Analytic performance estimation of client-server systems with multi-threaded clients
This paper presents an analytical performance model named Rendezvous Network with Multi-Threaded Clients (RNMTC) for performance analysis of client-server systems. RNMTC is able to model systems with multiple clients inter-communicating with multiple servers which may represent either hardware or software system components. Each system client is described by a precedence graph, and may consist of multiple concurrent execution threads whose number can vary due to fork and join operations. The analytic method for RNMTC proposed in the paper is based on hierarchical decomposition: at the higher level, the system behaviour is represented by a Markov Chain (MC) model whose states correspond to all possible combinations of client execution states; at the lower level, a Stochastic Rendezvous Network (SRVN) model with simple clients corresponds to each MC state. SRVN was previously introduced and MVA approximate analytic solutions are known. The RNMTC model has been used with a number of different test cases and the analytic results were found to be in close agreement with simulation results.
|Proceedings of the 2nd International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems|
Petriu, D, Majumdar, S, Lin, Jingping, & Hrischuk, Curtis. (1994). Analytic performance estimation of client-server systems with multi-threaded clients. Presented at the Proceedings of the 2nd International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems.