A Hybrid TCAM plus SRAM Scheme for Multi-match Packet Classification

Modern network routers provide differentiated services for incoming network packets based on classification, where the packet header is compared against a rule set for matching. Traditional packet classification only reports a single matched rule with the highest priority in case of multiple matched ones. With the emergence of new applications such as network intrusion detection system (NDIS), all matched rules need to be reported. This multi-match problem is more challenging and is getting higher attention in recent years. Because of the stringent time budget on classification, architectural solutions using Ternary Content Addressable Memory (TCAM) attract more attention than software solutions for backbone network routers. However, despite its advantage on search speed, TCAM is much more expensive than SRAM, and is notorious for its extraordinarily high power consumption. These problems limit the application and scalability of TCAM solutions. This paper presents a novel tree-based hybrid TCAM+SRAM solution for the purposes of both TCAM space reduction and power saving. The experiments show that the proposed solution achieves significantly more savings on both memory space and power consumption on packet matching than existing solutions.Computer Science, Theory & MethodsEICPCI-S(ISTP)