Data centers cost millions of dollars to build and operate, and buying servers is the single largest expense. Yet at any given moment, most of the servers in a typical data center are only using 20 percent of their capacity, because the workload can vary greatly depending on factors such as how many users log on. Since data centers must always be ready to meet peak demand, having excess capacity is the best way to ensure this today.
As cloud computing grows, so will the cost of keeping such large cushions of capacity. That’s why two Stanford engineers have created a cluster management tool that can triple server efficiency while delivering reliable service at all times, allowing data center operators to serve more customers for each dollar they invest.
Christos Kozyrakis, a professor of electrical engineering and computer science, and Christina Delimitrou, a doctoral student in electrical engineering, will explain their cluster management system, called Quasar, when scientists who design and run data centers meet for a conference that begins March 1.
For the full story, visit Stanford Engineering.