Fair sampling across network flow measurements

Sampling is crucial for controlling resource consumption by internet traffic flow measurements. Routers use Packet Sampled NetFlow [9], and completed flow records are sampled in the measurement infrastructure [13]. Recent research, motivated by the need of service providers to accurately measure both small and large traffic subpopulations, has focused on distributing a packet sampling budget amongst subpopulations [26, 33, 40]. But long timescales of hardware development and lower bandwidth costs motivate post-measurement analysis of complete flow records at collectors instead. Sampling in collector databases then manages data volumes, yielding general purpose summaries that are rapidly queried to trigger drill-down analysis on a time limited window of full data. These are sufficiently small to be archived. This paper addresses the problem of distributing a sampling budget over subpopulations of flow records. Estimation accuracy goals are met by fairly sharing the budget. We estab...

• Type: Journal
• Year: 2012
• Where: SIGMETRICS
• Authors: Nick G. Duffield
• Keywords: Computer Communication Networks, Estimation Accuracy, Hardware, Measurement Infrastructure, SIGMETRICS 2012