Science. It is sponsored by the Netherlands Organisation for Scientific Research (NWO).CWI is a founding member of ERCIM, the European Research Consortium for Informatics and Mathematics.CWI's research has a theme-oriented structure and is grouped into four clusters. Listed below are the names of the clusters and in parentheses their acronyms. From coordination to stochastic models of QoS ABSTRACT Reo is a channel-based coordination model whose operational semantics is given by Constraint Automata (CA). Quantitative Constraint Automata extend CA (and hence, Reo) with quantitative models to capture such non-functional aspects of a system's behaviour as delays, costs, resource needs and consumption, that depend on the internal details of the system. However, the performance of a system can crucially depend not only on its internal details, but also on how it is used in an environment, as determined for instance by the frequencies and distributions of the arrivals of I/O requests. In this paper we propose Quantitative Intentional Automata (QIA), an extension of CA that allow incorporating the influence of a system's environment on its performance. Moreover, we show the translation of QIA into ContinuousTime Markov Chains (CTMCs), which allows us to apply existing CTMC tools and techniques for performance analysis of QIA and Reo circuits. Abstract. Reo is a channel-based coordination model whose operational semantics is given by Constraint Automata (CA). Quantitative Constraint Automata extend CA (and hence, Reo) with quantitative models to capture such non-functional aspects of a system's behaviour as delays, costs, resource needs and consumption, that depend on the internal details of the system. However, the performance of a system can crucially depend not only on its internal details, but also on how it is used in an environment, as determined for instance by the frequencies and distributions of the arrivals of I/O requests. In this paper we propose Quantitative Intentional Automata (QIA), an extension of CA that allow incorporating the influence of a system's environment on its performance. Moreover, we show the translation of QIA into Continuous-Time Markov Chains (CTMCs), which allows us to apply existing CTMC tools and techniques for performance analysis of QIA and Reo circuits. Probability, Networks and Algorithms (PNA)SoftwareKeywords: Performance evaluation, Coordination language, Reo, MarkovChains. IntroductionService-oriented Computing (SOC) provides the means to design and deploy distributed applications that span organization boundaries and computing platforms by exploiting and composing existing services available over a network. Services are platform-and network-independent applications that support rapid, low-cost, loosely-coupled composition. Services run on the hardware of their own providers, in different containers, separated by fire-walls and other ownership and trust barriers. Their composition requires additional mechanisms (e.g., process work-flow engines, connectors, or glue code) to impos...

Modern Internet systems have evolved from simple monolithic systems to complex multitiered architectures. For these systems, providing good response time performance is crucial for the commercial success. In practice, the response-time performance of multi-tiered systems is often degraded by severe synchronization problems, causing jobs to wait for responses from different tiers. Synchronization between different tiers is a complicating factor in the optimal control and analysis of the performance. In this paper, we study a generic multi-tier model with synchronization. The system is able to share processing capacity between arriving jobs that need to be sent to other tiers and the responses that have arrived after processing from these tiers. We provide structural results on the optimal resource allocation policy and provide a full characterization of the policy in the framework of Markov decision theory. We also highlight important effects of synchronization in the model and discuss their implications for practice. We validate our expressions through extensive experimentations for a wide range of resource configurations.

Abstract. Quantifying the performance of component-based or serviceoriented systems is a complex task, e.g., it is non-trivial to calculate the end-to-end quality of service of a composite Web service. An established approach to reason about such systems in general is the use of coordination models, which can provide a formal basis for both their verification and implementation. An example of such a model is the channel-based coordination language Reo and its probabilistic extension Stochastic Reo. However, all existing performance analysis approaches for Stochastic Reo are restricted to the use of exponential distributions. To this end we introduce a transition structure, which enables a simulation approach for performance evaluation in Reo, enabling the use of arbitrary distributions and predefined probabilistic behaviors. Our approach supports steadystate and transient analysis and, moreover, scales much better than the existing automata-based algorithms.