Predictive performance modeling of virtualized storage systems using optimized statistical regression techniques
Predictive performance modeling of virtualized storage systems using optimized statistical regression techniques
复制标题
使用优化的统计回归技术对虚拟化存储系统进行预测性能建模
DOI：
10.1145/2479871.2479910
复制
发表时间：
2013
影响因子：
8.1
通讯作者：
Ralf H. Reussner
中科院分区：
文献类型：
--
作者：
Qais Noorshams;D. Bruhn;Samuel Kounev;Ralf H. Reussner
现代虚拟化环境是降低数据中心运营成本的关键。通过实现物理资源共享，虚拟化有望提高资源效率，同时降低管理成本。然而，随着I/O密集型应用程序的日益普及，此类环境中使用的虚拟化存储可能很快成为瓶颈，并导致性能和可扩展性问题。在系统部署之前应用的性能建模和评估技术有助于避免此类问题。然而，在目前的实践中，虚拟化存储及其性能影响因素往往被忽视或视为黑箱。在本文中，我们提出了一个基于测量的虚拟化存储系统的性能预测方法的基础上优化的统计回归技术。我们首先提出一个通用的启发式搜索算法来优化回归技术的参数。然后，我们应用我们的优化方法，并使用四种回归技术创建性能模型。最后，我们提出了一个深入的评估，我们的方法在现实世界的代表性环境的基础上IBM System z和IBM DS 8700服务器硬件。使用我们的优化技术，我们有效地创建性能模型，在最典型的情况下预测误差小于7%。此外，我们的优化方法将预测误差降低了74%。
Modern virtualized environments are key for reducing the operating costs of data centers. By enabling the sharing of physical resources, virtualization promises increased resource efficiency with decreased administration costs. With the increasing popularity of I/O-intensive applications, however, the virtualized storage used in such environments can quickly become a bottleneck and lead to performance and scalability issues. Performance modeling and evaluation techniques applied prior to system deployment help to avoid such issues. In current practice, however, virtualized storage and its performance-influencing factors are often neglected or treated as a black-box. In this paper, we present a measurement-based performance prediction approach for virtualized storage systems based on optimized statistical regression techniques. We first propose a general heuristic search algorithm to optimize the parameters of regression techniques. Then, we apply our optimization approach and create performance models using four regression techniques. Finally, we present an in-depth evaluation of our approach in a real-world representative environment based on IBM System z and IBM DS8700 server hardware. Using our optimized techniques, we effectively create performance models with less than 7% prediction error in the most typical scenario. Furthermore, our optimization approach reduces the prediction error by up to 74%.