Tape libraries, like this one at Google, provide an example of the use of robotics to manage data centers. Robotic arms (visible at the end of the aisle) can load and unload tapes. (Photo: Connie Zhou for Google)

There is an evolution happening within the modern data center. Huge data center operators like Google and Amazon are quietly redefining the future of the data center. This includes the integration of robotics to create a lights-out, fully automated data center environment.

Let’s draw some parallels. There’s a lot of similarity between the modern warehouse center and a state-of-the-art data center. There is an organized structure, a lot of automation, and the entire floor plan is built to be as efficient as possible. Large organizations like Amazon are already using highly advanced control technologies – which include robotics – to automate and control their warehouses.

So, doesn’t it make sense to logically carry over this technology to the data center?

Robotics in the Data Center

As the reliance on the data center continues to grow, full software and hardware robotics automation is no longer a question of if, but a matter of when, technologists predict. Robotics organizations, like Chicago-based DevLinks LTD are already having conversations and creating initial designs for data center robotics automation.

Scott Jackson, Senior Robotics Programmer at DevLinks, says it’s becoming quite feasible to have a robot fetch a drive, blade or even a chassis and deliver it to a central bay for replacement.

“Simple RFID tags, laser and barcode identifiers can create true data center automation,” Jackson explains. “For example, you can tag drives with RFIDs and assign them to be wiped, destroyed and reused as needed.” Conveyor systems are able to run in parallel to robotics within the data center environment.

There are already working examples of robotics in the data center. Tape archives seen at Google and high-performance computing data centers use robotic arms to locate and retrieve backup storage tapes.  (For an example, see this video of a system in action at the NCAR data center).

What Will Be Different?

What might a robot-driven “lights-out” data center look like? There would be rail-based robotics capable of scaling the entire data center. Here’s an interesting wrinkle: the modern data center would no longer be limited by horizontal expansion space. When using robotics, data centers can literally scale upwards. Utilizing space in the best possible manner is always a challenge for data center providers, so having the ability to scale both horizontally and vertically becomes a huge advantage.

“These robotics can scale the entire rack, which can now be much taller because of these intelligent robots can reach higher,” said Jackson. “Once a part is removed, a conveyer at the bottom can move the part to the appropriate floor space. Furthermore, detailed vision technology has progressed a long way as well. Solutions like Cognex are able to allow machines to take pictures of a device, barcode and many other variables to help identify the part’s destination or origin.”

Large organizations that invest heavily in their data center infrastructure are actively exploring robotics solutions to help them better control their data centers. IT shops such as Amazon and Google are looking at ways to create a fully automated, lights out data center. AOL has taken a first in that direction with an unmanned data center facility.

The Cost Equation

As with any technology, costs for custom data center robotics will start high and come down as time progresses and platforms become smarter. Smaller robotics are already becoming less expensive. Manufacturers like FANUC develop large machines; but they also create smaller, more agile robotics. Models like the LR and the Mate M-1iA are paving the way for super-agile, fast, robotics capable of granular part identification and distribution.

Both data center, automation, and robotics technologies have come a very long way over the past decade. From the warehousing perspective, robotics already know where everything is located, how to put things in order and are able to directly interact with the human-created automation scenarios. Because of robotics, something very interesting has happened: Instead of the human going to the warehouse, the warehouse comes to the human.

Soon it will be possible to do this at the data center level.

This would enable entirely new approaches to operations. Your data center will be able to run at a different temperature level, you won’t need any lights, and you can directly integrate your new robotics platform into a modern-day automation and orchestration platform. From a central command center, the human operator can maintain visibility into their data center environment, the robotics infrastructure and the workloads that are being managed. This can all be done without the need of a single person on the data center floor.

Microsoft is the first major U.S. provider to launch a public cloud in China. Windows Azure is rolling out in China through partner 21Vianet Group, a large carrier-neutral internet data services provider. Windows Azure service in China will be available on June 6.

Microsoft CEO Steve Ballmer attended an event for the launch with 21Vianet CEO Josh Chen, US Ambassador to China Gary Locke and Shanghai Governor, Jiang Liang.  Also in attendance were CEOs from several of the platform’s initial and potential customers.

This is a big development for Microsoft, and huge news for 21Vianet. In November 2012, Microsoft, 21Vianet and the Shanghai Municipal Government announced a strategic partnership agreement in which Microsoft licensed the technology know-how and rights to operate and provide Office 365 and Windows Azure services in China to 21Vianet.

“21Vianet will act as an operation entity for Azure, hosting the service in its data centers and handling the customer relationship,” said Vianet’s CFO, Shang Hsiao. ”We also support the infrastructure too. That’s one of the reasons Microsoft selected 21Vianet – we specialize in China internet infrastructure. We’re considered the biggest Internet data center services provider in China.

“In China at this moment, we don’t have open cloud services,” Hsiao continued. “This will be the first cloud partner outside of China to serve cloud customers. It’s very important.”

21Vianet already has several customers lined up for the service. Named in the press release are Pactera, RenRen Inc, PPTV, a leading online video company in China, Kingdee International Software, and QOROS Auto Co. an independent international car company. Many of these names will be unfamiliar to Western audiences, but therein lies why this announcement is huge; China is a massive market whose potential hasn’t been tapped. Microsoft, through 21Vianet, is first in with an outside public cloud.

“We are extremely excited to officially launch Microsoft Windows Azure services in China and believe 21Vianet will provide great contributions to the growth of cloud infrastructure and services throughout China,” said Chen, Chairman and CEO of 21Vianet. “Our cooperation further enhances 21Vianet’s capabilities in helping to develop China’s cloud infrastructure services and strengthening our core competency for customers.

“As a cloud enabler, 21Vianet is pleased to offer Microsoft’s world-class cloud services for the first time to businesses in China,” Chen added. “By providing carrier-level services for better public cloud operations, including security and compliance, datacenter networking, maintenance, highly reliable engineering and customer services related to cloud operations, 21Vianet and Microsoft are committed to offering the best cloud services available throughout China.”

@WalmartLabs acquires OneOps.  @WalmartLabs – the technology arm of the retail giant’s Global eCommerce division, announced that it is acquiring OneOps, an application lifecycle management company. OneOps was founded by former eBay employees Kire Filipovski, Vitaliy Zinchenko and Mike Schwankl. With the acquisition @WalmartLabs gains the Platform-as-a-Service capability that automates and accelerates many processes related to environment management, application deployment and the monitoring of datacenter operations. @WalmartLabs also acquired software development company TastyLabs. Founded by Nick Nguyen, Paul Schachter and Joshua Schachter, the Silicon Valley startup developed innovative social and mobile applications such as Jig, skills.to and human.io. Nick and Paul will join @WalmartLabs as full-time associates, while Joshua, who also created del.icio.us, will join as a consultant.

Hortonworks for Windows now available.  Hadoop contributor Hortonworks announced the availability of Hortonworks Data Platform (HDP) for Windows, a 100 percent open source data platform powered by Apache Hadoop. HDP for Windows is the first production-ready Apache Hadoop-based distribution that runs on both Windows and Linux, providing a common user experience and interoperability across operating systems. HDP includes all of the necessary components to refine and explore new data sources, as well as extend existing investments in applications, tools and processes with Hadoop. “Microsoft is committed to offering the best solutions for big data, and Hortonworks Data Platform for Windows extends our efforts to provide big data customers with access to Apache Hadoop-based solutions,” said Eron Kelly, general manager of product marketing for SQL Server at Microsoft. “HDP for Windows not only enables organizations to deploy Hadoop projects on Windows Server but also allows for easy migration to Windows Azure HDInsight Service in the cloud. Customers gain great Hadoop-based solutions across whatever environment they choose.”

Tableau announces IPO.  Tableau Software (DATA) announced the pricing of its initial public offering of 8,200,000 shares of its Class A common stock at a price to the public of $31.00 per share. Shares began trading last Friday under the NYSE symbol DATA. The Seattle based software company transforms the way people see and understand data to solve problems. The company was founded by Stanford graduates, and has helped business intelligence and data analytics efforts at LinkedIn and Facebook.

Concurrent launches Hadoop scoring engine.  Big Data application platform company Concurrent announced Pattern, a free, open source, standard-based scoring engine that enables analysts and data scientists to quickly deploy machine-learning applications on Apache Hadoop. Pattern lowers the barrier to Hadoop adoption by enabling companies to leverage existing intellectual property in predictive models, existing investments in software tooling and the core competencies of existing analytics staff to run Big Data applications from existing machine-learning models using Predictive Model Markup Language (PMML) or through a simple programming interface. “Concurrent is tearing down barriers for mass Hadoop adoption,” said Chris Wensel, CTO and Founder, Concurrent. ”With Pattern, we have cleared another path by enabling data scientists to more easily bring their work to production. When combined, Cascading, Lingual and Pattern close the modeling, development and production loop for all data oriented applications. The combination of the three is the application ensemble for further enabling enterprises to drive differentiation through data.”

“This financing round caps a tremendous year of momentum for the company,” said Michael Grant, CEO of Cloudscaling. “That momentum affirms the voice of the market, clearly stating that customers want more than OpenStack. They want an on-premise, OpenStack-based private or public cloud turnkey system solution that delivers architectural and behavioral fidelity with major public clouds like Amazon Web Services. Our Open Cloud System product delivers on that need to enable hybrid cloud application deployments that span private and public cloud services.”

In 2013 Cloudscaling has secured key customer wins with LivingSocial, EVault, Ubisoft and DataFort, launched a channel partner program, and announced support for OpenStack Grizzly in the third generation of its OCS technology, Open Cloud System 2.5.

Partnership With Juniper

When Cloudscaling announced Open Cloud System 2.5 in April, it was also the first step of its partnership with Juniper through the integration of Juniper’s virtual network control (VNC) technology, JunosV Contrail, into Open Cloud System (OCS). OCS is a turnkey, OpenStack-powered cloud infrastructure system for enterprises, SaaS providers and cloud service providers. Juniper liked what they saw.

“Juniper Networks and Cloudscaling share a vision of how cloud infrastructure should be built and operated to support a new generation of cloud-aware workloads,” said Jeff Lipton, VP of venture and strategic investments at Juniper.  “Collaborating to integrate our technology into OCS was just the first step. We are excited to continue our work with Cloudscaling and support the company as a strategic investor.”

Cloudscaling and Juniper plan to continue delivering innovative, joint networking solutions that are open and standards-based to support elastic cloud services and a new generation of enterprise workloads.

Cloudscaling also joined the Seagate Cloud Builder Alliance Partner program in April. Seagate liked what it saw.

“Seagate and Cloudscaling are working together on innovative solutions of jointly-optimized cloud systems supported by Seagate products,” said Rocky Pimentel, EVP and chief sales and marketing officer, Seagate. “We are pleased to deepen our relationship with them as an equity investor and be part of a collaborative effort to define and promote open source standards for cloud computing.”

Cloudscaling and Seagate are focused on the development of optimized storage solutions for OpenStack-powered cloud infrastructure.

Seagate and Juniper join Trinity Ventures, which so far seems happy with Cloudscaling’s prospects. “Cloudscaling has executed on a vision of elastic cloud infrastructure as a turnkey solution that many agree with but few have delivered,” said Dan Scholnick, general partner, Trinity Ventures. “The team has gained new customers and partners at an accelerating pace, highlighting their success at tapping an emerging, growing need among enterprise, SaaS and service provider segments.”

“Nowhere do speed and availability matter more than in eCommerce,” said Ted Middleton, EdgeCast VP of product management. “The Internet’s top retailers told us they wanted a discrete, secure, global network that they didn’t have to share with other types of content, so we spent the past year building exactly that.”

Edgecast designed, tested and built the new network in major metropolitan centers around the world over the course of a year. It’s based on the same proven methods Edgecast has been using for the past six years on its content delivery network.

The new solution offers optimized communication path to serve content and handle transactions regardless of conditions on the broader internet or with other EdgeCast CDN networks. eCommerce customers completely avoid competition for resources with other customers in different segments.

Security being a major concern, the network is architected with robust redundancy and failover, elastic provisioning for holiday-type traffic spikes, and credit card detection and removal algorithms.

Performance optimizations include secure pre-establishment of sessions between origin and end user. Mobile device detection and front end optimization is built in. Optimization is executed directly on edge servers for the best possible performance.

EdgeCast also aligns the network’s operating policies with eCommerce business cycles, conducting code freezes during the busiest shopping times to ensure 100 percent availability and stability.

“With Cloud Bus, TIBCO is combining the deployment flexibility of the cloud with enterprise-class integration features in a single subscription service that customers can run anywhere – on-premise, in the cloud, in bare metal or virtualized environments,” said Matt Quinn, CTO for TIBCO Software. ”TIBCO Cloud Bus provides ready-made integrations across popular SaaS and critical on-premise applications, while allowing subscribers the ability to identify, configure and extend integration templates for their own business context with ease. Finally, and as you would expect from TIBCO, Cloud Bus includes extensive capabilities for real-time integration, meaning changes are reflected in all connected applications as they happen, without waiting for the next batch update.”

Single subscription model

TIBCO Cloud bus subscribers can deploy cloud applications and only pay for what they consume. The solution provides ready-made integrations for a variety of applications such as Salesforce.com and other vendors. Changes are reflected in all connected cloud applications as they happen, without waiting for the next batch update, and connectivity capabilities to deliver real-time integration.

“If a company’s approach to integration is too fixed or locked-in, it could limit the company’s ability to leverage the cloud or switch SaaS providers once it’s there,” said Quinn. ”TIBCO Cloud Bus offers a choice of deployment options, ready-made integrations, and real-time integration support that delivers the flexibility and time to value that enterprises are looking for in moving applications and workloads to the cloud.”

On Tuesday VMware (VMW) unveiled vCloud Hybrid Service, an infrastructure-as-a-service (IaaS) cloud built and operated by VMware. The virtualization pioneer’s entry into the public cloud arena prompted lots of analysis and commentary from around the web. Here’s a look at some of the most notable posts:

Gartner – Lydia Leong comments on her CloudPundit blog: “VMware has previously had a strategy of being an arms dealer to service providers who wanted to offer cloud IaaS. In addition to the substantial ecosystem of providers who use VMware virtualization as part of various types of IT outsourcing offerings, VMware also signed up a lot of vCloud Powered partners, each of which offered what was essentially vCloud Director (vCD) as a service. … In theory, this was a sound channel strategy. In practice, it didn’t work.”

The Register – From Timothy Prickett Morgan: “the vCloud Hybrid Service is not so much about competing against AWS, Rackspace Cloud, and other public clouds as it is about giving the now 500,000 customers using the ESXi hypervisor to virtualize their servers a place where they can burst their workloads and a reason to buy vCloud Director and other tools in the VMware box.”

Ars Technica – Here’s the “where” question answered:”VMware’s US-based services will be available to early access customers in June and will be generally available in the third quarter of this year from data centers in Santa Clara, CA; Dallas, TX; Las Vegas, NV; and Sterling, VA. Services will be offered from data centers in Asia and the EMEA (Europe, Middle East, and Africa) sometime in 2014. Customers outside the US aren’t prohibited from using the US-based services, but they would have to handle some latency.”

ITworld – Another reason the Vmware cloud isn’t an Amazon killer: “Individual developers won’t be able to sign up quickly and easily to start using compute services from VMware. The vCloud Hybrid Services are sold either on an annual or monthly basis. I’m not exactly sure yet but that sounds like services will be sold the same way that VMware products are sold today – through sales people or partners. There won’t be any chance to visit a web site, plop down a credit card and get to work.”

GigaOm – Jordan Novet has details on pricing: “The vCloud Hybrid Service actually has two flavors: a Dedicated Cloud mode has “physically isolated and reserved compute resources” for predictable workloads and a Virtual Private Cloud for seasonal workloads that require greater elasticity but are multitenant in nature. The former service will start at 13 cents an hour for a 1 GB virtual machine with a single processor on an annual basis, while the latter will start at 4.5 cents an hour on a monthly basis.”

DICK BENTON
Glasshouse

Last August, I outlined seven key tips IT departments should follow to build a better service strategy for their internal users. Since then, I’ve taken a deeper dive into each of these steps on the way to becoming an Internal Cloud Provider (ICP), an essential transformation if IT wants to align with company goals and user expectations. My last post addressed the sixth step, proving what you delivered; in other words, it’s important to show management and service consumers that you’ve met the established service level agreements (SLAs) and key performance indicators (KPIs) for your IT services.

Now, we’ve come to the seventh and final step in this process: capture client satisfaction.

So you now have your nascent cloud service offerings out there in consumer land. Your service offerings are being selected by the end user from your Web-based service catalog. They are intelligently choosing the service they really need, because you have provided service attributes in terms the consumer can understand, and you have also identified the cost of each service offering to assist in their selection.

You have provided a mechanism not only for auto selection, but also for auto deployment. Services selected are now provisioned automatically under appropriate policies agreed by management. Mean time to provision is now a matter of minutes or hours instead of days and weeks. Each month, you produce your score card showing which groups, departments or divisions have consumed which service offerings and at what costs, and you have confirmed in formal reporting that all SLAs have been either met or exceeded.

Determine Satisfaction and Look to Tomorrow

What more can IT do? To lock in your new understanding of consumer needs and to stay abreast of trends in these needs, it is essential to include a survey into your processes. This is not just a satisfaction survey vainly seeking confirmation that IT has indeed “done well”. Rather, it’s critical to use this opportunity to ask probing questions to get a handle on how needs are changing and how future offerings might be driven.

The satisfaction survey process provides an opportunity to capture consumer needs, consumer consumption behaviors and service offering usage as well as satisfaction levels with your services. It is a tool you can use to better understand individual and overall service requirements. This is what we mean by aligning IT with business needs. Your metrics reporting should have already allowed you to identify frequent consumers from the occasional. You should also have a good handle on who is consuming what and be able to classify small, medium and large consumers. If you have offered services that lend themselves to being turned off as easily as they are turned on, you can also get a handle on the mean time-to-live of the various service offerings.

Survey Can Help Set Your Roadmap for the Future

The above information allows you to craft an intelligent survey that seeks information to assist you in planning new services to meet changing needs, changes to existing services as business drivers change, and even end-of-life decisions for some services that are no longer in demand. This knowledge is critical to retaining your relevancy to the consumer for your service offerings, and to remain competitive with outside public operations. It’s always a good idea to formally review what your competition is up to. Just because you think your consumers are captive doesn’t mean they see themselves as captive. Review the competition’s service offerings at least monthly, and follow their PR news feeds for service offering announcements. These new service offerings may well be suitable grist for your survey, to identify if there is a need for these within your organization.

Finally, there is room for the classic component of the satisfaction survey. How well did you do? A scale of one to five is usually sufficient. Further levels of granularity add little. One through five provides a high, medium and low score with something in between for those who want to be picky. Start by asking consumers to assess the service offerings themselves. Are the service offerings meeting their needs? Would more offerings be helpful?  Be sure to allow for written feedback as well. Then move to questions around ease of use. Can they find the service offerings they are looking for? How easy is it to find the service offering they seek? How easy is it to select the service offering and place an order? Are the terms and conditions of the service offering clear? Do they think the costs of the service offerings are reasonable and competitive?

Next, move on to the deployment process. The key question here is to ask how they feel about the mean time to provision the service they ordered (self-selected). Did they get the service they asked for? Were there any additional clerical steps required for approval? (This allows you to count such instances). Was the service delivered as promised? Were SLAs met on each occasion? Was the monthly/weekly reporting adequate? Did they need to escalate any issue? (Capture, count and classify). How do they feel about IT’s ability to respond to their issues? How do they feel about IT’s ability to resolve their issues? How do they rate the internal IT cloud against the competition (Amazon)?

The creative mind can conjure a number of other questions to include in the survey; however, there is a risk of driving boredom or even dissatisfaction once a survey gets beyond a certain size. Perhaps 10 to 15 questions should be sufficient to capture key information about the services you offer, your ability to respond to consumer demands, and trends and future service offering needs. There are quite a few Web-based survey tools, and many are free like Survey Monkey.

By running regular surveys, and even embedding mini surveys in your selection, approval or quote process and the provisioning and deployment process, a wealth of information becomes available to the IT organization dedicated to improving consumer satisfaction and continuous improvement. In summary, here’s the top tips to keep in mind:

• Build surveys into your service order and service fulfillment procedures;
• Run a quarterly satisfaction survey on your clients;
• Differentiate between large clients and most frequent users, and small clients and least frequent users; and
• Use the information to ensure you are delivering the service offerings your consumers need, with attributes they value, at prices they can afford.

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.

Power infrastructure in a data center (Photo by Tim Dorr via Flickr)

Last week the New York Times suggested that the data center industry has become a “wildcat power utility” by reselling power to customers at a profit and ripe for regulation. So we reached out to experts who were familiar with both data centers and utilities and asked: Is the data center industry a candidate for regulation as a utility?

Their answer: Although power is a key component of their offerings, data centers differ from utilities in very significant ways. Another key point is that data center clients are typically sophisticated companies that are paying premium prices, and unlikely candidates for exploitation by service providers – a key historical concern of utility regulation.

But these experts also noted that some industry practices open the door to greater scrutiny, and data center operators need to be more transparent about their practices to address concerns.

Times: Power A Central Component of Leases

In its story last week, The New York Times took a critical look at power provisioning in data centers. “Electrical capacity is often the central element of lease agreements, and space is secondary,” the Times wrote. “A result, an examination shows, is that the industry has evolved from a purveyor of space to an energy broker — making tremendous profits by reselling access to electrical power, and in some cases raising questions of whether the industry has become a kind of wildcat power utility.”

The paper added that “the capacity pricing by data centers …. appears not to have registered with utility regulators.”

Regulating data centers as utilities “doesn’t seem plausible to me,” said Coy Stine, Director of Data Center Services at Bluestone Energy, which works with utilities on energy efficiency incentives. “Data centers provide the service of a highly conditioned and very reliable power source. Customers can’t get that by plugging their services into the utility power plug in the wall. Comparing a data center to a utility is similar to saying a car manufacturer is a provider of sheet metal. The automobile has metal as a component, but there’s much more to it. The data center provider is playinhg the same role.”

“I think data centers are a whole different animal,” said Jon Koomey, a research fellow at Stanford University who has done several landmark studies on data center energy use. “It’s not only the cost of a kilowatt of power. They’re charging for equipment and infrastructure like backup generators. These data centers aren’t like individual households. The key difference is that these (customers) are people who know what they’re doing.”

Sophisticated Customers

Both Koomey and Stine said they have heard of concerns being raised about the role of data centers in energy purchasing. But they say that equating data center providers to residential or office landlords is a flawed comparison, as they offer different services and have different types of customers.

“I think it stems from the old model of tenants being exploited by their landlords,” said Koomey. “The people that are renting data center space are typically pretty sophisticated folks who are paying a lot of money for these services. This idea that they’re taking advantage of these clients doesn’t make sense.”

“Data center customers have teams of people to negotiate their SLAs (service level agreements) very carefully,” said Stine. “The cost for the data center operator to buy switchgear and UPS gear and generators is factored into the cost to the customer. I think the customers understand this, but the general public does not. Most of the audience of the New York Times doesn’t understand what happens in the data center.”

CHRIS CURTIS
Compass Datacenters

High explosives. Who doesn’t love them? Isn’t a large part of our culture based on blowing things up? Certainly some of our leading celebrities have made whole careers out of appearing in movies that feature one massive explosion after another. Well, the world of data center development is no different. It doesn’t happen often but, every once in a while, we have to roll out the dynamite and do some serious blasting. Like most things in the development world, the need to conduct controlled explosions has some plusses and some minuses.

Lessons in Geology

Most of the time, the average data center can be built without the need to prepare the site using cataclysmic force, but our site resides on what geologist’s refer to as a “limestone shelf.” In the technical parlance used by we developers. this is referred to as “a bunch of rock.” Maybe not as scientific, but a lot more descriptive. I don’t mind telling you, this news made the on-site guys positively giddy with excitement. The prospect of going to work and getting to say things like “fire in the hole” just seems to bring out the best in folks.

Despite the electric atmosphere that the prospect of dynamite utilization brings, this is serious stuff. You know how your mother used to say that it’s “all fun and games till someone gets hurt,” well, this a few notches above that. Being blown to smithereens has a degree of permanence that you just aren’t going to find with the average office related mishap. Just like any refined activity, there is a protocol that must be followed before you can begin demolishing large swaths of real estate.

Telling the Neighbors

First, you must alert the locals. This means going from house to house to advise the occupants of the homes surrounding your project site that they might just want to keep the kiddies and pets inside between the hours of 9 and 11 this coming Tuesday. Naturally folks have questions, “Will it be loud?,” “Am I at risk from flying debris?,” “Can I watch?,” to which the answers are of course, “Yes,” “No” and “Sorry, but our lawyers won’t allow that.”

Second, you put up signs and mark off the area. With this type of signage I’ve found that it’s best to be simple and declarative: “Blast Site – Keep Out,” for example. Some developers prefer “High Explosive Area – Trespassers Keep Out,”, but I find this a little pretentious and wordy. Short and pithy also eliminates the possibility of your sign being liberally interpreted. No one wants to have someone’s body parts distributed though out your job site because they live in the neighborhood and decided that the word “Trespasser” didn’t apply to them. This type of thing can really hurt morale. When marking off the blast area I prefer to go conservative. Sure it costs you a little more in orange plastic fencing, but I think we can all agree that the phrase “better safe than sorry” applies here.

Dress Code: Hard Hat and Ear Plugs

I don’t think that I can describe the level of anticipation until the big day finally arrives. Remember waiting for that special gift at Christmas? This is better, since you now it’s actually going to happen, and you’re not going to get a sweater instead of that new bike you wanted. When blast day finally comes, everyone gets to wear a hard hat and ear plugs–this is a developer’s version of a Fourth of July celebration. I must admit that even though I’ve been to a few of these things I can barely make it until the time that the big switch is thrown. And once it’s thrown – wow. The explosions are deafening, there’s dirt and debris flying everywhere, grown men are jumping up and down and pointing – you just don’t get entertainment like this every day.

Someone once said that “There is always one guy who doesn’t get the memo,” and that’s the case with blasting. Just accept the fact that no matter how thorough your canvassing, or how many signs you post, someone in the neighborhood is going to complain. This being the case, I was not surprised when I received a nasty email from a local resident complaining about the noise and, helpfully suggesting that I build my data center somewhere else. Since all it takes is one crank with a friend that works at Channel 8 to turn your project into a PR nightmare, I recommend handling these situations in a face-to-face manner. As I said, I’ve been through this drill before so I put on my sympathetic face (Note: It’s good to practice this before your visit. Sometimes a sympathetic face can look more like an “I could care less” face, or worse, the “surly punk” face, so you really need to get into character before you go) and went to visit the offended party.

The Developer’s Listening Skills

My first grade teacher always told me to be a good listener. This is great advice for these types of “disgruntled neighbor” situations because, really, what else can you do? After all, the blasting is already done, and there’s a big hole in the lot behind their house, so you sit and listen. Remember to nod at all the points that they use to tell you that your actions are akin to a crime against humanity and assure them that the data center you are building will not have a negative impact on the neighborhood. And this is true. Since it only takes a few folks to run a facility and the building is full of servers, traffic and noise aren’t going to be on-going issues. This is what folks really want to know. Once you’ve apologized and assured them that the worst is over, even the most disgruntled citizen tends to listen to reason. After all, doesn’t everyone really just want to have their “day in court.”

As a developer, the pendulum of your activity can swing widely. One day, you’re just another swarthy guy enjoying the primal thrill of blowing things up, and the next, a mild-mannered Dr. Phil talking an irate neighbor off the ledge. In this role, you must be prepared for anything.

Stay tuned for the next article in the series, titled, Maybe We Should Turn This Data Center into an Ark: How Bad Weather Can Cause Chaos with a Construction Timeline.

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.