International audienceContinuously adjusting the horizontal scaling ofapplications hosted by data centers appears as a good candidateto automatic control approaches allocating resources in closedloopgiven their current workload. Despite several attempts,real applications of these techniques in cloud computing infrastructuresface some difficulties. Some of them essentially turnback to the core concepts of automatic control: controllability,inertia of the controlled system, gain and stability. In thispaper, considering our recent work to build a managementframework dedicated to automatic resource allocation in virtualizedapplications, we attempt to identify from experiments thesources of instabilities in the controlled systems. As examples,we analyze two types of policies: threshold-based and reinforcementlearning techniques to dynamically scale resources. Theexperiments show that both approaches are tricky and thattrying to implement a controller without looking at the waythe controlled system reacts to actions, both in time and inamplitude, is doomed to fail. We discuss both lessons learnedfrom the experiments in terms of simple yet key points to buildgood resource management policies, and longer term issueson which we are currently working to manage contracts andreinforcement learning efficiently in cloud controllers
Abstract-Computing has reached the time of distributed applications everywhere. Service-oriented architectures are more and more used to organize such complex and highly dynamic applications into business processes calling services discovered in registries at load-time. In this context, Quality of Service (QoS) and agility in business processes become key issues. Instead of binding business processes to services at load-time, this paper proposes to monitor sets of candidate services for their current QoS and to choose among them at call-time. This new form of late-binding paves the way to more agile and robust applications called adaptive business processes. Besides the conceptual background and implementation of this late-binding in an industrial-strength web service platform, this paper presents the LCP-net formalism introduced to provide programmers with a mean to express qualitatively their preferences among the different QoS properties of services, hence tackling the multicriteria decision making arising from the run-time choice among candidate services given several unrelated QoS properties.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.