THE TOTEM SINGLE-RING ORDERING AND MEMBERSHIP PROTOCOL

被引:145
作者
AMIR, Y [1 ]
MOSER, LE [1 ]
MELLIARSMITH, PM [1 ]
AGARWAL, DA [1 ]
CIARFELLA, P [1 ]
机构
[1] UNIV CALIF SANTA BARBARA,DEPT ELECT & COMP ENGN,SANTA BARBARA,CA 93106
来源
ACM TRANSACTIONS ON COMPUTER SYSTEMS | 1995年 / 13卷 / 04期
关键词
FLOW CONTROL; MEMBERSHIP; RELIABLE DELIVERY; TOKEN PASSING; TOTAL ORDERING; VIRTUAL SYNCHRONY;
D O I
10.1145/210223.210224
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Fault-tolerant distributed systems are becoming more important, but in existing systems, maintaining the consistency of replicated data is quite expensive. The Totem single-ring protocol supports consistent concurrent operations by placing a total order on broadcast messages. This total order is derived from the sequence number in a token that circulates around a logical ring imposed on a set of processors in a broadcast domain. The protocol handles reconfiguration of the system when processors fail and restart or when the network partitions and remerges. Extended virtual synchrony ensures that processors deliver messages and configuration changes to the application in a consistent, systemwide total order. An effective flow control mechanism enables the Totem single-ring protocol to achieve message-ordering rates significantly higher than the best prior total-ordering protocols.
引用
收藏
页码:311 / 342
页数:32
相关论文
共 19 条
[1]  
AMIR Y, 1993, 13TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS : PROCEEDINGS, P551, DOI 10.1109/ICDCS.1993.287668
[2]  
AMIR Y, 1992, 6 INT WORKSH DISTR A, P292
[3]  
AMIR Y, 1994, 9419 U CAL DEP EL CO
[4]  
Birman K. P., 1994, RELIABLE DISTRIBUTED
[5]  
BOXMA OJ, 1990, 14TH P IFIP WG 7 3 I, P349
[6]   RELIABLE BROADCAST PROTOCOLS [J].
CHANG, JM ;
MAXEMCHUK, NF .
ACM TRANSACTIONS ON COMPUTER SYSTEMS, 1984, 2 (03) :251-273
[7]   IMPOSSIBILITY OF DISTRIBUTED CONSENSUS WITH ONE FAULTY PROCESS [J].
FISCHER, MJ ;
LYNCH, NA ;
PATERSON, MS .
JOURNAL OF THE ACM, 1985, 32 (02) :374-382
[8]  
Hodge S. P., 1992, 22ND P ANN INT S FAU, V117, P76
[9]  
KAASHOEK MF, 1991, 11 INT C DISTR COMP, P882
[10]   TIME, CLOCKS, AND ORDERING OF EVENTS IN A DISTRIBUTED SYSTEM [J].
LAMPORT, L .
COMMUNICATIONS OF THE ACM, 1978, 21 (07) :558-565