A Space-Efficient Fair Packet Sampling Algorithm

  • Authors:

  • Jin Zhang;Xiaona Niu;Jiangxing Wu

  • Affiliations:

  • National Digital Switching System Engineering and Technology Research Center (NDSC), Zhenzhou, China 450002;National Digital Switching System Engineering and Technology Research Center (NDSC), Zhenzhou, China 450002;National Digital Switching System Engineering and Technology Research Center (NDSC), Zhenzhou, China 450002

  • Venue:
  • APNOMS '08 Proceedings of the 11th Asia-Pacific Symposium on Network Operations and Management: Challenges for Next Generation Network Operations and Service Management
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Due to the high-skewed nature of network flow size distributions, uniform packet sampling concentrates too much on a few large flows and ignores the majority of small ones. To overcome this drawback, recently proposed Sketch Guided Sampling (SGS) selects each packet at a probability that is decreasing with its current flow size, which results in better flow wide fairness. However, the pitfall of SGS is that it needs a large, high-speed memory to accommodate flow size sketch, making it impractical to be implemented and inflexible to be deployed. We refined the flow size sketch using a multi-resolution d-left hashing schema, which is both space-efficient and accurate. A new fair packet sampling algorithm which is named Space-Efficient Fair Sampling (SEFS) is proposed based on this novel flow size sketch. We compared the performance of SEFS with that of SGS in the context of flow traffic measurement and large flow identification using real-world traffic traces. The experimental results show that SEFS outperforms SGS in both application contexts while a reduction of 65 percent in space complexity can be achieved.