PATPro: Power Aware Thin Provisioning of Resources in Virtualized Servers

PATPro: Power Aware Thin Provisioning of Resources in Virtualized Servers
复制标题

PATPro:虚拟化服务器中资源的节能感知精简配置

DOI:
10.12785/amis/071l28
复制
发表时间:
2013-02
影响因子:
--
通讯作者:
蒋从锋
蒋从锋
中科院分区:
--
文献类型:
--
作者:
蒋从锋

文献摘要

参考文献

相似文献

在传统的虚拟化系统中,为了保证托管应用程序的峰值性能,通常会过度配置虚拟机,从而浪费大量的计算资源。尽管虚拟机整合可以节省功耗,但它也增加了机架中的功率强度,使服务器更容易发生故障。在电力预算受限的情况下,它还增加了违反服务水平协议(sla)的可能性。由于虚拟机的自主性、工作负载动态和性能需求,在虚拟化服务器中权衡功率和性能是很重要的。在本文中,我们提出了一种用于资源分配的功率感知瘦配置方法,称为PATPro,以协调和权衡多个虚拟机之间的功率和性能。为了提供有关单个VM和应用程序的电源特性的足够信息,我们使用代理进行实时电源收集和工作负载表征。我们在一个有8个虚拟机的真实虚拟化环境中评估了我们的算法。结果表明,在web服务器和数据库操作等计算密集型、I/O密集型和混合工作负载的应用程序中,该方法可以节省5.41%至6.33%的功耗,以提供相同的性能。结果还显示了我们的方法在实际虚拟化环境中使用的潜力。
In traditional virtualization systems Virtual Machines (VMs) are usually over-provisioned for guarantying peak performance of hosting applications and thus waste a lot of computing resources. Although virtual machine consolidation can save power consumptions, it also increases the power intensity in a rack and makes the servers more prone to failures. It also increases the probability of Service Level Agreements (SLAs) violations under constrained power budget. Due to the autonomy, workload dynamics and performance requirements of Virtual Machines, it is nontrivial to tradeoff between the power and performance in virtualized servers. In this paper, we proposed a power aware thin provisioning approach for resource allocation, named PATPro, to coordinate and tradeoff the power and performance among multiple virtual machines. In order to provide enough information about power characteristics of individual VM and applications, we use agent for real time power collection and workload characterization. We evaluated our algorithm in a real virtualization environment with 8 VMs. The results show that the proposed approach can save 5.41% to 6.33% power consumption to provide the same performance in applications including computing-intensive, I/O intensive and hybrid workloads such as web servers and database operations. The results also show the potential of our approach to be used in real virtualized environments.
DOI: 10.1109/ipdps.2009.5160979
发表时间: 2009-05
期刊: 2009 IEEE International Symposium on Parallel & Distributed Processing
影响因子: --
作者:
Rong Ge;Xizhou Feng;K. Cameron
通讯作者: Rong Ge;Xizhou Feng;K. Cameron
DOI: 10.1109/mc.2007.443
发表时间: 2007-12-01
期刊: COMPUTER
影响因子: 2.2
作者:
Barroso, Luiz Andre;Hoelzle, Urs
通讯作者: Hoelzle, Urs
DOI: 10.1109/hcw.1999.765094
发表时间: 1999-04
期刊: Proceedings. Eighth Heterogeneous Computing Workshop (HCW'99)
影响因子: --
作者:
Muthucumaru Maheswaran;Shoukat Ali;H. Siegel;D. Hensgen;R. F. Freund
通讯作者: Muthucumaru Maheswaran;Shoukat Ali;H. Siegel;D. Hensgen;R. F. Freund
DOI: 10.1016/j.comnet.2009.06.008
发表时间: 2009-12
期刊: Comput. Networks
影响因子: --
作者:
T. Mukherjee;Ayan Banerjee;Georgios Varsamopoulos;S. Gupta;S. Rungta
通讯作者: T. Mukherjee;Ayan Banerjee;Georgios Varsamopoulos;S. Gupta;S. Rungta
DOI: 10.1007/978-3-642-14944-3_1
发表时间: 2009-09
期刊: --
影响因子: --
作者:
Congfeng Jiang;Jian Wan;Xianghua Xu;Yunfa Li;Xindong You
通讯作者: Congfeng Jiang;Jian Wan;Xianghua Xu;Yunfa Li;Xindong You