Predicting TCP throughput from non-invasive network sampling
Proceedings - IEEE INFOCOM - Tập 1 - Trang 180-189 vol.1
Tóm tắt
In this paper, we wish to derive analytic models that predict the performance of TCP flows between specified endpoints using routinely observed network characteristics such as loss and delay. The ultimate goal of our approach is to convert network observables into representative user and application relevant performance metrics. The main contributions of this paper are in studying which network performance data sources are most reflective of session characteristics, and then in thoroughly investigating a new TCP model based on Padhye et al. (2000) that uses non-invasive network samples to predict the throughput of representative TCP flows between given end-points.
Từ khóa
#Throughput #Sampling methods #Performance loss #Performance analysis #Monitoring #Application software #Predictive models #Scalability #Delay estimation #Computer networksTài liệu tham khảo
0, The network simulator - NS2
mathis, 1996, TCP selective acknowledgement options
10.1145/505672.505674
10.1109/90.251892
mccloghrie, 1991, Management information base for network management of TCP/IP-based internets: MIB-II
jacobson, 0, Berkeley TCP evolution from 4.3-Tahoe to 4.3-Reno, Proceedings of the Eighteenth Internet Engineering Task Force Vancouver B C 1990, 365
goyal, 2001, Predicting TCP throughput from non-invasive data
paxson, 2000, Computing TCP's retransmission timer, 10.17487/rfc2988
wright, 1996, TCP/IP Illustrated Volume 2 The Implementation
10.1109/90.611099
10.1145/251007.251012
allman, 1999, TCP congestion control, 10.17487/rfc2581
10.1109/90.842137
10.1109/90.909022
10.1145/301453.301550
altman, 0, A stochastic model of TCP/IP with stationary random losses, Proceedings of ACM SIGCOMM 2000 2000
10.1109/90.720921
10.1145/263932.264023
10.1109/INFCOM.2000.832574
10.1109/INFCOM.2000.832572