Evaluation of Header Field Entropy for Hash-Based Packet Selection
- Cite this paper as:
- Henke C., Schmoll C., Zseby T. (2008) Evaluation of Header Field Entropy for Hash-Based Packet Selection. In: Claypool M., Uhlig S. (eds) Passive and Active Network Measurement. PAM 2008. Lecture Notes in Computer Science, vol 4979. Springer, Berlin, Heidelberg
Network Measurements play an essential role in operating and developing today’s Internet. High data rates and complex measurement demands can origin an immense resource consumption for measurement tasks. Data selection techniques, like sampling and filtering, provide efficient solutions for reducing resource consumption while still maintaining sufficient information about the metrics of interest. Hash-based packet selection allows a synchronized selection of packets at multiple observation points. With this, the tracking of the path of a packet and the calculation of multipoint QoS metrics like one-way delay becomes possible. Nevertheless, hash-based selection is deterministic based on parts of the packet content and hence it is suspect to bias. The packet content used for hashing is a source for bias if the selected content is not variable enough. This paper empirically analyzes which header bytes are most variable and recommendable as input for hash-based selection if one targets the emulation of random selection.
Unable to display preview. Download preview PDF.