We examine the use of the ATM VBR service class to transport TCP traffic. For this service class, a sustainable cell rate (SCR) and a peak cell rate (PCR) are negotiated at connection set up and enforced using leaky bucket policing. Ideally, a policed TCP connection would realize an average throughput close to the SCR. Unfortunately, our results show that interactions between TCP congestion control algorithms and leaky bucket policing can cause the average TCP throughput to be much lower than the SCR. We demonstrate the cause of this degradation and suggest possible remedies to improve performance.
No takes yet. Share an insight, caveat, or question.
A. B. Mishra (2002) studied this question.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: