Measuring performance degradation of virtual machines based on the Bayesian network with hidden variables
Measuring performance degradation of virtual machines based on the Bayesian network with hidden variables
复制标题
基于隐变量贝叶斯网络测量虚拟机性能下降
DOI：
10.1002/dac.3732
复制
发表时间：
2018
影响因子：
2.1
通讯作者：
Zhang Jixian
中科院分区：
文献类型：
--
作者：
Hao Jia;Zhang Binbin;Yue Kun;Wu Hao;Zhang Jixian
在虚拟环境中，共享同一物理主机的多个虚拟机(VM)容易受到资源竞争的影响，这可能会导致VM之间的性能干扰，从而导致VM性能下降。本文根据虚拟机运行时环境的特点，重点测量了CPU、内存、I/O以及由于性能干扰导致的虚拟机整体性能下降。为此，我们采用贝叶斯网络(BN)作为不确定性表示和推理的框架，并构造了一个带有隐藏变量的VM属性-性能BN(VPBN)，这些变量分别表示CPU、内存和I/O的不可观测的性能下降。然后，我们给出了利用VPBN的概率推理来度量VM性能下降的方法。实验结果表明，该方法具有较高的精度和效率。
In the virtualized environment, multiple virtual machines (VMs) sharing the same physical host are vulnerable to resource competition, which may cause performance interference among VMs and thus lead to VM performance degradation. This paper focuses on measuring CPU, memory, I/O, and the overall VM performance degradation caused by the performance interference according to the properties in the runtime environment of VMs. To this end, we adopt Bayesian network (BN), as the framework for uncertainty representation and inference, and construct a VM property‐performance BN (VPBN) with hidden variables, which represent the unobserved performance degradation of CPU, memory, and I/O, respectively. Then, we present the method to measure performance degradation of VMs by probabilistic inferences with the VPBN. Experimental results show the accuracy and efficiency of our method.