The stochastic rendezvous network model for performance of synchronous client-server-like distributed software

Abstract

Distributed or parallel software with synchronous communication via rendezvous is found in client-server systems and in proposed Open Distributed Systems, in implementation environments such as Ada, V, Remote Procedure Call systems, in Transputer systems, and in speci cation techniques such as CSP, CCS and LOTOS. The delays induced by rendezvous can cause serious performance problems, which are not easy to estimate using conventional models which focus on hardware contention, or on a restricted view of the parallelism which ignores implementation constraints. Stochastic Rendezvous Networks are queueing networks of a new type which have been proposed as a modelling framework for these systems. They incorporate the two key phenomena of included service and a second phase of service. This paper extends the model to also incorporate di erent services or entries associated with each task. Approximations to arrival-instant probabilities are employed with a Mean-Value Analysis framework, to give approximate performance estimates. The method has been applied to moderately large industrial software systems.

Managing dynamic enterprise and urgent workloads on clouds using layered queuing and historical performance models

“…Further, although both techniques are well documented (e.g. [4,5,6,9,10,11]), it is once again only the layered queuing method that provides material for both beginner and more expert users.…”

“…Performance metrics generated include mean response time, throughputs and utilisation information for each service class. A detailed description of the layered queuing method can be found in [9,23].…”

“…A service class with n buy clients is created for buy users which involves clients making an average of 10 buy requests. The percentage of buy clients is defined as b. Think-times are exponentially distributed based on [9] with a mean of 7 seconds for all service classes as recommended by IBM for Trade clients, although heterogeneous think-times are supported by both techniques. Based on the Trade benchmark, a typical workload is defined as all browse clients.…”

“…In [10] a layered queuing model of a distributed database system is created and compared to a Markov chain-based queuing model of the system. In [9] the layered queuing method is compared more generally to other performance modelling techniques. Another recognised queuing technique which has been applied to similar applications is described in [7] and compared with the layered queuing method.…”

“…Examples of the queuing modelling approach include [7,8,2]. The layered queuing method [9] is of particular interest and will be examined further in this paper as it explicitly models the tiers of servers found in this class of application, and it has been applied to a range of distributed systems (e.g. [10]) including the benchmark used in this paper [11].…”