Implementing and testing a virus throttle
SSYM'03 Proceedings of the 12th conference on USENIX Security Symposium - Volume 12
Understanding data center traffic characteristics
Proceedings of the 1st ACM workshop on Research on enterprise networking
Data Center Switch Architecture in the Age of Merchant Silicon
HOTI '09 Proceedings of the 2009 17th IEEE Symposium on High Performance Interconnects
Hedera: dynamic flow scheduling for data center networks
NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation
Network traffic characteristics of data centers in the wild
IMC '10 Proceedings of the 10th ACM SIGCOMM conference on Internet measurement
DevoFlow: scaling flow management for high-performance networks
Proceedings of the ACM SIGCOMM 2011 conference
Frenetic: a network programming language
Proceedings of the 16th ACM SIGPLAN international conference on Functional programming
Software defined traffic measurement with OpenSketch
nsdi'13 Proceedings of the 10th USENIX conference on Networked Systems Design and Implementation
Towards secure and dependable software-defined networks
Proceedings of the second ACM SIGCOMM workshop on Hot topics in software defined networking
AVANT-GUARD: scalable and vigilant switch flow management in software-defined networks
Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security
Hi-index | 0.00 |
Software-Defined Networking (SDN) gains much of its value through the use of central controllers with global views of dynamic network state. To support a global view, SDN protocols, such as OpenFlow, expose several counters for each flow-table rule. These counters must be maintained by the data plane, which is typically implemented in hardware as an ASIC. ASIC-based counters are inflexible, and cannot easily be modified to compute novel metrics. These counters do not need to be on the ASIC. If the ASIC data plane has a fast connection to a general-purpose CPU with cost-effective memory, we can replace traditional counters with a stream of rule-match records, transmit this stream to the CPU, and then process the stream in the CPU. These software-defined counters allow far more flexible processing of counter-related information, and can reduce the ASIC area and complexity needed to support counters.