Previous work on network measurements have explored several primitives of increasing complexity for measurement tasks at individual nodes, ranging from counters to hashing to arbitrary code fragments. In an SDN network, these primitives may require significant bandwidth, memory and processing resources, and the resources dedicated to these can affect the accuracy of the eventual measurement. In this paper, we first qualitatively discuss the tradeoff space of resource usage versus accuracy for these different primitives as a function of the spatial and temporal measurement granularity, then quantify these tradeoffs in the context of hierarchical heavy hitter detection.
No takes yet. Share an insight, caveat, or question.
Moshref et al. (2013) studied this question.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: