PUMA publications for /tag/cloud-computingMon Jan 13 13:33:26 CET 2025New York, NY, USACompanion of the 2023 ACM/SPEC International Conference on Performance Engineering4277–282ICPE '23 CompanionHitchhiker's Guide for Explainability in Autoscaling2023autoscaling cloud-computing elasticity explainability 15Cloud-native applications force increasingly powerful and complex autoscalers to guarantee the applications' quality of service. For software engineers with operational tasks understanding the autoscalers' behavior and applying appropriate reconfigurations is challenging due to their internal mechanisms, inherent distribution, and decentralized decision-making. Hence, engineers seek appropriate explanations. However, engineers' expectations on feedback and explanations of autoscalers are unclear. In this paper, through a workshop with a representative sample of engineers responsible for operating an autoscaler, we elicit requirements for explainability in autoscaling. Based on the requirements, we propose an evaluation scheme for evaluating explainability as a non-functional property of the autoscaling process and guide software engineers in choosing the best-fitting autoscaler for their scenario. The evaluation scheme is based on a Goal Question Metric approach and contains three goals, nine questions to assess explainability, and metrics to answer these questions. The evaluation scheme should help engineers choose a suitable and explainable autoscaler or guide them in building their own.Mon Jan 13 13:31:11 CET 20252023 ACM/IEEE International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C)oct19-23Designing Elasticity Policies for Cloud-Native Applications with Slingshot2023autoscaling cloud cloud-computing elasticity performance policies simulation threshold-based Engineering cloud-native applications that provision resources autonomously to match the demand is a continuous and shared concern for stakeholders in the development process. Model-based performance engineering approaches help for up-front engineering of elasticity policies that control the adjustment of resources at runtime. Specifically, the Palladio approach allows stakeholders in the development process to model the application from various viewpoints and make performance predictions. This paper demonstrates Slingshot for designing elasticity policies for cloud-native applications. We make two contributions that build upon the Palladio approach. One contribution is a separate view-point for modeling elasticity policies for cloud-native applications. The second contribution is the Slingshot simulator capable of predicting the performance of modeled elasticity policies.Mon Sep 19 11:56:26 CEST 2022New York, NY, USACompanion of the 2022 ACM/SPEC International Conference on Performance Engineering753–60ICPE '22Beauty and the Beast: A Case Study on Performance Prototyping of Data-Intensive Containerized Cloud Applications2022cloud-computing myown performance threshold-based 14Data-intensive container-based cloud applications have become popular with the increased use cases in the Internet of Things domain. Challenges arise when engineering such applications to meet quality requirements, both classical ones like performance and emerging ones like resilience. There is a lack of reference use cases, applications, and experiences when prototyping such applications that could benefit the research community. Moreover, it is hard to generate realistic and reliable workloads that exercise the resources according to a specification. Hence, designing reference applications that would exhibit similar performance behavior in such environments is hard. In this paper, we present a work in progress towards a reference use case and application for data-intensive containerized cloud applications having an industrial motivation. Moreover, to generate reliable CPU workloads we make use of ProtoCom, a well-known library for the generation of resource demands, and report the performance under various quality requirements in a Kubernetes cluster of moderate size. Finally, we present the scalability of the current solution assuming a particular autoscaling policy. Results of the calibration show high variability of the ProtoCom library when executed in a cloud environment. We observe a moderate association between the occupancy of node and the relative variability of execution time.Mon Sep 19 11:56:26 CEST 2022New York, NY, USACompanion of the 2022 ACM/SPEC International Conference on Performance Engineering753–60ICPE '22Beauty and the Beast: A Case Study on Performance Prototyping of Data-Intensive Containerized Cloud Applications2022myown from:klinaku cloud-computing performance threshold-based 14Data-intensive container-based cloud applications have become popular with the increased use cases in the Internet of Things domain. Challenges arise when engineering such applications to meet quality requirements, both classical ones like performance and emerging ones like resilience. There is a lack of reference use cases, applications, and experiences when prototyping such applications that could benefit the research community. Moreover, it is hard to generate realistic and reliable workloads that exercise the resources according to a specification. Hence, designing reference applications that would exhibit similar performance behavior in such environments is hard. In this paper, we present a work in progress towards a reference use case and application for data-intensive containerized cloud applications having an industrial motivation. Moreover, to generate reliable CPU workloads we make use of ProtoCom, a well-known library for the generation of resource demands, and report the performance under various quality requirements in a Kubernetes cluster of moderate size. Finally, we present the scalability of the current solution assuming a particular autoscaling policy. Results of the calibration show high variability of the ProtoCom library when executed in a cloud environment. We observe a moderate association between the occupancy of node and the relative variability of execution time.Mon Jan 18 11:00:48 CET 2021Advances in Service-Oriented and Cloud Computing - Workshops of {ESOCC} 2018, Como, Italy, September 12-14, 2018, Revised Selected Papers158--165Communications in Computer and Information ScienceThe Slingshot Approach - Model-Driven Engineering the Coordination of Autoscaling Mechanisms for Elastic Cloud Applications11152018cloud-computing myown performance Mon Jan 18 10:52:15 CET 20212020 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW)oct267-274Resilience, Survivability, and Elasticity: A Taxonomy for Change Impact Quantification of Reconfigurable Systems2020cloud-computing performance Context. Modern distributed systems are flexible in moving from one configuration to another during operation in an automated or semi-automated manner, e.g., concerning dynamic CPU allocation and deploying updated versions of system services. Software architects need assurance that the system satisfies agreed quality of service (QoS) despite a change in system configuration. In the literature, under resilience, survivability, and elasticity, there are different change impact quantification approaches that each has different methods for quality metric specification, modeling a change, and impact analysis. However, independent of a particular approach, no taxonomy exists that clarifies a set of general concepts concerning change impact quantification in reconfigurable systems.Objective. We propose a taxonomy by examining existing approaches under the three meta-quality attributes for change impact quantification.Method. We start with works done by heavily cited authors behind resilience, survivability, and elasticity who provided unambiguous and measurable definitions.Result. We classify existing approaches for change impact quantification based on the taxonomy. We demonstrate the application of our taxonomy through an example.Conclusion. The taxonomy provides a unified and structured knowledge across communities that further eases communication and development of new approaches for change impact quantification.Thu Dec 19 16:25:32 CET 2019Proceedings of the 13th European Conference on Software Architecture - {ECSA} {\textquotesingle}19 - volume 2The applicability of palladio for assessing the quality of cloud-based microservice architectures2019cloud-computing containerssend:unibiblio myown performance threshold-based Fri Jan 18 09:44:10 CET 2019New York, NY, USACompanion of the 2018 ACM/SPEC International Conference on Performance Engineering93--98ICPE '18CAUS: An Elasticity Controller for a Containerized Microservice2018cloud-computing elasticity horizontal-scaling myown over-provisioning threshold-based cloud-computingCommunity for tag(s) cloud-computing