Fragmentation considered harmful
SIGCOMM '87 Proceedings of the ACM workshop on Frontiers in computer communications technology
Computer Networks and ISDN Systems
Network performance effects of HTTP/1.1, CSS1, and PNG
SIGCOMM '97 Proceedings of the ACM SIGCOMM '97 conference on Applications, technologies, architectures, and protocols for computer communication
Modeling the performance of HTTP over several transport protocols
IEEE/ACM Transactions on Networking (TON)
Generating representative Web workloads for network and server performance evaluation
SIGMETRICS '98/PERFORMANCE '98 Proceedings of the 1998 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems
Efficient policies for carrying Web traffic over flow-switched networks
IEEE/ACM Transactions on Networking (TON)
A performance evaluation of hyper text transfer protocols
SIGMETRICS '99 Proceedings of the 1999 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
LSAM proxy cache: a multicast distributed virtual cache
Computer Networks and ISDN Systems - Selected papers of the 3rd international caching workshop
Managing TCP connection under persistent HTTP
WWW '99 Proceedings of the eighth international conference on World Wide Web
Proceedings of the 9th international World Wide Web conference on Computer networks : the international journal of computer and telecommunications netowrking
End-to-end arguments in system design
ACM Transactions on Computer Systems (TOCS)
Ethernet: distributed packet switching for local computer networks
Communications of the ACM
Web caching and replication
Handbook of Applied Cryptography
Handbook of Applied Cryptography
IP Telephony with H.323: Architectures for Unified Networks and Integrated Services
IP Telephony with H.323: Architectures for Unified Networks and Integrated Services
Blocking Java Applets at the Firewall
SNDSS '97 Proceedings of the 1997 Symposium on Network and Distributed System Security
An Empirical Model of HTTP Network Traffic
INFOCOM '97 Proceedings of the INFOCOM '97. Sixteenth Annual Joint Conference of the IEEE Computer and Communications Societies. Driving the Information Revolution
Analysis and modeling of world wide web traffic
Analysis and modeling of world wide web traffic
Characterization of a large web site population with implications for content delivery
Proceedings of the 13th international conference on World Wide Web
PRO-COW: Protocol compliance on the web-a longitudinal study
USITS'01 Proceedings of the 3rd conference on USENIX Symposium on Internet Technologies and Systems - Volume 3
Organization-based analysis of web-object sharing and caching
USITS'99 Proceedings of the 2nd conference on USENIX Symposium on Internet Technologies and Systems - Volume 2
TPOT: translucent proxying of TCP
Computer Communications
Realization of Call-Back Authentication (CBA) for secure web to cellular phone SMS communication
Computers & Mathematics with Applications
Hi-index | 0.01 |
Today's HTTP carries Web interactions over client-initiated TCP connections. An important implication of using this transport method is that interception caches in the network violate the end-to-end principle of the Internet, which severely limits deployment options of these caches. Furthermore, while an increasing number of Web interactions are short, and in fact frequently carry only control information and no data, TCP is often inefficient for short interactions We propose a new transfer protocol for the Web, called Dual-Transport HTTP (DHTTP), which splits the traffic between UDP and TCP channels. When choosing the TCP channel, it is the server who opens the connection back to the client. Through server-initiated connections, DHTTP upholds the Internet end-to-end principle in the presence of interception caches, thereby allowing unrestricted caching within backbones. Moreover, the comparative performance study of DHTTP and HTTP using trace-driven simulation as well as testing real HTTP and DHTTP servers showed a significant performance advantage of DHTTP when the bottleneck is at the server and comparable performance when the bottleneck is in the network.