July 21, 2008
The treasury of truck-drivin’ lyrics has yet to include any reference to hauling a datacenter on the back of a rig. But the way things are going, it won’t be long before some updated Red Sovine sings about carrying crates of gigahertz down Interstate 95.
HP is now offering customers the chance to have their datacenter built inside a 40-foot shipping container, instead of a more traditional stationary structure. Not a novel idea -- Sun rolled out its Black Box in 2006 -- but one with some obvious benefits. For starters, there’s no need to construct a new building or apply an extreme makeover to your current space. Bring in the brick and mortar, and you’re talking at least a year before your new digs is ready. HP says it can deliver a containerized datacenter within six weeks.
HP’s new Performance Optimized Data Center, or HP POD, is essentially 4,000 square feet of IT real estate filled with custom-configured equipment of the customer’s choice and housed inside one of those big steel boxes often seen on the backs of 18-wheelers and in mobster movies.
The HP container can support as many as 3,500 compute nodes, or if you wanted it more as a place to store 12 petabytes of your stuff, 12,000 hard drives. There’s room for 22 standard 19-inch 50u racks. (That’s the 40-foot version; a 20-foot version is also available.) To get the maximum compute density that HP claims, you’d need to fill those racks with HP’s newish ProLiant BL2x220c G5, which combines two Xeon-based blade servers into one blade. The 220c doubles CPU capacity while consuming about 60 percent less power than a comparable blade, HP says. But you don’t have to fill the racks with HP equipment.
“We'll support Dell, IBM, Sun, Cisco, whatever fits in a standard rack,” says Steve Cumings, director of infrastructure for HP’s Scalable Computing and Infrastructure Organization. “You can use all the normal equipment you'd expect in a datacenter. Customers told us, ‘Don't have your container limit the kind of IT we can put in place.’ People don't want to be limited to a certain type of equipment or certain brand.” Cumings says HP lets companies mimic the environment they already have in their datacenter. “That way managers don’t have to train people to work in a POD. IT can manage the POD with the same software, the same tools. The POD will plug right into your usual management software. It’s really an extension of your current datacenter.”
HP assembles, configures and integrates third-party equipment if you like, and tests each POD through its Factory Express service. Inside the container, racks are “anchored top and bottom and shock-absorbed for shipping,” Cumings says. “Inside the POD you have your cold aisle and hot aisle, and full access just like you’d have in your regular datacenter. We can deliver everything in one POD, including all the power modules and UPS battery and transformers, or you can have all your utility modules in a separate, 20-foot container.” HP says the separate-box approach is better for two main reasons: the power gear is more temperature-sensitive and should be in a cooler unit, and people who service power hardware might not have the same security clearance as the people who service the IT hardware.
After trucking, installation and deployment, HP will handle whatever the customer needs, including day-to-day management tasks. “There’s a portfolio of services that goes around all this,” Cumings says. “Our design and data center strategy group has a ton of expertise. They’ll sit down with you and help develop a plan. They’ll do site assessments, arrange for site prep, take care of all the prerequisites, and even manage it for you. We’re not just dropping off a container.”
Although the big metal box eliminates the time and cost consumption of construction, HP does not see PODs replacing traditional data shacks. “The POD is a complement,” Cumings says. “Customers are still going to build out some brick-and-mortar space. The POD is an economic and efficient way to support a really intense IT environment or to get more capacity really quickly.”
“We still hear from customers that power, cooling, and space limitations are still problems in their datacenters. Out of power capacity, out of cooling capacity, out of space,” Cumings says. “The thing that exacerbates that is there's a lead time in building out additional space. It can take up to 18 months to build and fill a typical datacenter, and then there's a lag time in reaching the capacity limit. People see the need, and then it takes time to get the capacity they need. The POD goes a long way toward solving that problem because you’ll have your expansion within six weeks, delivered, tested, and ready to turn on.”
According to the EPA, energy costs for datacenters are doubling every five years, and with approximately 50 percent of a center’s operational costs related to power, cutting that electric bill is a business necessity. “Customers have been telling us in the past year that energy costs are having more impact than the cost of servers and other IT hardware,” Cumings says. “We can design the POD for increased energy efficiency. You’re going to gain some of that just by going with the BL 2x220c [blade server] because it draws less power than competing servers.” (HP says the 2x220c consumes about 60 percent less energy than a comparable machine from Dell.)”
There’s another way the truckable datacenter could cut utility bills, Cumings says: “It can go wherever the customer wants it to go, so there’s the option of deploying the POD in an area where they can get lower energy rates. If you’re located in a place where utilities are really high, you’re not locked in to that location. You can think about setting up in a part of the country where electricity is less expensive.”
The datacenter-in-a-crate would work for a wide range of organizations, and HP says it has seen interest from financial, healthcare, manufacturing, and collocation companies. Many prospects have more than one datacenter already. But they all have one big thing in common: they’re exceeding capacity and need to expand quickly.
HP would not talk POD pricing, but Cumings did say “there’s not a price premium for the POD itself. We expect it will typically have a lower total cost of ownership than a brick-and-mortar equivalent. It’s going to be more energy-efficient, and certainly more space-efficient.” PODs will be available in the United States in October, and elsewhere next March, HP says.
View from a Real Datacenter
We asked a man who designs and manages datacenters for a living what he thinks of HP’s POD. John Engates is chief technical officer at Rackspace, a large IT hosting services provider with eight datacenters around the world. (Rackspace uses a mix of servers, including HP, Dell and its own house blend.)
Rackspace would consider adding a POD “because we’re interested in any solution that would buy us more efficiency and would be more cost-effective in the short or long term,” Engates says. “We are looking for the sweet spot of power efficiency, space efficiency, acquisition cost, and cost of ownership. As we move into the era of cloud computing, solutions like these become more and more appealing. When you add servers a few or a dozen at a time like a traditional enterprise does, it's hard to utilize a system like this. But when you start buying servers hundreds or even thousands at a time, it becomes more likely that these containers would make sense. In the cloud, you could essentially treat the entire container as a black box and likely not even service failed components inside until you crossed some threshold, maybe 10 percent failed components or something like that.”
“The coolest -- no pun intended -- part about these containers is their ability to truly isolate the hot and cold aisles of the datacenter and channel the cool air exactly where it needs to go,” Engates says. “That can be difficult in a traditional datacenter. These containers essentially turn almost any datacenter, or even a warehouse, into a well-designed environment for efficient cooling of server equipment. Anything we can do to cut down on the energy consumed by the equipment, the heat produced, or the amount of energy required to cool the data center is worth pursuing. The containers primarily help better manage the cooling aspects, which is certainly a significant cost.”
HP’s POD is similar to IBM’s Portable Modular Data Center in that both offer a 40-foot container and support third-party hardware. But HP, with its dense hardware, currently has the lead in how much IT can be packed into a pod -- and also how quickly it can do it: HP promises to have customers up and running within six weeks; IBM promises 12 weeks.
May 23, 2013 |
The study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.