Efficient multi-category packet classification using TCAM

摘要: Abstract Packet classification is the base of various network functions such as firewall filtering, intrusion detection and quality services, etc. Ternary content addressable memory (TCAM) widely employed in performing efficient packet classification. However, TCAM has some drawbacks, including limited capacity, high energy consumption, incapability to store arbitrary ranges. Moreover, only suitable for single-match natively, which associated with one rule-set reports rule, it first matching entry. except classification, another type multi-category multiple rule-sets rule each rule-set, also required scenarios, consolidation functions. The naive scheme search a by one. Its performance decreases linearly number increases. To efficiently perform using TCAM, novel named REM proposed this paper. based on idea reducing accesses per merging rule-entry sets converted from rule-sets. experiments show that compared scheme, can achieve 3x 5x improvement throughput, reduce consumption 50% 75%.