RPM: Um Sistema para Posicionar Réplicas
Abstract
Distributed systems use object replication to assure availability. However, new problems arise as how to control the replica consistency, how to determine the needed number of replicas and where the replicas should be placed. A replica consistency protocol guarantees the replica consistency. The replication level and replica placement, nowadays, are an empirical designer decision. Here we show aspects that should be considered in replica placement. We also introduce a manager module, the RPM — Replica Placement Manager — that decides where these replicas should be placed, using data obtained from the dynamic monitoring of the system.
References
Birman, Kenneth P.; et alii. HORUS: A Flexible Group Communication System. Communications of the ACM. Vol. 39, no 4, pág. 76-83, April, 1996.
Budhiraja, Navin; et alii. The Primary-Backup Approach em Mullender, Sape. Distributed Systems. 2 ed., New York: ACM Press, 1993. Pg. 199-215
Guerraoui, R.; Schiper, André Software-Based Replication for Fault Tolerance. IEEE Computer, April, 1997, pag. 68-74
Hayden, Mark G. The Ensemble System. Comell University, January, 1998
Little. M.C.; McCue, D.L. The Replica Management System: a Scheme for Flexible and Dynamic Replication, Proc. Of the 2nd Workshop on Configurable Distributed Systems, University of Newcastle upon Tyne, March, 1994
Pasin, Marcia, et alii. Reconfiguring Replicated Objects to Provide Fault Tolerance and Load Balancing in a Distributed System. Universidade Federal do Rio Grande do Sul, Maio, 2000.
Russ, Samuel H.: et alii. The Hector Distributed Run-Time Environment. IEEE Transactions on Parallel and Distributed Systems, Vol. 9, n. 11, Nov., 1998
Schneider, Fred B. Replication Management Using the State-Machine Approach em Mullender, Sape. Distributed Systems. 2. ed., New York: ACM Press, 1993. Pg. 169-197
Kopetz, H. et alii. Tolerant Transient Faults in MARS. Proceedings of the 20th International Symposium on Fault-Tolerant Computing, 1990, pp. 466-473.
Budhiraja, Navin; et alii. The Primary-Backup Approach em Mullender, Sape. Distributed Systems. 2 ed., New York: ACM Press, 1993. Pg. 199-215
Guerraoui, R.; Schiper, André Software-Based Replication for Fault Tolerance. IEEE Computer, April, 1997, pag. 68-74
Hayden, Mark G. The Ensemble System. Comell University, January, 1998
Little. M.C.; McCue, D.L. The Replica Management System: a Scheme for Flexible and Dynamic Replication, Proc. Of the 2nd Workshop on Configurable Distributed Systems, University of Newcastle upon Tyne, March, 1994
Pasin, Marcia, et alii. Reconfiguring Replicated Objects to Provide Fault Tolerance and Load Balancing in a Distributed System. Universidade Federal do Rio Grande do Sul, Maio, 2000.
Russ, Samuel H.: et alii. The Hector Distributed Run-Time Environment. IEEE Transactions on Parallel and Distributed Systems, Vol. 9, n. 11, Nov., 1998
Schneider, Fred B. Replication Management Using the State-Machine Approach em Mullender, Sape. Distributed Systems. 2. ed., New York: ACM Press, 1993. Pg. 169-197
Kopetz, H. et alii. Tolerant Transient Faults in MARS. Proceedings of the 20th International Symposium on Fault-Tolerant Computing, 1990, pp. 466-473.
Published
2000-07-15
How to Cite
ZAMPIERI, André; WEBER, Taisy Silva; PASIN, Marcia.
RPM: Um Sistema para Posicionar Réplicas. In: FAULT TOLERANCE WORKSHOP (WTF), 2. , 2000, Curitiba/PR.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2000
.
p. 28-33.
ISSN 2595-2684.
DOI: https://doi.org/10.5753/wtf.2000.23470.
