An Adaptable Storage Slicing Algorithm for Content Delivery Networks

Several works study the performance of Content Delivery Networks (CDNs) under various network infrastructure and demand conditions. Some go even further while considering demand elasticity by leveraging on Cloud elasticity where each Content Service Provider (CSP) is served only the amount of storage space and network throughput that it needs and pays accordingly. Many of today's CDN implementations are based on these proposals. However, the allocation of virtual servers in cloud computing is not yet very fine-grained and suffers from limitations and time constraints for reallocation. This work proposes an efficient cache slicing mechanism that frees the CDN provider from dedicating a different virtual surrogate for each CSP in each location. This is achieved by dealing internally with the allocation space for each CSP in a shared surrogate, while still providing services in terms of network storage allowing a CSP to select and pay the amount of content that can be stored. We show that the proposed approach deals better with peak surrogate usage, and reduces the total network traffic by around 15% and cross-traffic by as much as 35% under some scenarios.