CCndnS: A strategy for spreading content and decoupling NDN caches

Many proposals for information-centric networking (ICN) share the idea of in-network caching. This idea has four issues: (1) Memory capacity can be wasted through caching redundant copies and unpopular content. (2) Memory latency is high because the caches must be large. (3) Traffic filtering can result in high miss rates in the core and load imbalance. (4) Performance coupling among caches makes modeling their behavior intractable. CCndnS is a caching strategy for Named Data Networking that segments each file and spreads them among the caches, thus addressing the above issues: (1) It reduces redundant copies and cache pollution by unpopular content. (2) It reduces the number of futile checks on caches, thus reducing the delay from memory accesses. (3) It increases hit rates in the core without reducing hit rates at the edge (thus improving overall hit rates) and balances the load among caches. (4) It decouples the caches, so there is a simple analytical performance model for the network of caches. The efficacy of CCndnS and the accuracy of the model are validated with simulations using an Abilene-like topology.