Tcp Stretch Acknowledgements And Timestamps: Findings And Implications For Passive Rtt Measurement

This paper examines several TCP characteristics and their effect on existing passive RTT measurement techniques. In particular, using packet traces from three geographically distributed vantage points, we find relatively low use of TCP timestamps and significant presence of stretch acknowledgements. While the former simply affects the applicability of some measurement techniques, the latter may in principle affect the accuracy of RTT estimation. Using these insights, we quantify implications of common methodologies for passive RTT measurement. In particular, we show that, unlike delayed TCP acknowledgement, stretch acknowledgments do not distort RTT estimations.