Scheduling Policy Optimization in Kernel-Based Virtual Machine

In Cloud Computing, the topic about hypervisors is the key research as it concerns management of physical resources and deployment virtual machines. Currently, modern hypervisors obtain new features to increase their performance under different architectures. Cloud data centers start to adopt techniques for power consumption management that can reduce the power, and meanwhile maintain the performance. In this paper, we investigate on the power consumption and performance issues concerning memory and disk I/O, comparing two open-source virtualization platforms: Xen and Kernel-based Virtual Machine (KVM). We compare Xen with raw disk and KVM's different disk I/O types, including the write through, write back and none modes with the block sizes of 8, 64 and 128 KB, relating to web downloading and database query workload. The results show that the KVM write back mode can reduce about a half (56%) of power consumption comparing to Xen with raw disk when writing files and the KVM write through mode with page cache can reduce power consumption to about 3% of that consumed by Xen with raw disk when reading files. In case of performance, the speed of KVM when page cache can increase to about 26 times faster than the speed of Xen with raw disk. In case of memory, the VM's power consumption is rather steady even when the memory usage varies.

SummaryVirtual desktop infrastructure (VDI) solutions seek to provide a satisfactory user experience at the client side when accessing remote desktop applications, even from mobile devices with limited capabilities. This paper presents a new approach, improving on previous work by the authors, in which a combination of Virtual Network Computing (VNC) and streaming protocols allowed efficient remote web access to virtualized applications within a cloud architecture. The new approach simplifies virtual machine templates, from which virtual machine instances are deployed, by centralizing software modules, greatly simplifying their management. Our new contribution consists of an integrated solution with specific WebM video encoding modules in charge of application visual output processing, an Hypertext Transfer Protocol (HTTP) streaming server, and a VNC server. The solution can be installed in the hypervisor of the host machines instead of replicating the servers and modules throughout the guest (virtual) machines that run the virtualized applications. Consequently, their implementations are unique and independent of the operating system of the virtual machines. In short, it is not necessary to provide different implementations for different operating systems, which reduces the complexity of virtual machine templates and greatly simplies platform management. To demonstrate our solution, we have modified the Quick Emulator (QEMU)‐Kernel‐based Virtual Machine (KVM) hypervisor source code accordingly. We also present qualitative and quantitative analyses that demonstrate that the new approach is advantageous in terms of software management and quality of experience, compared with our previous work and other well‐known thin clients, contributing to the enhancement of VDI systems. Copyright © 2015 John Wiley & Sons, Ltd.

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.

Keeping a high-precision time base in cloud clusters is still a big challenge, even using the Precision Time Protocol version 2 (PTPv2) specified in IEEE 1588. One of the main factors on this issue is that too many uncertainties in the network path from the master clock to the slave one, which is likely residing on the Kernel-based Virtual Machine (KVM). The Transparent Clock (TC) of PTPv2 may be useful to solve this issue. However, at present the network I/O path in the virtual machine environment has not been considered in such works, which seriously affect the performance of the synchronization accuracy. In this work, we make improvements in the kernel network stack to manipulate the PTP frames to record the residence time for the path from the physical machine to the virtual machine, making its network I/O architecture an End-to-End Transparent Clock (E2E TC). Although the idea of E2E TC for more accurate synchronization is not new, there is no such implementation publicized for the virtualized environment, as far as we know. The proposed mechanism is specifically tailored to make latency corrections for the neglected routing path between the physical Network Interface Card (NIC) and the virtual machines. Extensive experiments and tests show that this approach makes quite significant improvement of about 50%.

Cloud platforms often take advantage of virtualization technology and make their actual hosts virtualized. As network attack events occur frequently, providing system security in a virtualized environment is the focus of this study. We have designed and implemented a lightweight network-based intrusion prevention system (IPS) named VMM-IPS for the virtual machine (VM) execution environment. To ensure the system safety of VMs and the host system at the same time, VMM-IPS is operated in the Linux kernel of the host system and co-located with the Kernel-based Virtual Machine that turns Linux kernel into a hypervisor. As packets enter the system, no matter destined to VMs or passing through the host, they are detected by VMM-IPS. Unlike user-level IPS that needs switching protection domain and copying packets to user buffer for inspection, VMM-IPS is more efficient because of the capability to perform in-place packet inspection. It adopts signature-based detection and is implemented with the multiple-pattern search algorithm AC-BM for efficient string matching. Besides, VMM-IPS can protect the system against attacks using packet splitting and reassembly to evade introduction detection system (IDS). The experimental results demonstrate VMM-IPS can achieve system safety effectively and efficiently.

In Recent years embedded world has been undergoing a shift from traditional single-core processors to processors with multiple cores. However, this shift poses a challenge of adapting legacy uniprocessor-oriented real-time operating system (RTOS) to exploit the capability of multi-core processor. In addition, some embedded systems are inevitably going towards the direction of integrating real-time with off-the-shelf time-sharing system, as the combination of the two has the potential to provide not only timely and deterministic response but also a large application base. Virtualization technology, which ensures strong isolation between virtual machines, is therefore a promising solution to above mentioned issues. However, there remains a concern regarding the responsiveness of the RTOS running on top of a virtual machine. In this paper we propose an embedded real-time virtualization architecture based on Kernel-Based Virtual Machine (KVM), in which VxWorks and Linux are combined together. We then analyze and evaluate how KVM influences the interrupt-response times of VxWorks as a guest operating system. By applying several real-time performance tuning methods on the host Linux, we will show that sub-millisecond interrupt response latency can be achieved on the guest VxWorks.

Graphics processing Units (GPUs), which originally designed for computer graphics applications, have been widely adopted to general purpose computing in many domains owing to their massive computational power. In the era of cloud computing, GPU virtualization becomes an important technique for the better management of GPUs in data centers. However, most of current solutions are not full virtualization. They either need to modify the guest drivers or libraries, or restrict the hardware sharing capability. The only full GPU virtualization solution is GPUvm, which however can only be executed on Xen hypervisors. In this paper, we present a full GPU virtualization solution on KVM (Kernel-based Virtual Machine), called G-KVM. Our work is not merely a direct porting of GPUvm to KVM, since Xen and KVM have fundamental differences in their system architectures. Two major changes of G-KVM are aggregator and QEMU device model. The experiments show that G-KVM has better performance for MMIO operations than GPUvm on Xen hypervisor. For the compute-extensive experiments, execution time of G-KVM can achieve nearly 82% of native performance, which is similar to GPUvm. The performance scaling experiment shows that the performance of single machine with G-KVM can be scaled up to multiple virtual machines.

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.

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.

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.

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.

Modern applications running on cloud data centers often consume a large amount of memory and their memory demands can vary during execution. Dynamic memory allocation is a necessity for high memory utilization. For a large dataset application, using hugepages instead of regular 4KB pages can efficiently reduce memory access and memory management overhead and improve overall performance. Virtualization, which is widely applied in data centers for server consolidation, brings new challenges to manage memory dynamically and effectively, especially for hugepages. In a virtualized system, ballooning is a popular mechanism used to dynamically adjust memory allocations for co-located virtual machines. We observe that the current Linux Kernel-Based Virtual Machine (KVM) does not support huge page ballooning. An application that can benefit from hugepages often loses its performance advantage when the guest OS experiences memory ballooning. This paper presents design and implementation of HUB, a HUgepage Ballooning mechanism in KVM which can dispatch memory in the granularity of hugepages. The experimental results show that our approach significantly reduces TLB misses and improves the overall performance for those applications with large memory demand.

Virtualization technology promotes the development of cloud computing technology, and cloud service providers provide many virtual machines with different configurations. It is becoming more and more important to analyze the performance of virtual machines based on the characteristics of the workload. This paper analyzes the performance of memory-intensive, compute-intensive and I/O intensive workloads running in virtual machines with different sizes. In order to avoid excessive overhead when comparing the performance of virtual machines, this paper proposes a performance prediction method for virtual machines based on the results of micro-benchmarks. Finally, this paper proposes the concept of virtual machine consistency. If a workload has the same performance in two virtual machines, we call the performance of the two virtual machines consistent with respect to this workload.

In cloud computing, virtualization is accomplished by equipping with a virtual switch to connect between physical machine and virtual machine. The virtual switch which is usually written coded in software provides a flexible configuration and management. In this paper, we use kernel based virtual machine (KVM) to deploy the virtual server cluster and apply Open vSwitch for the virtualized network environment. Our platform provides service with single entry point so that the virtual server cluster is fully transparent to end users. The implementation of load balancing is carried out by using Open vSwitch with an Openflow controller. Openflow controller dynamically manages the flow table in Open vSwitch through secure channel by Openflow protocol. With the platform, we can also deploy a virtual cluster across two Local Area Networks (LANs) through Generic Routing Encapsulation tunnel protocol. Upon a request, the Open vSwitch forwards the traffic to the virtual server cluster upon the loading policy to achieve load balancing.