Architecture-level software performance abstractions for online performance prediction

Architecture-level software performance abstractions for online performance prediction
复制标题

用于在线性能预测的架构级软件性能抽象

DOI:
10.1016/j.scico.2013.06.004
复制
发表时间:
2014
期刊:
Sci. Comput. Program.
影响因子:
--
通讯作者:
Samuel Kounev
Samuel Kounev
中科院分区:
--
文献类型:
--
作者:
Fabian Brosig;Nikolaus Huber;Samuel Kounev

文献摘要

参考文献

被引文献

相似文献

现代面向服务的企业系统具有日益复杂和动态的松散耦合体系结构,这些体系结构往往表现出较差的性能和资源效率,并且具有较高的运营成本。这是因为无法在运行时预测工作负载变化对与性能相关的应用程序级依赖关系的影响,并相应地调整系统配置。体系结构级性能模型为性能预测提供了强大的工具,然而,当前建模软件组件上下文的方法不适合在运行时使用。本文分析了典型的在线性能预测场景,提出了一个性能元模型,用于(I)表示和解析参数和上下文依赖,(Ii)在不同粒度级别对服务抽象进行建模,(Iii)在复杂资源环境中对软件组件的部署进行建模。提出的元模型是笛卡尔元模型模型(DMM)的一个子集,用于在线性能预测,专门为在线预测而设计。我们在基于SPECjEnterprise2010标准基准的现实和具有代表性的在线业绩预测场景的背景下,激励和验证我们的方法。
Modern service-oriented enterprise systems have increasingly complex and dynamic loosely-coupled architectures that often exhibit poor performance and resource efficiency and have high operating costs. This is due to the inability to predict atrun-timethe effect of workload changes on performance-relevant application-level dependencies and adapt the system configuration accordingly. Architecture-level performance models provide a powerful tool for performance prediction, however, current approaches to modeling the context of software components are not suitable for use at run-time. In this paper, we analyze typical online performance prediction scenarios and propose a performance meta-model for (i) expressing and resolving parameter and context dependencies, (ii) modeling service abstractions at different levels of granularity and (iii) modeling the deployment of software components in complex resource landscapes. The presented meta-model is a subset of the Descartes Meta-Model (DMM) for online performance prediction, specifically designed for use inonlinescenarios. We motivate and validate our approach in the context of realistic and representative online performance prediction scenarios based on the SPECjEnterprise2010 standard benchmark.
具有场景和资源的中间元模型,用于从 UML 设计生成性能模型
DOI: --
发表时间: 2007
期刊: Journal of Software and Systems Modeling
影响因子: --
作者:
D. Petriu;M. Woodside
通讯作者: M. Woodside
CB-SPE 工具:将基于组件的性能工程付诸实践
DOI: --
发表时间: 2004
期刊: International Symposium on Component-Based Software Engineering
影响因子: --
作者:
A. Bertolino;R. Mirandola
通讯作者: R. Mirandola
在线架构级性能模型中对参数和上下文依赖关系进行建模
DOI: --
发表时间: 2012
期刊: International Symposium on Component-Based Software Engineering
影响因子: --
作者:
Fabian Brosig;Nikolaus Huber;Samuel Kounev
通讯作者: Samuel Kounev
从 UML 模型到软件性能结果:基于 XML 交换格式的 SPE 流程
DOI: --
发表时间: 2005
期刊: Workshop on Software and Performance
影响因子: --
作者:
C. U. Smith;Catalina M. Lladó;V. Cortellessa;A. Marco;L. Williams
通讯作者: L. Williams
DOI: --
发表时间: 2004
期刊: International Symposium on Component-Based Software Engineering
影响因子: --
作者:
E. M. Eskenazi;A. V. Fioukov;D. Hammer
通讯作者: D. Hammer