In this paper we study the design issues for improving TCP performance
over the ATM UBR service. ATM-UBR switches respond to congestion by d
ropping cells when their buffers become full. TCP connections running
over UBR can experience low throughput and high unfairness. Intelligen
t switch drop policies and end-system policies can improve the perform
ance of TCP over UBR with limited buffers. We describe the various des
ign options available to the network as well as to the end systems to
improve TCP performance over UBR. We study the effects of early packet
discard, and present a per-VC accounting-based buffer management poli
cy. We analyze the performance of the buffer management policies with
various TCP end system congestion control policies, including slow sta
rt and congestion avoidance, fast retransmit and recovery and selectiv
e acknowledgments. We present simulation results for various small and
large latency configurations with varying buffer sizes and number of
sources. (C) 1998 Published by Elsevier Science B.V.