Network-aware service placement in a distributed cloud environment

摘要: We consider a system of compute and storage resources geographically distributed over large number locations connected via wide-area network. By distributing the resources, latency to users can be decreased, bandwidth costs reduced availablility increased. The challenge is distribute services with varying characteristics among data centers optimally. Some are very sensitive, others need vast amounts storage, yet computationally complex but do not require hard deadlines on execution. propose efficient algorithms for placement get maximum benefit from cloud systems. input status network, which matched application requirements.This demonstration shows how network-aware combine all three resource types - computation, network connectivity in environments. Our dynamic service algorithm monitors center real-time. prototype uses information gathered place or migrate provide best user experience service.