M. Ahmadi and S. Wong (The Netherlands)
Packet classification, tuple space, hashing, Bloom filter
Packet classification continues to be an important challenge in network processing. It requires matching each packet against a database of rules and forwarding the packet ac cording to the highest priority matching rule. Within the packet classification hash-based algorithms, an algorithm that is gaining interest is the tuple space search algorithm that groups the rules into a set of tuple spaces according to their prefix lengths. An incoming packet can now be matched to the rules in a group by taking into consider ation only those prefixes specified by the tuples. More importantly, matching of an incoming packet can now be performed in parallel over all tuples. Within these tuple spaces, a drawback of utilizing hashing is that certain rules will be mapped to the same location, also called collision. The negative effect of such collision is that it will result in multiple memory accesses and subsequently longer pro cessing time. In this paper, we propose to use a pruned counting Bloom filter to reduce collisions in the tuple space packet classification algorithm. This approach decreases the number of collisions and memory accesses in the rule set hash table in comparison to a traditional hashing sys tem. We propose to utilize the pruned counting Bloom fil ter to decrease the number of collisions. More specifically, we investigate several well-known hashing functions and determine the number of collisions and show that utilizing the pruned counting Bloom filter the number of collisions can be further reduced by at least 4% and by at most 32% for real rule sets.
Important Links:
Go Back
