Affiliation:
1. Distributed Systems Group, TU Wien, Vienna, Austria
Abstract
Cloud applications can benefit from the on-demand capacity of cloud infrastructures, which offer computing and data resources with diverse capabilities, pricing, and quality models. However, state-of-the-art tools mainly enable the user to specify “if-then-else” policies concerning resource usage and size, resulting in a cumbersome specification process that lacks expressiveness for enabling the control of complex multilevel elasticity requirements.
In this article, first we propose SYBL, a novel language for specifying elasticity requirements at multiple levels of abstraction. Second, we design and develop the rSYBL framework for controlling cloud services at multiple levels of abstractions. To enforce user-specified requirements, we develop a multilevel elasticity control mechanism enhanced with conflict resolution. rSYBL supports different cloud providers and is highly extensible, allowing service providers or developers to define their own connectors to the desired infrastructures or tools. We validate it through experiments with two distinct services, evaluating rSYBL over two distinct cloud infrastructures, and showing the importance of multilevel elasticity control.
Funder
European Commission in terms of the CELAR FP7 project
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications
Cited by
11 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Introducing Monitoring and extended Elasticity support in TOSCA;Proceedings of the IEEE/ACM 16th International Conference on Utility and Cloud Computing;2023-12-04
2. Elastic Smart Contracts in Blockchains;IEEE/CAA Journal of Automatica Sinica;2021-12
3. Model-Driven Elasticity Management with OCCI;IEEE Transactions on Cloud Computing;2021-10-01
4. An Elasticity Framework for Smart Contracts;2021 IEEE International Conference on Smart Data Services (SMDS);2021-09
5. Severity: a QoS-aware approach to cloud application elasticity;Journal of Cloud Computing;2021-08-21