Automatic creation and reconfiguration of network-aware service access paths

This paper describes an adaptive network infrastructure, Composable Adaptive Network Services (CANS), for bridging the bandwidth and resource gap between network services and mobile clients. CANS enables construction of service access paths augmented with 'impedance matching' components that handle operations such as caching, protocol conversion, and content transcoding. The CANS infrastructure focuses on the automatic creation and efficient dynamic reconfiguration of such network-aware access paths, relying upon three key mechanisms: (a) a high-level integrated type-based specification of components and network resources; (b) an automatic path creation strategy; and (c) system support for low-overhead path reconfiguration. We evaluate the CANS infrastructure over a range of network and end-device characteristics using two application scenario: web access and image streaming. Our results validate the effectiveness of the CANS approach for enabling network-aware service access to mobile clients, verifying that (1) communication paths automatically generated by CANS bring considerable performance advantages to applications; (2) desirable adaptation can be achieved using our flexible path creation mechanisms, which consider both underlying network conditions and different performance preferences of applications; and (3) despite their flexibility, both run-time overheads of CANS communication paths and reconfiguration time are negligible for most applications, providing applications with agile adaptation to dynamic changes in networks.

[1]  M. Frans Kaashoek,et al.  Mobile Computing with the Rover Toolkit , 1997, IEEE Trans. Computers.

[2]  B. R. Badrinath,et al.  Transformer Tunnels: A Framework for Providing Route Specific Adaptations , 1998, USENIX Annual Technical Conference.

[3]  Ben Y. Zhao,et al.  The Ninja architecture for robust Internet-scale systems and services , 2001, Comput. Networks.

[4]  Armando Fox,et al.  Extensible Cluster-Based Scaleable Network Services , 1997, SOSP 1997.

[5]  Hong Va Leong,et al.  Mobile Data Access , 2001, Lecture Notes in Computer Science.

[6]  Klara Nahrstedt,et al.  Finding service paths in a media service proxy network , 2001, IS&T/SPIE Electronic Imaging.

[7]  Weisong Shi,et al.  CANS: Composable, Adaptive Network Services Infrastructure , 2001, USITS.

[8]  Joan Feigenbaum,et al.  KeyNote: Trust Management for Public-Key Infrastructures (Position Paper) , 1998, Security Protocols Workshop.

[9]  John R. Smith,et al.  Adapting Multimedia Internet Content for Universal Access , 1999, IEEE Trans. Multim..

[10]  Hermann de Meer,et al.  A survey of programmable networks , 1999, CCRV.

[11]  Klara Nahrstedt,et al.  QoS-assured service composition in managed service overlay networks , 2003, 23rd International Conference on Distributed Computing Systems, 2003. Proceedings..

[12]  Brian D. Noble,et al.  Mobile network estimation , 2001, MobiCom '01.

[13]  Robert Cole,et al.  Computer Communications , 1982, Springer New York.

[14]  S. Gribble,et al.  Adapting to Network and Client Variation Using Active Proxies : Lessons and PerspectivesArmando , 1998 .

[15]  Mary Baker,et al.  Nettimer: A Tool for Measuring Bottleneck Link Bandwidth , 2001, USITS.

[16]  Dean Sutherland,et al.  A resource query interface for network-aware applications , 1998, Proceedings. The Seventh International Symposium on High Performance Distributed Computing (Cat. No.98TB100244).

[17]  John V. Guttag,et al.  ANTS: a toolkit for building and dynamically deploying network protocols , 1998, 1998 IEEE Open Architectures and Network Programming.

[18]  Armando Fox,et al.  Using Dynamic Mediation to Integrate COTS Entities in a Ubiquitous Computing Environment , 2000, HUC.

[19]  David L. Tennenhouse,et al.  Towards an active network architecture , 2007, Comput. Commun. Rev..

[20]  Mark D. Yarvis,et al.  Automated Planning for Open Architectures , 2000 .

[21]  David E. Culler,et al.  The multispace: an evolutionary platform for infrastructural services , 1999 .

[22]  Mark D. Yarvis,et al.  Conductor: Distributed Adaptation for Complex Networks , 1999 .

[23]  Xiaodong Fu,et al.  Performance implications of different adaptation mechanisms for network content delivery , 2004, IEEE International Conference on Performance, Computing, and Communications, 2004.

[24]  Steven McCanne,et al.  An active service framework and its application to real-time multimedia transcoding , 1998, SIGCOMM '98.

[25]  David Wetherall,et al.  Towards an active network architecture , 1996, CCRV.

[26]  Vijay Karamcheti,et al.  dRBAC: distributed role-based access control for dynamic coalition environments , 2002, Proceedings 22nd International Conference on Distributed Computing Systems.

[27]  Joan Feigenbaum,et al.  Decentralized trust management , 1996, Proceedings 1996 IEEE Symposium on Security and Privacy.

[28]  Akihiro Nakao,et al.  Constructing end-to-end paths for playing media objects , 2002, Comput. Networks.

[29]  Fangzhe Chang,et al.  User-level resource-constrained sandboxing , 2000 .

[30]  Martín Abadi,et al.  Authentication in the Taos operating system , 1993, SOSP '93.

[31]  Eric A. Brewer,et al.  Adapting to network and client variation using infrastructural proxies: lessons and perspectives , 1998, IEEE Wirel. Commun..

[32]  Jonathan M. Smith,et al.  Operating System Support for Protocol Boosters , 1996 .