Implementing hybrid consistency with high-level synchronization operations

被引:8
作者
Friedman, R
机构
[1] Department of Computer Science, The Technion, Haifa
关键词
distributed shared memory; consistency condition; hybrid consistency; synchronization operations;
D O I
10.1007/s004460050014
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In recent years, there is a growing tendency to support high-level synchronization operations, such as read-modify-write, FIFO queues and stacks, as part of the programmer's shared memory model. This paper examines the problem of implementing hybrid consistency with high-level synchronization operations. It is shown that for any implementation of weak consistency, the time required to execute a read-modify-write, a dequeue or a pop operation is Omega(d), where d is the network delay. Following this, an efficient and simple algorithm for providing hybrid consistency that supports most types of high-level synchronization operations and weak read and weak write operations is presented. Weak read and weak write operations are executed instantaneously, while the time required to execute strong operations is O(d). This is within a constant factor of the lower bounds for most of the commonly used types of operations.
引用
收藏
页码:119 / 129
页数:11
相关论文
共 38 条
[1]  
ADVE S, 1991, 1051 U WISC COMP SCI
[2]  
ADVE SV, 1990, 17TH ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE, P2, DOI 10.1109/ISCA.1990.134502
[3]   LAZY CACHING [J].
AFEK, Y ;
BROWN, G ;
MERRITT, M .
ACM TRANSACTIONS ON PROGRAMMING LANGUAGES AND SYSTEMS, 1993, 15 (01) :182-205
[4]  
AGARWEL A, 1991, P WORKSHOP SCALABLE
[5]  
AHAMAD M, 1995, DISTRIB COMPUT, V9, P37, DOI 10.1007/BF01784241
[6]  
AHAMAD M, 1991, 5TH INT WORKSH DISTR
[7]  
AHAMAD M, 1990, TR GITCC9049 GEORG I
[8]  
ALVAREZ G, 1995, CS95416 U CAL DEP CO
[9]  
AMIR Y, 1992, CS929 HERBR U JER DE
[10]   SEQUENTIAL CONSISTENCY VERSUS LINEARIZABILITY [J].
ATTIYA, H ;
WELCH, JL .
ACM TRANSACTIONS ON COMPUTER SYSTEMS, 1994, 12 (02) :91-122