The Community for Technology Leaders
Green Image
<p>Bubba is a highly parallel computer system for data-intensive applications. The basis of the Bubba design is a scalable shared-nothing architecture which can scale up to thousands of nodes. Data are declustered across the nodes (i.e. horizontally partitioned via hashing or range partitioning) and operations are executed at those nodes containing relevant data. In this way, parallelism can be exploited within individual transactions as well as among multiple concurrent transactions to improve throughput and response times for data-intensive applications. The current Bubba prototype runs on a commercial 40-node multicomputer and includes a parallelizing compiler, distributed transaction management, object management, and a customized version of Unix. The current prototype is described and the major design decisions that went into its construction are discussed. The lessons learned from this prototype and its predecessors are presented.</p>
highly parallel database system; data-intensive applications; Bubba design; scalable shared-nothing architecture; declustered; horizontally partitioned; hashing; range partitioning; parallelism; multiple concurrent transactions; throughput; response times; Bubba prototype; commercial 40-node multicomputer; parallelizing compiler; distributed transaction management; object management; customized version; Unix; distributed databases; parallel architectures; parallel machines; parallel programming; transaction processing
P. Valduriez, M. Smith, S. Danforth, W. Alexander, M. Franklin, L. Clay, H. Boral, B. Hart, G. Copeland, "Prototyping Bubba, A Highly Parallel Database System", IEEE Transactions on Knowledge & Data Engineering, vol. 2, no. , pp. 4-24, March 1990, doi:10.1109/69.50903
91 ms
(Ver 3.1 (10032016))