Adaptive Resource Provisioning for Virtualized Servers Using Kalman Filters
Adaptive Resource Provisioning for Virtualized Servers Using Kalman Filters
复制标题
DOI：
10.1145/2626290
复制
发表时间：
2014-07
期刊：
影响因子：
--
通讯作者：
Evangelia Kalyvianaki;Themistoklis Charalambous;S. Hand
中科院分区：
文献类型：
--
作者：
Evangelia Kalyvianaki;Themistoklis Charalambous;S. Hand
数据中心虚拟化服务器的资源管理已成为一项关键任务，因为它可以实现服务器应用程序的经济高效的整合。资源管理是一项重要且具有挑战性的任务，特别是对于具有不可预测的时变工作负载的多层应用程序。使用控制理论进行的资源管理工作已经显示出动态调整资源分配以匹配波动的工作负载的明显好处。然而，针对未知工作负载类型的自适应控制器的研究还很少。这项工作提出了一种新的资源管理方案，该方案将卡尔曼滤波器合并到反馈控制器中，以动态地将 CPU 资源分配给托管服务器应用程序的虚拟机。我们提出了一组控制器，可以持续检测并自适应不可预见的工作负载变化。此外，我们最先进的控制器还可以在没有任何先验信息的情况下进行自我配置，并且在高强度工作负载变化的情况下，性能损失较小，为 4.8%。此外，我们的控制器得到了增强，可以处理多层服务器应用程序：通过使用层之间的成对资源耦合，与没有这种资源耦合机制的控制器相比，它们提高了服务器对大量工作负载增加的响应。我们的方法经过评估，并在部署在原型 Xen 虚拟化集群上的 3 层 Rubis 基准网站上展示了它们的性能。
Resource management of virtualized servers in data centers has become a critical task, since it enables cost-effective consolidation of server applications. Resource management is an important and challenging task, especially for multitier applications with unpredictable time-varying workloads. Work in resource management using control theory has shown clear benefits of dynamically adjusting resource allocations to match fluctuating workloads. However, little work has been done toward adaptive controllers for unknown workload types. This work presents a new resource management scheme that incorporates the Kalman filter into feedback controllers to dynamically allocate CPU resources to virtual machines hosting server applications. We present a set of controllers that continuously detect and self-adapt to unforeseen workload changes. Furthermore, our most advanced controller also self-configures itself without any a priori information and with a small 4.8% performance penalty in the case of high-intensity workload changes. In addition, our controllers are enhanced to deal with multitier server applications: by using the pair-wise resource coupling between tiers, they improve server response to large workload increases as compared to controllers with no such resource-coupling mechanism. Our approaches are evaluated and their performance is illustrated on a 3-tier Rubis benchmark website deployed on a prototype Xen-virtualized cluster.