Real-time computing. Real-time news.
May 05, 2008
The Do-it-Yourself Datacenter
1 | 2 | 3 All »
The idea of financing your own private datacenter off your credit card isn’t so crazy anymore. Renting CPUs is nothing new: At least two gigantic companies with very famous Web sites will let you run your applications on their metropolis-sized server farms, with fees within reach of many businesses.
But the model they offer doesn’t work for everyone.
What if you want a datacenter built specifically to maximize your application, using the software and hardware components you want, and costing you only when you use it? Can you put hat tailor-made, on-demand datacenter on your credit card?
Si, usted puede. (Yes, you can.)
Several providers are taking advantage of technology developed by 3Tera to offer customers whatever level of grid computing power they need, on a pay-as-they-go basis, but allowing a level of flexibility you don’t get with the more traditional or gigantic hosts. 3Tera set out in 2004 to enable companies to run scalable Web applications on grids of commodity servers, on a utility basis. In 2006, 3tera went live with AppLogic, its grid operating system designed specifically for scalable Web applications.
“It’s not a grid in the traditional terms,” says Bert Armijo, senior vice president of sales, marketing and product management. “It’s a grid in terms of organization of resources, the ability to rack and stack at will and spread apps across hardware, and it separates the app from the hardware, so it’s an excellent tool for utility computing. But it’s also a meta OS, it runs other OSes within it.”
AppLogic mimics traditional hardware facilities, so you can run your existing apps on top of it, Armijo says. One of the biggest user benefits of the 3Tera architecture is that businesses can use the operating systems, middleware, applications, open source tools, security methods, and vendors they choose, and not what the host prefers, he says.
In 3Tera’s system, you’re running virtual appliances. “Each one has everything it needs to run on the grid, like OS code, application code, database schema, file storage, load balancer, whatever makes the app what it is, plus all the configuration information,” Armijo says. “This is why apps can scale from a tiny slice of a server to hundreds of servers on demand, be replicated on demand, or deployed in different locations without the customer having to make any modifications.”
Because you can send these app packages anywhere with one command, it makes it easy and convenient to move an application between networks or locations -- a pretty handy backup and redundancy scheme. Depending on your host provider, you could have copies running on datacenters in other parts of the country.
Armijo demonstrated over the Web the visual tools used to define an application in AppLogic, dragging and dropping elements such as Web servers and firewalls from a catalog. “Our infrastructure editor uses a visual metaphor, so configuration is simple, and you don’t have to do things like login and edit tables or worry about syntax.” A visual interface also is used to set the amount of resources each process gets, and there’s a dashboard for monitoring the grid and managing applications.
Page: 1 of 31 | 2 | 3 All »
Article Tools
Share Options
(Digg, Technorati, more)
