Search Results

1. M. Ilvesmäki, On the Behavior and Performance of the Packet Count Flow Classifier, Licentiate thesis, Helsinki University of Technology, 2001 (bib)

   Abstract: Flow classication is used in the Internet to nd and detect flows of packets that can be handled separately from the rest of the trac. The packet flows may receive di erent service levels or they may be treated di erently in the network. This work studies a flow classi cation method where the flows are detected by counting packets on flow candidates. This counting is continued until the packet count threshold is reached and an active flow is established. This work studies the packet count classi er using a set of trac measurements made in di erent networks. Results show that the number of packets outside of any active flows is relatively small thus reducing the workload of conventional packet forwarding. However, the classi ed flows are from a large number of di erent applications and it is doubtful that packet count flow classi cation may be used to support the introduction of quality of service in the Internet. Furthermore, the candidate table, an essential part of the packet count classi er implementation, forms a signi cant performance bottleneck because of the size and frequent changes in it.