Experimentations with TCP selective acknowledgment
- 1 April 1998
- journal article
- Published by Association for Computing Machinery (ACM) in ACM SIGCOMM Computer Communication Review
- Vol. 28 (2) , 54-77
- https://doi.org/10.1145/279345.279350
Abstract
This paper reports our experimentation results with TCP Selective Acknowledgments (TCP-Sack), which became an Internet Proposed Standard protocol recently. To understand the performance impact of TCP-Sack deployment, in this study we examined the following issues:• How much performance improvement TCP-Sack may bring over the current TCP implementation, TCP-Reno. We conducted experiments both on a lab testbed and over the Internet, under various conditions of link delay and losses.• In particular, how well TCP-Sack may perform over long delay paths that include satellite links.• What is the performance impact of TCP connections with Sack options on those connections without Sack when the two types running in parallel, if there is any.Keywords
This publication has 7 references indexed in Scilit:
- The macroscopic behavior of the TCP congestion avoidance algorithmACM SIGCOMM Computer Communication Review, 1997
- TCP Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery AlgorithmsPublished by RFC Editor ,1997
- Improving the start-up behavior of a congestion control scheme for TCPPublished by Association for Computing Machinery (ACM) ,1996
- Forward acknowledgementACM SIGCOMM Computer Communication Review, 1996
- Simulation-based comparisons of Tahoe, Reno and SACK TCPACM SIGCOMM Computer Communication Review, 1996
- TCP VegasPublished by Association for Computing Machinery (ACM) ,1994
- Congestion avoidance and controlPublished by Association for Computing Machinery (ACM) ,1988