Cooperative client caching strategies for social and web applications

We evaluate the efficiency and cost of different placement strategies for a distributed cache implemented on the clients of an online social network or web service. In our system model, the service maintains a directory for content that tracks the location of objects. The service informs requesting clients of these locations and the clients will cache, serve, and push content according to directives provided by the service. We show that we can improve the individual cache hit ratio by leveraging relationships between clients (e.g., social links). The network load imposed on clients is practical.