Transport-Level Protocol Coordination in Cluster-to-Cluster Applications

Future Internet applications will increasingly use multiple communications and computing devices in a distributed fashion. In this paper, we identify an emerging and important application class comprised of a set of processes on a cluster of devices communicating to a remote set of processes on another cluster of devices across a common intermediary Internet path. We call applications of this type cluster-to-cluster (C-to-C) applications. The networking requirements of C-to-C applications present unique challenges that current transport-level protocols fail to address. In particular, these applications require aggregate measurement of network conditions across all associated flows and coordinated transport-level protocol behavior. A Coordination Protocol (CP) is proposed which allows a C-to-C application to coordinate flow behavior in the face of changing network conditions. CP provides cluster endpoints with a consistent view of network conditions, as well as cluster membership and bandwidth usage information. An application may use CP to define and implement a coordination scheme supporting particular flow priorities and other objectives.

[1]  Shie-Yuan Wang,et al.  TCP trunking: design, implementation and performance , 1999, Proceedings. Seventh International Conference on Network Protocols.

[2]  Luke M. Leslie,et al.  The Tempest-a practical framework for network programmability , 1998, IEEE Netw..

[3]  R. D. Rockwell,et al.  Smart Packets for active networks , 1999, 1999 IEEE Second Conference on Open Architectures and Network Programming. Proceedings. OPENARCH '99 (Cat. No.99EX252).

[4]  Greg Welch,et al.  The office of the future: a unified approach to image-based modeling and spatially immersive displays , 1998, SIGGRAPH.

[5]  Marianne Shaw,et al.  Active bridging , 1997, SIGCOMM '97.

[6]  Tzi-cker Chiueh,et al.  Aggregate TCP congestion control using multiple network probing , 2000, Proceedings 20th IEEE International Conference on Distributed Computing Systems.

[7]  David L. Tennenhouse,et al.  Toward an active network architecture , 1996, Electronic Imaging.

[8]  Srinivasan Seshan,et al.  An integrated congestion management architecture for Internet hosts , 1999, SIGCOMM '99.

[9]  Mark Weiser,et al.  Some computer science issues in ubiquitous computing , 1993, CACM.

[10]  Mark Weiser,et al.  Some Computer Science Problems in Ubiquitous Computing , 1993 .

[11]  Bernhard Plattner,et al.  Router plugins: a software architecture for next generation routers , 1998, SIGCOMM '98.

[12]  David Wetherall,et al.  Active network vision and reality: lessions from a capsule-based system , 1999, SOSP.

[13]  Carl A. Gunter,et al.  PLANet: an active internetwork , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[14]  Stephen J. Garland,et al.  PAN: a high-performance active network node supporting multiple mobile code systems , 1999, 1999 IEEE Second Conference on Open Architectures and Network Programming. Proceedings. OPENARCH '99 (Cat. No.99EX252).

[15]  Lawrence A. Rowe,et al.  dc: a live Webcast control system , 2000, IS&T/SPIE Electronic Imaging.

[16]  Jonathan Grudin,et al.  Computer-supported cooperative work: history and focus , 1994, Computer.