Melynda Eden, [email protected] (A paper written under the guidance ofProf. Raj Jain) DownloadIn virtualized environments, physical resources are partitioned into virtual resources so that they can beshared among individual virtual machines. This sharing of virtualized resources can reduce waste byincreasing used capacity thereby reducing the need for as many physical machines. Currently, there is anincreased desire to use virtualized systems in enterprise cloud computing in order to more efficiently utilizeresources thereby reducing costs. However, it is challenging to accurately model virtualized systems in orderto analyze performance issues. Traditional modeling methods that were developed for physical machines donot seamlessly work in virtualized environments. This paper explores the complexities associated withcorrectly modeling and measuring the performance of virtualized systems, and surveys various newapproaches in performance analysis for virtualization including recently developed benchmarks, newmodeling methodologies, and updated simulation techniques.Keywords: virtualized environments, performance modeling, virtualization benchmarks, simulationframework, cloud computing, hypervisors, VMware, Xen, server partitioning, Benchvm, VMmark,vConsolidate, VSCBenchmark, Performance Metric M, Linear Parameter Varying, Fuzzy models, ArtificialNeural Networks, probabilistic performance model, CloudSim1. Introduction1.1 Overview of Virtualization1.2 Terminology Challenges: Virtual Machine Monitor1.3 x86 Bare-Metal Hypervisors1.4 Introduction to Cloud Computing1.5 Cloud Computing Categories2. Issues with Performance Analysis in Virtualized Environments2.1. Hypervisor Differences2.2. Resource Interdependence2.3. Workload Variability2.4. Three Dimensions of Virtualization Modeling2.5. Modeling Framework Differences3. Virtualization Measurement Tools3.1. Benchvm benchmark3.2. VMmark benchmarkA Survey of Performance Modeling and Analysis Issues in Resource Man... http://www1.cse.wustl.edu/~jain/cse567-11/ftp/hypervsr/index.html1 of 13 5/4/2011 4:48 PM3.3. vConsolidate benchmark3.4. VSCBenchmark3.5. Performance Metric M4. Modeling and Simulation in Virtualized Environments4.1. Linear Parameter Varying (LPV)4.2. Fuzzy Models4.3. Artificial Neural Networks (ANN)4.4. Probabilistic Performance Model4.5. CloudSim5. SummaryReferencesList of AcronymsVirtualization is gaining popularity in enterprise cloud computing environments because of realized costsavings and better management that result from resource sharing and server consolidation. In an effort toimprove virtualized systems, researchers look to modeling and simulation techniques in order to pinpointperformance bottlenecks and resource contention. Many challenges unfold in the development of accurateperformance models, as virtualized environments add levels of complexity beyond models suitable for singlephysical machines [Benevenuto06]. This paper first defines virtualization, cloud computing and hypervisors;then investigates the multifaceted problem of performance analysis issues, and finally explores recentsolutions in measurement, modeling and simulation for virtualized environments.1.1 Overview of VirtualizationVirtualization allows for the partitioning of physical resources into virtualized containers. These containers,more commonly referred to as virtual machines, are functionally nothing more than sets of files that representvirtual hardware, executing in the context of a hypervisor. This virtual hardware provides a platform on whichan operating system and applications can be installed and can be configured to provide almost any servicethat a physical server typically provides [Ardagna10]. These services include email, database, hosting, file andprint, monitoring, management, and more. The virtualized environment consists of the underlying hardware,the hypervisor, the Virtual Machine Monitor (VMM), the virtual machines (VMs), and the operating systemsand applications installed on these virtual machines.A Survey of Performance Modeling and Analysis Issues in Resource Man... http://www1.cse.wustl.edu/~jain/cse567-11/ftp/hypervsr/index.html2 of 13 5/4/2011 4:48 PMFigure 1: Virtualized Environment Representation [Hostway11]Next, the VMM and hypervisor are discussed.1.2 Terminology Challenges: Virtual Machine MonitorThe components of the virtualized environment include the hypervisor and the VMM. Unfortunately,terminology for what goes on inside a hypervisor is not consistently applied, most notably with the concept ofthe VMM. Most resources agree that the VMM is involved with the scheduling of virtual resources on theirunderlying physical counterparts, however in some cases the VMM is referred to as the hypervisor itself whilein others this is merely a component of a hypervisor in a broader context. To avoid confusion, the VMM willnot be a specific point of focus in this paper, since its meaning would change based on context. The followingsection explores various hypervisors.1.3 x86 Bare-Metal HypervisorsHypervisors are an important component of virtualized environments. Hypervisors are programs that allowmultiple operating systems, known as guests, to run in virtual machines in an isolated fashion, and thus share asingle physical machine, or host. Many different hypervisors have been developed, a few of which are listedin the following table:Table 1: Common x86 Bare-Metal Hypervisors [Lu06] [VMware10]x86 Hypervisors Vendor Type Licensing PricingXenServer Citrix Para, Full Open Source Basic implementation is freeESXi VMware Para, Full Proprietary Basic implementation is freeHyper-V Microsoft Full Proprietary Requires OS purchaseKVM RedHat Full Open Source Basic implementation is freeSome x86 hypervisors can support both fully virtualized and para-virtualized operating systems. FullyA Survey of Performance Modeling and Analysis Issues in Resource Man... http://www1.cse.wustl.edu/~jain/cse567-11/ftp/hypervsr/index.html3 of 13 5/4/2011 4:48 PMvirtualized systems are unaware they are running in a virtualized environment, and no modifications to thecore operating system are required in order for them to function. Para-virtualized systems, on the other hand,are specifically modified to work in concert with the hypervisor. Prior to recent advances in CPUvirtualization technologies, para-virtualized systems enabled performance improvements because thehypervisor could grant a para-virtualized system direct access to the underlying hardware
View Full Document
Unlocking...