Title :
Valued redundancy
Author :
Pu, Calton ; Leff, Avraham ; Korz, Frederick ; Chen, Shu-Wie
Author_Institution :
Dept. of Comput. Sci., Columbia Univ., New York, NY, USA
Abstract :
The idea of valued redundancy for the complex memory hierarchies of the gigabit networks of tomorrow is introduced. The goal of valued redundancy is to replicate only the most valuable objects in the system, i.e. those that contribute the most to system performance and availability. The objects value explicitly represents its cost/performance ratio for the redundancy management system. In this way, performance and availability are maximized while the redundancy cost is minimized. Valued redundancy integrates the main components of a redundancy management system: the object location algorithm, the page replacement algorithm, and the consistent update algorithm
Keywords :
redundancy; storage management; consistent update algorithm; gigabit networks; management system; memory hierarchies; object location algorithm; page replacement algorithm; system performance; valued redundancy; Availability; Bandwidth; Communication networks; Computer science; Costs; Delay; Frequency; Performance gain; System performance; Voting;
Conference_Titel :
Management of Replicated Data, 1990. Proceedings., Workshop on the
Conference_Location :
Houston, TX
Print_ISBN :
0-8186-2085-4
DOI :
10.1109/MRD.1990.138249
