In this work we present a novel concept of augmenting a search tree in a packet-processing system with an additional data structure, a Network of Shortcuts, in order to adapt the search to current input traffic patterns and significantly speed-up the frequently traversed search-tree paths. The method utilizes node statistics gathered from the tree and periodically adjusts the shortcut positions. After an overview of tree-search methods used in networking tasks such as lookup or classification, and a discussion of the impact of typical traffic characteristics, we argue that adding a small number of "direct links", or shortcuts, to the few frequently traversed paths can significantly improve performance, at a very low cost. We present a shortcut-placement heuristic, compare our method to a standard caching mechanism and show how the use of different levels of aggregation in a search tree enables to achieve similar results with much fewer entries. © IFIP International Federation for Information Processing 2005.
CITATION STYLE
Bergamini, A., & Kencl, L. (2005). Network of shortcuts: An adaptive data structure for tree-based search methods. In Lecture Notes in Computer Science (Vol. 3462, pp. 523–535). Springer Verlag. https://doi.org/10.1007/11422778_42
Mendeley helps you to discover research relevant for your work.