Specifying and using a partitionable group communication service

作者: Alan Fekete , Nancy Lynch , Alex Shvartsman , None

DOI: 10.1145/377769.377776

关键词:

摘要: Group communication services are becoming accepted as effective building blocks for the construction of fault-tolerant distributed applications. Many specifications group have been proposed. However, there is still no agreement about what these should say, especially in cases where partitionable, i.e., failures may lead to simultaneous creation groups with disjoint memberships, such that each unware existence any other group. In this paper, we present a new, succinct specification view-oriented partitionable service. The service associates message particular view membership. All send and receive events occur within associated view. provides total order on messages view, processor receives prefix order. Our separates safety requirements from performance fault-tolerance requirements. expressed by an abstract, global state machine. To requirements, include failure-status input actions specification; then give properties saying consensus timely delivery guaranteed execution provided stabilizes situation which stops changing corresponds consistently partioned system. Because not required every execution, subject existing impossibility results partionable systems. has simple implementation, based membership algorithm Christian Schmuck. We show utility constructing ordered-broadcast application, using (based algorithms Amir, Dolev, Keidar, others) reconciles information derived different instantiations application manages view-change activity build shared sequence messages, per-view orders combined universal prove correctness analyze resulting application.

参考文章(49)
Flaviu Cristian, Synchronous and Asynchronous Group Communication. Communications of The ACM. ,vol. 39, pp. 88- 97 ,(1996)
Paul D Ezhilchelvan, Raimundo A Macêdo, Santosh K Shrivastava, None, Newtop: a fault-tolerant group communication protocol international conference on distributed computing systems. pp. 296- 306 ,(1995) , 10.1109/ICDCS.1995.500032
A. Fekete, M.F. Kaashoek, N. Lynch, Implementing sequentially consistent shared objects using broadcast and point-to-point communication international conference on distributed computing systems. pp. 439- 449 ,(1995) , 10.1109/ICDCS.1995.500049
Jason Hickey, Nancy Lynch, Robbert van Renesse, Specifications and Proofs for Ensemble Layers tools and algorithms for construction and analysis of systems. pp. 119- 133 ,(1999) , 10.1007/3-540-49059-0_9
Mark Garland Hayden, The Ensemble System Cornell University. ,(1998)
N.A. Lynch, M.R. Tuttle, An introduction to input/output automata CWI quarterly. ,vol. 2, pp. 219- 246 ,(1989)
Roger Igor Khazan, Group communication as a base for a load-balancing replicated data service Massachusetts Institute of Technology. ,(1998)
Christophe Malloth, Andre Schiper, View Synchronous Communication in Large Scale Networks University of Bologna. ,(1995)
Roberto De Prisco, Alan Fekete, Nancy Lynch, Alex Shvartsman, A Dynamic Primary Configuration Group Communication Service international symposium on distributed computing. pp. 64- 78 ,(1999) , 10.1007/3-540-48169-9_5
O. Babaoglu, A. Montresor, R. Davoli, Group-Enhanced Remote Method Invocations University of Bologna. ,(1999)