面向命名数据网的高性能内核级网络缓存方法

Named data networking（NDN）is a new information-centric network architecture. In-network caching is one of core functions in NDN. Current cache modules are mainly deployed in user-level, which brings issues of network operation efficiency, compatibility among devices and limitation of deployment location. Comparing to user-level cache module, kernel-level cache module can be directly and widely deployed on general net devices, so it can boost the large-scale deployment of in-network caching and the practical use of NDN solutions. However, due to the frequent per-packet caching operations in NDN, introducing cache into kernel may cause performance issues. To solve these performance issues, this paper designs and implements a kernel-level cache method. The cache method uses a hash table for exact cache lookup and utilizes the naming conventions of NDN to construct a trie for prefix cache lookup. Furthermore, this paper presents an approach of using fine-grained per-slot locks for lookup table and atomic operations for replacement queues to parallelize cache operations. The multi-thread cache module is implemented in the Linux kernel. The experimental results show that the proposed cache scheme reduces the lookup latency by half comparing to current solutions, and boosts the throughput up to 6.785 Mpacket/s via multithreading.