Building an Elastic Cloud out of Small Datacenters

Cloud providers typically operate large-scale datacenters in a few locations.With network service providers already owning a large number of central offices that are geographically distributed across a country, there is a case for deploying a large number of small-scale distributed datacenters in a cost-effective way. Small-scale datacenters, however, may not be able to provide elastic services. In this paper, we investigate distributed smallscale datacenters with load reallocation where jobs that cannot be suitably processed locally will be reallocated to remote datacenters. We formulate an optimization problem for load reallocation in distributed datacenters, provide performance comparisons among different alternatives and offer insights on handling multiple job types. We develop online optimization algorithms that can be operated in a decentralized and measurement-based fashion to dynamically reallocate load in response to sudden load surges. The experimental results demonstrate that elasticity can be practically provided by small-scale datacenters enhanced with effective load reallocation techniques.