Performance aspects of dynamic re-allocation for partitioned data

Authors:
Paul Jensen;Monica Brockmeyer;Nandit Soparkar
Affiliations:
Electrical Engineering & Computer Science, The University of Michigan, Ann Arbor, MI;Electrical Engineering & Computer Science, The University of Michigan, Ann Arbor, MI;Electrical Engineering & Computer Science, The University of Michigan, Ann Arbor, MI
Venue:
CASCON '96 Proceedings of the 1996 conference of the Centre for Advanced Studies on Collaborative research
Year:
1996

Citing 7
Cited 0

Consistency in a partitioned network: a survey

ACM Computing Surveys (CSUR)
Concurrency control and recovery in database systems

Concurrency control and recovery in database systems
Operating system concepts (3rd ed.)

Operating system concepts (3rd ed.)
P.S. to operating systems

P.S. to operating systems
Mobile wireless computing: challenges in data management

Communications of the ACM
Data-valued partitioning and virtual messages (extended abstract)

PODS '90 Proceedings of the ninth ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems
Computers and Intractability: A Guide to the Theory of NP-Completeness

Computers and Intractability: A Guide to the Theory of NP-Completeness

Quantified Score

Hi-index	0.00

Visualization

Abstract

The correct and effcient management of data in distributed databases or mobile computing environments is diffcult. Communication disruptions within such systems render the execution of database transactions problematic due to difficulties in atomic commitment strategies. A previously proposed non-traditional system for data and operators, with single site transaction executions and decentralized commitment [9], is useful in specific applications. For this approach, we use some simple analytical and simulation models to assess performance, and provide our findings for straightforward demand-driven and periodic re-allocation strategies.