These kinds of efficiency gains, I would claim, are a fundamental element driving our digital economy; a kind of “Jevon’s Paradox” on steroids. Industry Perspectives is a content channel at Data Center Knowledge highlighting thought leadership in the data center arena. See our guidelines and submission process for information on participating. View previously published Industry Perspectives in our Knowledge Library. (Comment on this)
6:00p	Pulsant Expands Data Center North of London UK cloud and colocation company Pulsant announced that it has completed a £3.8 million (~$6.1 million) expansion at its tier 4 data center in Milton Keynes, north of London. The 37,000 square foot data center expansion will support both large and small UK businesses, and  will provide additional space for Pulsant’s existing enterprise and large-scale financial service tenants to grow. The Milton Keynes facility provides superior resilience through multiple utility sources, advanced power management and sophisticated operational and system monitoring. It is designed to minimize environmental impact as 100 percent of its energy is from renewable and sustainable resources. “This is a flagship data centre in a prime ‘out of London’ location for businesses seeking an established, high quality, highly secure and PCI compliant facility,” said Mark Howling, CEO at Pulsant. “It operates to ISO27001, supports high rack power densities up to 15Kw, is connected by a resilient, multi-carrier high speed network with 0.2ms of network latency and is within one hour of the Capital.” The expansion will also be used to provide multi-site capability for Pulsant’s recently launched Enterprise Cloud platform. The new platform was built with HP servers, Intel E5 processors and VMware virtualization. “Many businesses, particularly in financial services, retail and enterprise sectors, as well as Software as a Service providers, are looking for Tier 4 facilities that offer the right combination of resilience, 100 per cent availability and 24/7 service,” added Howling. “At Milton Keynes, Pulsant is able to provide flexible, cost-conscious data storage solutions that meet a broad range of needs. For those whose data is absolutely crucial for sales, CRM or business operations, our enhanced Tier 4 facilities offer unmatched resilience, performance and support to keep their websites, databases and networks live at all times. That’s why over 100 customers already trust our Milton Keynes site.” (Comment on this)
10:30p	AST Modules Beat the Heat in the Iraq Desert It’s one thing to design modular data centers that perform well in the cool climates of Iceland. It’s another matter to build a module that can operate at 130 degrees  F (55 degrees C) in the summer heat of the Iraq desert. One company that has accomplished both tasks is AST Modular, a Barcelona-based company that specializes in providing modular data centers to global customers including IBM and Opera, the tenant in the aforementioned facility in Iceland. AST recently supplied a four-site modular installment to a major oil and gas company to provide IT support for its oil well operations in Iraq. To beat the heat in the desert, the modules are using  AST’s Hot Corridor Exchanger, a water based overhead cooling technology that employs variable-speed fans and a water coil with an oversized surface. AST says the extended surface of the coil allows the chiller to supply water at higher temperatures, thus resulting in improved energy efficiency. The client had no central data center operation in Iraq, and its previous distributed IT system as capacity-constrained and didn’t meet the company’s standards for operational performance. AST Modular’s containerized data centers are designed to operate in harsh conditions. All infrastructure components are installed at AST’s manufacturing plants, resulting in a pre-fabricated module. The cooling units are “tropicalized” – using condensers that are larger than usual to operate in temperatures up to 55 C (130 F). Several of the units feature a pressurized vestibule to protect the equipment. The first unit was transported by road from AST’s facilities to the port in Barcelona, and then shipped to a harbor in Turkey, and then trucked to its final destination. Subsequent units were shipped to a port in Dubai, and than traveled by road to their final destinations. (Comment on this)

<< Previous Day

2012/12/06 [Calendar]

Next Day >>