Virtual Machine Performance Analysis and Prediction

Virtual machine placement (VMP) technology is widely used in cloud computing systems. The existing VMP methods mainly aimed at improving the cloud resource utilization, such as load balancing among physical machines (PMs), but they may result in virtual machine (VM) performance degradation because of the great resource contention among VMs running on top of the same PM. In contract to existing VMP algorithms, this paper proposes a virtual machine (VM) Performance maximization and physical machine (PM) Load balancing Virtual Machine Placement method (PLVMP) in cloud, which tries to maximize VM performance and balance PM workload from both users’ and cloud providers’ perspectives. First, we study the relationship between PM workload and VM performance to train a new and improved VM performance model, which can predict VM performance more accurately and offer help to the following VMP. Second, we take VM performance maximization and PM workload balancing into account to formulate the VMP as an optimization problem, which tries to maximize VM performance for users and make load balancing among PMs for cloud providers. Third, we propose a greedy-based algorithm to solve the VMP problem efficiently. We then evaluate PLVMP with other VMP methods on CloudSim platform and a real OpenStack platform. The results show PLVMP can maximize the VM performance significantly and make a good load balancing among PMs.

In elastic cloud computing environment, multiple virtual machines may reside in the same physical machine for services consolidation. For the same residential guest domains or multi-tiered hosting services, the inter-domain communications are complex and frequent. However, traditional inter-domain communications are conducted through the virtual network interfaces of both sending and receiving virtual machines. Such TCP/IP networking communications involve lengthy communication path and frequent kernel interactions and thus downgrade the I/O performance of virtual machines. In this paper, we present an optimized inter-domain communication approach based on shared memory to improve the communication performance of multiple virtual machines residing in the same physical machine. In our approach, the sending data is shared in memory, not transferred via TCP/IP stack. The communication data are directly mapped into user space of the virtual machine and therefore it reduces useless system calls and context switches. The memory is shared via a customized shared device kernel module with bidirectional event channel resided in both communicating virtual machines. We use state flags in circular buffer to reduce wait and notify operations and thus reduce the system calls. Experiments show that our proposed approach can provide 5 time higher throughput and 2.5 times less latency compared to TCP/IP communication path.

Public Clouds are the backbone of the modern IT Industry. The modern tech start-ups to are heavily dependent on the Public Clouds as save the capital expenditure. Public Clouds offer a wide range of Virtual Infrastructure beginning from single core 0.25 GB RAM virtual machines to 128 cored 3904 GB RAM Virtual Servers aided with GPUs. Apart from costing, The performance of the virtual machines can impact on the services offered. The paper tries to analyse the performance of the Light virtual machines provided by the different cloud vendors and maps their ability to handle certain set of tasks. The prime objective is to compare the entry level virtual machines that are mostly used across the industry for the multiple purposes and find which is the efficient and productive. The systems under Test are the 1 GB RAM machines provided by the most popular Cloud service providers.

Purpose – The physical server transition to virtualized infrastructure server have encountered crucial problems such as server consolidation, virtual machine (VM) performance, workload density, total cost of ownership (TCO), and return on investments (ROIs). In order to solve the problems mentioned above, the purpose of this paper is to perform the analysis of virtualized cloud server together with shared storage as well as the estimation of consolidation ratio and TCO/ROI in server virtualization. Design/methodology/approach – This paper introduces five distinct virtualized cloud computing servers (VCCSs), and provides the appropriate assessment to five well-known hypervisors built in VCCSs. The methodology the authors proposed in this paper will gives people an insight into the problem of physical server transition to virtualized infrastructure server. Findings – As a matter of fact, VM performance seems almost to achieve the same level, but the estimation of VM density and TCO/ROI are totally different among hypervisors. As a result, the authors have the recommendation to choose the hypervisor ESX server if you need a scheme with higher ROI and lower TCO. Alternatively, Proxmox VE would be the second choice if you like to save the initial investment at first and own a pretty well management interface at console. Research limitations/implications – In the performance analysis, instead of ESX 5.0, the authors adopted ESXi 5.0 that is free software, its function is limited, and does not have the full functionality of ESX server, such as: distributed resource scheduling, high availability, consolidated backup, fault tolerance, and disaster recovery. Moreover, this paper do not discuss the security problem on VCCS which is related to access control and cryptograph in VMs to be explored in the further work. Practical implications – In the process of virtualizing the network, ESX/ESXi has restrictions on the brand of the physical network card, only certain network cards can be detected by the VM. For instance: Intel and Broadcom network cards. The newer versions of ESXi 5.0.0 and above now support parts of Realtek series (Realtek 8186, Realtek 8169, and Realtek 8111E). Originality/value – How to precisely assess the hypervisor for server/desktop virtualization is also of hard question needed to deal with it crisply before deploying new IT with VCCS on site. The authors have utilized the VMware calculator and developed an approach to server/desktop consolidation, virtualization performance, VM density, TCO, and ROIs. As a result, in this paper the authors conducted a comprehensive approach to analyze five well-known hypervisors and will give the recommendation for IT manager to choose a right solution for server virtualization.

In virtualized environments, the customers who purchase virtual machines (VMs) from a third-party cloud would expect that their VMs run in an isolated manner. However, the performance of a VM can be negatively affected by co-resident VMs. In this paper, the authors propose vExplorer, a distributed VM I/O performance measurement and analysis framework, where one can use a set of representative I/O operations to identify the I/O scheduling characteristics within a hypervisor, and potentially leverage this knowledge to carry out I/O based performance attacks to slow down the execution of the target VMs. The authors evaluate their prototype on both Xen and VMware platforms with four server benchmarks and show that vExplorer is practical and effective. The authors also conduct similar tests on Amazon’s EC2 platform and successfully slow down the performance of target VMs.

As the size of data increases and computation becomes complicated in fog computing environments, the need for highperformance computation is increasing. One of the most popular ways to improve the performance of a virtual machine (VM) is to allocate a graphic processing unit (GPU) to the VM for supporting general purpose computing on graphic processing unit (GPGPU) operations. The direct pass-through, often used for GPUs in VMs, is popular in the cloud because VMs can use the full functionality of the GPU and experience virtually no performance degradation owing to virtualization. Direct pass-through is very useful for improving the performance of VMs. However, since the GPU usage time is not considered in the VM scheduler that operates based on the central processing unit (CPU) usage time of the VM, the VM performing the GPGPU operation degrades the performance of other VMs. In this paper, we analyze the effect of the VM performing the GPGPU operation (GPGPU-intensive VM) on other VMs through experiments. Then, we propose a method to mitigate the performance degradation of other VMs by dynamically allocating the resource usage time of the VM and preventing the priority preemption of the GPGPU-intensive VM.

Cloud service providers offer virtual machines (VMs) as services to users over Internet. As VMs are running on physical machines (PMs), PM power consumption needs to be considered. Meanwhile, VMs running on the same PM share physical resources, and there exists great resource contention, which results in VM performance degradation. Therefore, how to place VMs to reduce PM power consumption and guarantee VM performance is still one major challenge. However, existing VMPs did not study VM performance degradation, so they could not guarantee VM performance. To solve the high power consumption and VMs performance degradation problems, this paper explores the balance between saving PM power and guaranteeing VM performance, and proposes a power-aware and performance-guaranteed VMP (PPVMP). First, we investigate the relationship between power consumption and CPU utilization to build a non-linear power model, which is helpful for the following VMP. Second, we construct VM performance models to present the VM performance degradation trend. Third, based on these models, we formulate VMP as a bi-objective optimization problem, which tries to minimize PM power consumption and guarantee VM performance. We then propose an algorithm based on ant colony optimization to solve it. Finally, the results show the efficiency of our algorithm.

Cloud computing manages system resources such as processing, storage, and networking by providing users with multiple virtual machines (VMs) as needed. It is one of the rapidly growing fields that come with huge computational power for scientific workloads. Currently, the scientific community is ready to work over the cloud as it is considered as a resource-rich paradigm. The traditional way of executing scientific workloads on cloud computing is by using virtual machines. However, the latest emerging concept of containerization is growing more rapidly and gained popularity because of its unique features. Containers are treated as lightweight as compared to virtual machines in cloud computing. In this regard, a few VMs/containers-associated problems of performance and throughput are encountered because of middleware technologies such as virtualization or containerization. In this paper, we introduce the configurations of VMs and containers for cloud-based scientific workloads in order to utilize the technologies to solve scientific problems and handle their workloads. This paper also tackles throughput and efficiency problems related to VMs and containers in the cloud environment and explores efficient resource provisioning by combining four unique methods: hyperthreading (HT), vCPU cores selection, vCPU affinity, and isolation of vCPUs. The HEPSCPEC06 benchmark suite is used to evaluate the throughput and efficiency of VMs and containers. The proposed solution is to implement four basic techniques to reduce the effect of virtualization and containerization. Additionally, these techniques are used to make virtual machines and containers more effective and powerful for scientific workloads. The results show that allowing hyperthreading, isolation of CPU cores, proper numbering, and allocation of vCPU cores can improve the throughput and performance of virtual machines and containers.

Resurgence of virtualization calls for suitable benchmark to validate the design of virtualization system. Among the virtual machines' performance, I/O especially disk I/O is the most critical one. Since I/O is a key factor that impacts virtual machine performance, this paper introduces a benchmark- vBench for disk I/O micro-performance evaluation of virtual machine. vBench is mainly consisted of serial disk I/O evaluation and parallel disk I/O evaluation. Since error during test is inevitable, for the purpose of error correction, we design an efficient approach which we runs the same workloads in two loops, then the execution times of two loops minus each other. The approach can correctly deal with loop overhead. To prevent compiler from optimizing the code and lead to the wrong execution time of workloads, vBench is embedded inline assembly code. vBench provides the performance evaluation for system call of disk I/O, application level disk I/O and parallel disk I/O. Disk I/O performance evaluation of vBench can measure disk I/O micro-performance of virtual machine in certain extreme conditions. Experiments show that the results of vBench are accurate and vBench can reflect the disk I/O performance of the virtual machines correctly. Therefore, vBench is more accurate, more reliable than the traditional benchmarks and more suitable for evaluating virtual machine disk I/O performance.

VM3: Measuring, modeling and managing VM shared resources

This paper explores the relationship between I/O scheduling in a virtual machine monitor (VMM) and performance of Map Reduce applications running on the virtual machines (VMs). Traditionally, Map Reduce applications running on the virtual machines perform worse than on the physical machines due to competing for I/O. In this paper, we discuss the effect of I/O scheduling on performance of Map Reduce running on VMs. We present two strategies to improve the I/O scheduling and evaluate the performance through experiments. The results show that the strategies could reduce the percentage of I/O waiting and time consuming of Map Reduce applications effectively.

Stochastic scheduling for variation-aware virtual machine placement in a cloud computing CPS

Scheduling policy in host operating system (OS) will have effect on the performance of Kernel-based Virtual Machine (KVM). This paper proposed an optimized scheduler policy to improve the performance of KVM. Firstly, a special process queue for virtual machine (VM) is added in the host OS, which is scheduled prior to normal process. Same time slices is given to each VM to make their load balanced. Secondly, the VM process queue is periodic sorted based on the remaining time slices of VM and a special state is added to identify I/O-intensive VM, which make sure that I/O-intensive VM is processed specially to receive a prior schedule opportunity. In the end, an experiment in KVM environment is designed and executed to show the effectiveness of this optimized scheduling policy.

We experimentally evaluate the performance overhead of the virtual environments VMware Player, QEMU, VirtualPC and VirtualBox on a dual-core machine. Firstly, we assess the performance of a Linux guest OS running on a virtual machine by separately benchmarking the CPU, file I/O and the network bandwidth. These values are compared to the performance achieved when applications are run on a Linux OS directly over the physical machine. Secondly, we measure the impact that a virtual machine running a volunteer @home project worker causes on a host OS. Results show that performance attainable on virtual machines depends simultaneously on the virtual machine software and on the application type, with CPU-bound applications much less impacted than IO-bound ones. Additionally, the performance impact on the host OS caused by a virtual machine using all the virtual CPU, ranges from 10% to 35%, depending on the virtual environment.

Cloud computing has become indispensable for meeting the rising demand for compute-intensive applications by providing cost-effective computational and storage resources. As reliance on cloud services increases, optimizing resource allocation is more critical than ever. This study introduces CloudProphet, an innovative machine learning-based framework designed to predict virtual machine (VM) performance in cloud environments. The approach begins with Dynamic Time Warping (DTW) to classify different types of applications based on their behavioral patterns. It further employs Pearson correlation to identify runtime metrics that are highly correlated with performance, ensuring that only the most relevant features are used in prediction models. These selected metrics are incorporated into three variations of deep learning models for evaluation: (1) an LSTM model without the use of DTW or feature selection, (2) an LSTM model with both DTW classification and selected features, and (3) a GRU model leveraging both DTW and highly correlated runtime indicators. Among these, the GRU-based approach demonstrates superior performance, achieving a remarkable 99.3% accuracy in predicting VM performance. The methodology is validated using a publicly available cloud workload dataset from GitHub and is further enhanced through real-time experimentation on live datasets to ensure practical applicability. The results highlight the robustness and accuracy of the proposed GRU model in forecasting both application types and VM behavior, making it a powerful tool for improving cloud resource management. By effectively anticipating workload demands and system performance, CloudProphet aids in reducing latency, minimizing resource wastage, and enhancing overall cloud service efficiency. This study underscores the value of combining time-series alignment techniques like DTW with correlation-based metric selection and advanced deep learning models such as GRU, ultimately offering a scalable and accurate solution for proactive and intelligent cloud performance prediction.