Users typically want their flows to complete as quickly as possible. This makes Flow Completion Time (FCT) an im-portant- arguably the most important- performance met-ric for the user. Yet research on congestion control focuses almost entirely on maximizing link throughput, utilization and fairness, which matter more to the operator than the user. In this paper we show that with typical Internet flow sizes, existing (TCP Reno) and newly proposed (XCP) con-gestion control algorithms make flows last much longer than necessary- often by one or two orders of magnitude. In contrast, we show how a new and practical algorithm- RCP (Rate Control Protocol)- enables flows to complete close to the minimum possible
Theory and experiments show that as the per-flow product of band-width and latency increases, TCP be...
The main points of this paper are the following. • I present a simple and elegant proof of how feedb...
This paper describes the engineering of a new congestion control for TCP motivated by theoretical re...
Users typically want their flows to complete as quickly as possible. This makes Flow Completion Time...
Abstract — We believe that a congestion control algorithm should make flows finish quickly- as quick...
Abstract—Congestion control algorithms are usually de-signed to maximize network utilization, while ...
The transmission control protocol (TCP) is the major trans- port layer protocol in the Internet tod...
The transmission control protocol (TCP) is the major trans- port protocol in the Internet. TCP and ...
Network conditions and traffic requirements of the Internet have been dynamically changing. These c...
Why the flow completion time must be faster for congestion control algorithms? How the existing and ...
The transmission control protocol (TCP) which is the dominant congestion control protocol at the tr...
Users want web pages to load quickly. Because modern web pages make connections to many hosts, this ...
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer...
As datacenter speeds scale to 100 Gb/s and beyond, tradi-tional congestion control algorithms like T...
RCP (Rate Control Protocol) is a rate-based congestion control algorithm, which can reduce the flow ...
Theory and experiments show that as the per-flow product of band-width and latency increases, TCP be...
The main points of this paper are the following. • I present a simple and elegant proof of how feedb...
This paper describes the engineering of a new congestion control for TCP motivated by theoretical re...
Users typically want their flows to complete as quickly as possible. This makes Flow Completion Time...
Abstract — We believe that a congestion control algorithm should make flows finish quickly- as quick...
Abstract—Congestion control algorithms are usually de-signed to maximize network utilization, while ...
The transmission control protocol (TCP) is the major trans- port layer protocol in the Internet tod...
The transmission control protocol (TCP) is the major trans- port protocol in the Internet. TCP and ...
Network conditions and traffic requirements of the Internet have been dynamically changing. These c...
Why the flow completion time must be faster for congestion control algorithms? How the existing and ...
The transmission control protocol (TCP) which is the dominant congestion control protocol at the tr...
Users want web pages to load quickly. Because modern web pages make connections to many hosts, this ...
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer...
As datacenter speeds scale to 100 Gb/s and beyond, tradi-tional congestion control algorithms like T...
RCP (Rate Control Protocol) is a rate-based congestion control algorithm, which can reduce the flow ...
Theory and experiments show that as the per-flow product of band-width and latency increases, TCP be...
The main points of this paper are the following. • I present a simple and elegant proof of how feedb...
This paper describes the engineering of a new congestion control for TCP motivated by theoretical re...