作者: Florin Coras , Jordi Domingo-Pascual , Albert Cabellos-Aparicio
DOI: 10.1016/J.COMNET.2015.08.009
关键词: Locality of reference 、 Computer science 、 Cache 、 Computer network 、 Scalability 、 Parallel computing 、 Lisp
摘要: The Locator/ID Separation Protocol (LISP) limits the growth of Default-Free Zone routing tables by creating a highly aggregatable and quasi-static Internet core. However, LISP pushes forwarding state to edge routers whose timely operation relies on caching location identity bindings. In this paper we develop an analytical model study asymptotic scalability cache. Under assumptions that (i) long-term popularity can be modeled as Generalized Zipf distribution, independent site (ii) temporal locality is predominantly determined popularity, find cache miss rate scales O(1) with respect amount prefixes (Internet growth) users (LISP growth). We validate discuss accuracy our using several one-day-long packet traces.