Issue No. 08 - August (2006 vol. 55)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TC.2006.123
Kai Zheng , IEEE
Hao Che , IEEE
Bin Liu , IEEE
Packet classification has been a critical data path function for many emerging networking applications. An interesting approach is the use of Ternary Content Addressable Memory (TCAM) to achieve deterministic, high-speed packet classification performance. However, apart from high cost and power consumption, due to slow growing clock rate for memory technology, in general, the traditional single TCAM-based solution has difficulty to keep up with fast growing line rates. Moreover, the TCAM storage efficiency is largely affected by the need to support rules with ranges or range matching. In this paper, a distributed TCAM scheme that exploits chip-level-parallelism is proposed to greatly improve the throughput performance. This scheme seamlessly integrates with a range encoding scheme which not only solves the range matching problem, but also ensures a balanced high throughput performance. A thorough theoretical worst-case analysis of throughput, processing delay, and power consumption, as well as the experimental results show that the proposed solution can achieve scalable throughput performance matching up to OC768 line rate or higher. The added TCAM storage overhead is found to be reasonably small for the five real-world classifiers studied.
Packet classification, range matching, TCAM.
B. Liu, H. Che, K. Zheng, Z. Wang and X. Zhang, "DPPC-RE: TCAM-Based Distributed Parallel Packet Classification with Range Encoding," in IEEE Transactions on Computers, vol. 55, no. , pp. 947-961, 2006.