In this paper we study the design issues in improving TCP performance over the ATM UBR service. ATM-UBR switches respond to congestion by dropping cells when their buffers become full. TCP connections running over UBR can experience low throughput and high unfairness. Intelligent switch drop policies and end-system policies can improve the performance of TCP over UBR with limited buffers. We describe the various design 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 two per-VC accounting based buffer management policies. We also study the effects of various TCP end system congestion control policies including slow start and congestion avoidance, fast retransmit and recovery and selective acknowledgments. We present simulation results for various small and large latency configurations with varying buffer sizes and number of sources.
Complete Paper in Adobe Acrobat (1,292,819 Bytes)