Promoting the use of end-to-end congestion control in the Internet
IEEE/ACM Transactions on Networking (TON)
TCP revisited: a fresh look at TCP in the wild
Proceedings of the 9th ACM SIGCOMM conference on Internet measurement conference
Comparison of end-to-end and network-supported fast startup congestion control schemes
Computer Networks: The International Journal of Computer and Telecommunications Networking
Improving HTTP performance using "stateless" TCP
Proceedings of the 21st international workshop on Network and operating systems support for digital audio and video
Proceedings of the 2nd ACM SIGCOMM workshop on Home networks
Identifying performance bottlenecks in CDNs through TCP-level monitoring
Proceedings of the first ACM SIGCOMM workshop on Measurements up the stack
Overclocking the Yahoo!: CDN for faster web page loads
Proceedings of the 2011 ACM SIGCOMM conference on Internet measurement conference
ASAP: a low-latency transport layer
Proceedings of the Seventh COnference on emerging Networking EXperiments and Technologies
Proceedings of the Seventh COnference on emerging Networking EXperiments and Technologies
Pangolin: speeding up concurrent messaging for cloud-based social gaming
Proceedings of the Seventh COnference on emerging Networking EXperiments and Technologies
A practical solution to the client-LDNS mismatch problem
ACM SIGCOMM Computer Communication Review
An IP-ERN architecture to enable hybrid E2E/ERN protocol and application to satellite networking
Computer Networks: The International Journal of Computer and Telecommunications Networking
Preventing TCP incast throughput collapse at the initiation, continuation, and termination
Proceedings of the 2012 IEEE 20th International Workshop on Quality of Service
WWIC'12 Proceedings of the 10th international conference on Wired/Wireless Internet Communication
Trickle: rate limiting YouTube video streaming
USENIX ATC'12 Proceedings of the 2012 USENIX conference on Annual Technical Conference
Periodic early detection for improved TCP performance and energy efficiency
Computer Networks: The International Journal of Computer and Telecommunications Networking
Network performance of smart mobile handhelds in a university campus WiFi network
Proceedings of the 2012 ACM conference on Internet measurement conference
Inside dropbox: understanding personal cloud storage services
Proceedings of the 2012 ACM conference on Internet measurement conference
Computer Networks: The International Journal of Computer and Telecommunications Networking
Reproducible network experiments using container-based emulation
Proceedings of the 8th international conference on Emerging networking experiments and technologies
Deadline-aware data plane for internet video
Proceedings of the 2012 ACM conference on CoNEXT student workshop
Effect of competing TCP traffic on interactive real-time communication
PAM'13 Proceedings of the 14th international conference on Passive and Active Measurement
Reducing web latency: the virtue of gentle aggression
Proceedings of the ACM SIGCOMM 2013 conference on SIGCOMM
TCP ex machina: computer-generated congestion control
Proceedings of the ACM SIGCOMM 2013 conference on SIGCOMM
Proceedings of the 2013 conference on Internet measurement conference
packetdrill: scriptable network stack testing, from sockets to packets
USENIX ATC'13 Proceedings of the 2013 USENIX conference on Annual Technical Conference
How to improve your network performance by asking your provider for worse service
Proceedings of the Twelfth ACM Workshop on Hot Topics in Networks
Recursively cautious congestion control
NSDI'14 Proceedings of the 11th USENIX Conference on Networked Systems Design and Implementation
Hi-index | 0.00 |
TCP flows start with an initial congestion window of at most four segments or approximately 4KB of data. Because most Web transactions are short-lived, the initial congestion window is a critical TCP parameter in determining how quickly flows can finish. While the global network access speeds increased dramatically on average in the past decade, the standard value of TCP's initial congestion window has remained unchanged. In this paper, we propose to increase TCP's initial congestion window to at least ten segments (about 15KB). Through large-scale Internet experiments, we quantify the latency benefits and costs of using a larger window, as functions of network bandwidth, round-trip time (RTT), bandwidth-delay product (BDP), and nature of applications. We show that the average latency of HTTP responses improved by approximately 10% with the largest benefits being demonstrated in high RTT and BDP networks. The latency of low bandwidth networks also improved by a significant amount in our experiments. The average retransmission rate increased by a modest 0.5%, with most of the increase coming from applications that effectively circumvent TCP's slow start algorithm by using multiple concurrent connections. Based on the results from our experiments, we believe the initial congestion window should be at least ten segments and the same be investigated for standardization by the IETF.