Best Paper Award in IEEE Cluster 2020
Computer Science faculty members Minseok Kwon and M. Mustafa Rafique have received a best paper award in IEEE Cluster 2020 together with Krishna Neupane (GCCIS PhD student), and John Marshall (Cisco Systems and RIT alumnus). IEEE Cluster is a major international conference for sharing technical accomplishments in the field of cluster computing as well as the use of cluster systems for scientific and commercial applications.
IEEE Cluster is a major international conference for sharing technical accomplishments in the field of cluster computing as well as the use of cluster systems for scientific and commercial applications.
Programmability in network switches has become increasingly important as virtualization is introduced into networking and software-defined networking becomes more prevalent. Yet, the performance of programmable network switches on commodity hardware is a major concern, in light of ever-increasing network speed and routing table size. In this work, we present a cuckoo-filter based longest prefix matching mechanism in IP lookup called CuVPP that helps provide high-speed packet processing in a programmable 100% software switch. CuVPP uses packet batch processing and cache locality for both instructions and data by leveraging Vector Packet Processing (VPP). Our evaluation shows that CuVPP can achieve up to 4.5 million lookups per second with real traffic, higher than the other trie- or filter- based lookup approaches, and scales well even when the routing table size grows to 2 million prefixes. This research has been funded by Cisco Systems.