This year marks the 10th anniversary of the 1,200-square-foot data center at the Franklin W. Olin College of Engineering -- that means the facility has been operating three years longer than CIO and vice president of operations Joanne Kossuth had originally planned. Now, even though the school needs a facility with more capacity and better connectivity, Kossuth has been forced to back-burner the issue because of the iffy economic times.
"Demand has certainly increased over the years, pushing the data center to its limits, but the recession has tabled revamp discussions," she says.
Like many of her peers, including leaders at Citigroup and Marriott International, Kossuth has had to get creative to eke more out of servers, storage and the facility itself. To do so, she's had to re-examine the life cycle of data and applications, storage array layouts, rack architectures, server utilization, orphaned devices and more.
Rakesh Kumar, research vice president at Gartner, says he's been bombarded by large organizations looking for ways to avoid the cost of a data center upgrade, expansion or relocation. "Any data center investment costs at minimum tens of millions, if not hundreds of millions, of dollars. With a typical data center refresh rate of five to 10 years, that's a lot of money, so companies are looking for alternatives," he says.
While that outlook might seem gloomy, Kumar finds that many companies can extract an extra two to five years from their data center by employing a combination of strategies, including consolidating and rationalizing hardware and software usage; rolling out virtualization; and physically moving IT equipment around. Most companies don't optimize the components of their data center and, therefore, bump up against its limitations faster than necessary, he says.
Here are some strategies that IT leaders and other experts suggest to push data centers farther.
Relocate noncritical data. One of the first areas that drew the attention of Olin College's Kossuth was the cost of dealing with data. As one example, alumni, admissions staff and other groups take multiple CDs worth of high-resolution photos at every event. They use server, storage and bandwidth resources to edit, share and retain those large images over long periods of time.
To free the data center from dealing with the almost 10 terabytes of data those photos require, Kossuth opened a corporate account on Flickr and moved all processes surrounding management of those photos over there. Not only did it save her the cost of a $40,000 storage array she would have had to purchase, but also alleviated the pressure on the data center from the resource-intensive activity associated with high-resolution images.
"There is little risk in moving non-core data out of the data center, and now we have storage space for mission-critical projects," Kossuth says.
Take the pressure off of high-value applications and infrastructure. Early on, Olin College purchased an $80,000 Tandberg videoconferencing system and supporting storage array. Rather than exhausting that investment from overuse, Kossuth now prioritizes video capture and distribution, shifting lower-priority projects to less expensive videoconferencing solutions and YouTube for storage.
For example, most public relations videos are generated outside of the Tandberg system and are posted on the college's YouTube channel. "The data center no longer has to supply dedicated bandwidth for streaming and dedicated hardware for retention," she says. More importantly, the Tandberg system is kept pristine for high-profile conferences and mission-critical distance learning.
Standardize servers and storage. Dan Blanchard, vice president of enterprise operations at hotel giant Marriott International, boasts that his main data center is 22 years old and he intends to get 20 more years from it. He credits discipline on the part of IT as a reason for its long life, particularly in terms of standardization.
Each year, the IT team settles on a handful of server and storage models to purchase. If a new project starts up or one of the 300 to 400 physical servers fails, machines are ready and waiting. Storage is handled similarly.
Even switches, though on a longer refresh cycle of about five years, are standardized. "Uniformity makes it much simpler to manage resources and predict capacity. If you have lots of unique hardware from numerous vendors, it's harder to plan [out the data center]," Blanchard says.
He recommends working closely with vendors to understand their roadmap and strategize standardized refreshes accordingly. For instance, Marriott might delay a planned refresh if a vendor's announced feature sets are worth it.
Virtualize whatever you can. Blanchard also is a fan of virtualization. Marriott's pool of physical machines supports almost 1,000 virtual servers, freeing up floor space, power and cooling. Though virtualization requires high-power, high-density servers, the fact that Marriott is able to consolidate the pool to several hundred physical machines that are energy-efficient saves on overall data center consumption.
Gartner's Kumar agrees that consolidation is a positive for data centers because low-utilization servers -- those dedicated to just one or two applications -- consume almost the same amount of energy as highly utilized ones. "Just to keep a server on consumes 50% to 60% of the energy as it would if it were running full," he says.
Also, older servers tend to be far less efficient than those used for today's virtualization efforts.
Root out and retire unused or low-utilized devices and applications. Taking the previous point a step further, "organizations should "clean house," Kumar says. Data center managers should conduct an audit using asset management software or other such tools that garner visibility into application and hardware inventories.
When in doubt, move it out
If all else fails and it looks like you are going to bump up against data center capacity, don't be afraid to move servers, software or storage off-site. Options abound for taking up the slack, and they might even give you just enough leeway to eke several more years from your current data center.
Here are some options:
Head to the cloud. Companies like Amazon, HP, IBM and Oracle all offer cloud-based services that enable bursts in computing capacity when needed. For instance, if you have a seasonal project that would push your internal data center to its limits infrastructure-wise, you can temporarily contract server resources from a provider. This will meet your short-term needs without forcing a long-term investment.
Roll in a pod. If building out or relocating your data center is out of the question for your organization, a pod just might be the answer. Cisco, HP and Silicon Graphics International are among vendors offering portable data centers. These self-contained units can boost your overall capacity without the expense of a massive construction project.
Say hello to co-lo. Colocation is nothing new in the world of data centers. However, it can be your best friend when trying to avoid an overhaul of your existing site. By transferring some of your infrastructure to a provider's site, you can free up valuable floor space, power and cooling, but still maintain control of your hardware and software.
What you're likely to turn up: Some 5% to 10% of hardware devices are either switched off or are maintaining a single, rarely used application, according to Kumar. Falling back to the reality that servers consume energy and other resources at any utilization rate, either trash the application or virtualize it and retire or reuse the hardware.
"You have to make sure that every piece of hardware in your data center is doing productive work," he says.
At international financial conglomerate Citigroup, uncovering little-used applications is a regular exercise among the company's 14 data centers (the oldest has been in use for 20 years).
"Over the years, things get lost. Not only do we use asset management tools, but we also physically walk around the data center to make sure each device has a purpose," says Jack Glass, Citigroup's director of data center planning. He warns, though, to consult with applications teams before unplugging anything.
Glass agrees if a low-utilized application is consuming hardware resources, it should be virtualized. "Virtualization is definitely our standard here. If it can't be decommissioned, then, where possible, it gets virtualized," he says.
Contain test and development sprawl. IT leaders concur that most test and development folks will consume whatever resources you offer them and, therefore, must be carefully monitored. In fact, Citigroup's Glass says, he often finds abandoned or concluded test and development projects during his utilization reviews. Kossuth uses a proactive strategy to ensure that test and development efforts don't overtake her data center. She ropes off an area of the data center complete with server and storage resources as a sandbox. Usage is carefully monitored and when projects end, resources are immediately reabsorbed. She calls it a way to protect the data center without stifling innovation.
Look for duplicate data in your storage arrays. Jason Kutticherry, vice president of data center planning at Citigroup, says the company has made a concerted effort to reduce its storage footprint, saving on data center floor space, power and cooling. A key technology for this has been data deduplication, which keeps an eye out for duplication of files and, in some cases, data within files.
"As a financial institution, we store a lot of data, so we want to make sure we're not adding to the burden by saving multiple copies," he says. Using deduplication consistently has helped the company reclaim storage at a fast enough rate that it has avoided unnecessary buildouts of storage arrays.
Push your developers to use effective coding. While this advice might seem unrelated to the life of a data center manager, Kutticherry insists that inefficient coding can have a tremendous impact on data center resources. Applications that are poorly coded force servers to work harder, consume far more processing power and add to the overall number of needed servers. "Ensure your developers are using the tightest code they can so that applications are most effective," he says.
Data center managers should also require developers to use common databases and not the custom variety. "Again, it makes for a more optimized computing environment and reduces the strain on hardware and software," he adds.
Rearrange the furniture. If floor space is your nemesis, consider moving IT equipment around. "What typically happens in most data centers is that once built and commissioned to a certain design specification, new equipment is added over the ensuing years with consideration to cabling and cooling requirements rather than an optimal floor layout," Gartner's Kumar says.
He urges IT teams to review layouts every three to five years and use available tools such as computational fluid dynamics (CFD) analysis, which models proper airflow, or those available from equipment vendors to redraw floor plans. "While a CFD can be expensive at around $30,000, gaining a few more years from your data center makes it worthwhile," he argues.
He also points to pace-layering, a design technique used to organize data centers in an optimal manner where different pieces evolve at different speeds, or phases. So, in other words, the Web servers need to be managed differently from, say, tier-1 storage.
Analyze your energy efficiency. A CFD, in addition to helping to map floor space, is a useful tool for energy efficiency. Too often, companies overload certain areas of the data center with equipment, creating hotspots that max out power and cooling, Kumar says. By analyzing the data center's temperature, you can potentially delay the expense of larger air conditioners and increased power supplies. A simple repositioning of racks or equipment could buy you years with your data center, he says.
Kossuth engineers her racks so that there is plenty of airflow in the back of racks and equipment is properly cooled. "We have heat and humidity sensors all over the room and receive alerts if the temperature exits a certain band. This has helped us maintain optimal power and cooling levels over the years," she says.