POEMS: Peer-Based Overload Management

The Internet has become increasingly important to many emerging application such as Blog, Wikis, podcasts, and others Web-based communities and social-networking services, i.e. Web 2.0. Behind the scenes, added functionalities depend on the ability of users to work with the data stored on servers, i.e. DBMSs. However, the unpredictability and fluctuations of requests could result in overload, which can substantially degrade the quality of service. It is a challenging task to provide quality of service with inexpensive and scalable infrastructure. In this paper, we look at a new architectural design dimension, POEMS, that is online transformable between a single-node server and peer-based service network architectures. POEMS operates as a conventional DBMS under normal load conditions and transforms to peer-to-peer operation mode for processing under heavy load. In contrast to traditional distributed DBMSs, all nodes contribute their spare capacities for data manipulation. This is achieved without the need to install any DBMS at any of the contributing nodes. Data are partitioned online and operators are distributed to nodes similarly. The effectiveness of query processing is achieved by node cooperation. POEMS allows processes or operators to be dismissed online, so a user can fully utilise his/her resources.

[1]  Bruce M. Maggs,et al.  A Scalability Service for Dynamic Web Applications , 2005, CIDR.

[2]  Michael Stonebraker,et al.  The Case for Shared Nothing , 1985, HPTS.

[3]  David E. Culler,et al.  A case for NOW (networks of workstation) , 1995, PODC '95.

[4]  Bruce M. Maggs,et al.  Simultaneous scalability and security for data-intensive web applications , 2006, SIGMOD Conference.

[5]  Klara Nahrstedt,et al.  Self-Configuring Information Management for Large-Scale Service Overlays , 2007, IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications.

[6]  Hesham El-Rewini,et al.  Dynamic Data Reallocation for Skew Management in Shared-Nothing Parallel Databases , 1997, Distributed and Parallel Databases.

[7]  Renée J. Miller,et al.  Mapping data in peer-to-peer systems: semantics and algorithmic issues , 2003, SIGMOD '03.

[8]  Gerhard Weikum,et al.  Data partitioning and load balancing in parallel disk systems , 1998, The VLDB Journal.

[9]  Miron Livny,et al.  A worldwide flock of Condors: Load sharing among workstation clusters , 1996, Future Gener. Comput. Syst..

[10]  Patrick Valduriez,et al.  Scaling heterogeneous databases and the design of Disco , 1996, Proceedings of 16th International Conference on Distributed Computing Systems.

[11]  Joann J. Ordille,et al.  Data integration: the teenage years , 2006, VLDB.

[12]  Stefano Spaccapietra,et al.  Issues and approaches of database integration , 1998, CACM.

[13]  Dan Suciu,et al.  The Piazza peer data management system , 2004, IEEE Transactions on Knowledge and Data Engineering.

[14]  Beng Chin Ooi,et al.  PeerDB: a P2P-based system for distributed data sharing , 2003, Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405).

[15]  Dan Suciu,et al.  Schema mediation in peer data management systems , 2003, Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405).

[16]  Richard M. Karp,et al.  Load Balancing in Structured P2P Systems , 2003, IPTPS.

[17]  Jeffrey O. Kephart,et al.  The Vision of Autonomic Computing , 2003, Computer.

[18]  Tom W. Keller,et al.  Data placement in Bubba , 1988, SIGMOD '88.

[19]  Laura M. Haas,et al.  Transforming Heterogeneous Data with Database Middleware: Beyond Integration , 1999, IEEE Data Eng. Bull..

[20]  Thomas L. Sterling,et al.  BEOWULF: A Parallel Workstation for Scientific Computation , 1995, ICPP.