Anycast is a powerful paradigm for managing and locating resources in decentralized distributed systems. Ideally, an anycast system must be scalable, location-aware and load-aware. Location-awareness means that the anycast system should be able to locate a resource that is near the client in the network. Load-awareness means that it must be able to disperse load to avoid overloading group members in the case of high demand in a certain region of the network.; Existing anycast systems are either location-aware or load-aware, but not both. We motivate LALA, a generic architecture for doing scalable, location-aware, load-aware anycast that realizes the following anycast functionality: Given a client request, our goal is to select the closest anycast server that has enough resources to satisfy the client's request. We show how LALA can be designed on some of the existing overlay anycast architectures and close with an evaluation that demonstrates its effectiveness.
展开▼
