On the resilience of SACK and newReno TCP

The de facto requirement in traditional telephone networks is to restore failures in 50 milliseconds or less. The same standard has been assumed in data networks. In this study we consider the reaction of TCP to a failure in a continental-scale network. Our goal is to determine whether there are particular values for outage duration at which file transfer times increase markedly. Such values would indicate significant objectives for the restoration of networks carrying TCP traffic. For SACK and NewReno TCP, we find that a restoration objective of 600 ms to 1 s is appropriate. In addition, we also find that receive buffers can be sized at 2 rτ to maximize link utilization and resilience.