Packet losses increase latency for Web users. Fast recovery is a key mechanism for TCP to recover from packet losses. In this paper, we explore some of the weaknesses of the standard algorithm described in RFC 3517 and the non-standard algorithms implemented in Linux. We ﬁnd that these algorithms deviate from their intended behavior in the real world due to the combined eﬀect of short ﬂows, application stalls, burst losses, acknowledgment (ACK) loss and reordering, and stretch ACKs. Linux suﬀers from excessive congestion window reductions while RFC 3517 transmits large bursts under high losses, both of which harm the rest of the ﬂow and increase Web latency.
Our primary contribution is a new design to control transmission in fast recovery called proportional rate reduction (PRR). PRR recovers from losses quickly, smoothly and accurately by pacing out retransmissions across received ACKs. In addition to PRR, we evaluate the TCP early retransmit (ER) algorithm which lowers the duplicate acknowledgment threshold for short transfers, and show that delaying early retransmissions for a short interval is eﬀective in avoiding spurious retransmissions in the presence of a small degree of reordering. PRR and ER reduce the TCP latency of connections experiencing losses by 3-10%% depending on the response size. Based on our instrumentation on Google Web and YouTube servers in U.S. and India, we also present key statistics on the nature of TCP retransmissions.