Narrow Results

The emerging cloud computing model has recently gained a lot of interest both from commercial companies and from the research community. XtreemOS is a distributed operating system for large-scale wide-area dynamic infrastructures spanning multiple administrative domains. XtreemOS, which is based on the Linux operating system, has been designed as a Grid operating system providing native support for virtual organizations. In this paper, we discuss the positioning of XtreemOS technologies with regard to cloud computing. More specifically, we investigate a scenario where XtreemOS could help users take full advantage of clouds in a global environment including their own resources and cloud resources. We also discuss how the XtreemOS system could be used by cloud service providers to manage their underlying infrastructure. This study shows that the XtreemOS distributed operating system is a highly relevant technology in the new era of cloud computing where future clouds seamlessly span multiple bare hardware providers and where customers extend their IT infrastructure by provisioning resources from different cloud service providers.

In a large multiprocessor server platform using multicore chips, the scheduler often migrates a thread or process, in order to achieve better load balancing or ensure fairness among competing scheduling entities. Each migration incurs a severe performance impact from the loss of cache and Translation Lookaside Buffer (TLB) footprints and subsequent higher cache misses and page walks. Such impact is likely to be more severe in virtualized environments, where high over-subscription of CPUs is very common for server consolidation workloads or virtual desktop infrastructure deployment, causing frequent migrations and context switches. We demonstrate the performance benefit of preserving a portion of L2 cache—in particular, MRU cache lines—and warming the destination L2 cache by prefetching those cache lines under different migration scenarios. We observed a 1.5-27% reduction in CPI (cycles per instruction) following a migration. We also study the effectiveness of preserving TLB entries over a context switch or migration.

Virtualization technology, as the technical support for cloud computing, frees users from the limitations of hardware resources. Dynamic migration technology enables virtual machines to be moved across hosts, and services running on the virtual machines are basically uninterrupted during the migration process, which greatly facilitates the maintenance work in the data center. However, dynamic migration needs to transmit a large amount of repeated data. In order to improve the migration efficiency, this paper conducts the following research on the original pre-copy algorithm. First, we introduce a high dirty page determination algorithm based on the locality principle to classify memory pages and propose an improved memory migration pre-copy algorithm on this basis. Second, in order to solve the problem that the pre-copy algorithm cannot converge under a high load, an improved VM downtime determination algorithm is proposed. Third, the paper also introduces the LZ4 compression algorithm to further optimize the memory migration process. Finally, this paper implements the above optimization scheme on a KVM platform and tests its performance. It is compared with the native pre-copy algorithm and Three-Phase Optimization algorithm (TPO). The result shows that the optimized scheme significantly reduces the total migration time and downtime.

Kernel security is of paramount importance in computer systems. As the number of vulnerabilities in the kernel continues to grow, computer systems security risks are increasing. To prevent the kernel interrupt stack from being attacked, researchers provide discussion over complete hypervisor supervision and kernel co-layer security domain techniques. Complete hypervisor supervision brings a heavy overhead and co-layer security domain techniques cannot achieve privilege-level isolation. We focus on memory-based security threats in kernel security vulnerabilities, protecting the kernel at a higher level by using virtualization technology. Compared with the existing work, our implementation method achieves a small performance loss to protect the interrupt stack. We have implemented our system on openEuler operating systems and Phytium processors. Although the deployment of protection code will result in increased kernel interrupt latency and processor overhead, experimental verification shows that the overall system overhead is acceptable.

Satoh and Taniguchi introduced the $n$-writhe $J_n$ for each non-zero integer $n$, which is an invariant for virtual knots. The $n$-writhes give the coefficients of some polynomial invariants for virtual knots including the index polynomial, the odd writhe polynomial and the affine index polynomial. It is obvious that the virtualization of a real crossing is an unknotting operation for virtual knots. The values of $n$-writhes changed by some local moves are calculated. However for the virtualization, it is unknown. In this paper, we show that for any given non-zero integer $n$ and any given integer $N$, there exists a virtual knot whose unknotting number by the virtualization is one and the value of the $n$-writhe equals $N$. Namely, the virtualization of a real crossing changes the value of $n$-writhe by any given integer $N$.

We introduce some polynomial invariants for flat virtual links which are similar to the Jones–Kauffman polynomial, the Miyazawa polynomial and the arrow polynomial for virtual link diagrams, and we give several properties and examples.

An unknotting operation is a local move such that any knot diagram can be transformed into a diagram of the trivial knot by a finite sequence of these operations plus some Reidemeister moves. It is known that for all $n\ge 2$ the $H(n)$-move is an unknotting operation for classical knots and links. In this paper, we extend the classical unknotting operation $H(n)$-move to virtual knots and links. Virtualization and forbidden move are well-known unknotting operations for virtual knots and links. We also show that virtualization and forbidden move can be realized by a finite sequence of generalized Reidemeister moves and $H(n)$-moves.

The hypercubic family of interconnection networks, encompassing the hypercube and its derivatives and variants, has a wide range of applications in parallel processing. Various problems in general complex networks can be addressed by choosing a hypercubic network as a skeleton. In this paper, we provide insight into why hypercubic networks are suitable as network skeletons and discuss a mapping scheme to take advantage of the symmetry of such networks for developing efficient algorithms.

Cloud computing is the emerging trend that provides a variety of applications to promote corporate business across the globe over the internet. Cloud computing offers services to deploy the infrastructure in the specified environment. Different computing techniques are used to manipulate the cloud services. One of the most eminent techniques is Virtual Machine (VM) Migration which enables to set up the compute resources and storages from one to another host without detaching the application or client. Virtual Machine Migration helpful in minimizing energy dissipation, load balancing, and fault management. It is based on the migration and down time with live and non-live categorization. Live VM Migration in data hubs has potential to minimize energy consumption. The proposed Optimized Energy Model Virtual Machine Algorithm is used to calculate each host in the data hub, while the energy consumed by the system in each hour is increasing exponentially then the proposed algorithm is also responsible for reorders the node and the minimizing the energy after reordering.

Cyber-physical systems (CPS) tightly integrate cyber and physical components and transcend discrete and continuous domains. It is greatly desired that the synergy between cyber and physical components of CPS is explored even before the complete system is put together. Virtualization has potential to play a significant role in exploring such synergy. In this paper, we propose a CPS virtualization approach based on the integration of virtual machine and physical component emulator. It enables real software, virtual hardware, and virtual physical components to execute in a holistic virtual execution environment. We have implemented this approach using QEMU as the virtual machine and Matlab/Simulink as the physical component emulator, respectively. To achieve high-fidelity between the real system and its virtualization, we have developed a strategy for synchronizing the virtual machine and the physical component emulator. To evaluate our approach, we have successfully applied it to real-world control systems. Experiments results have shown that our approach achieves high-fidelity in capturing dynamic behaviors of the entire system. This approach is promising in enabling early development of cyber components of CPS and early exploration of the synergy of cyber and physical components.

Desktop Virtualization is an essential problem in cloud manufacturing to make full use of shared resources so as to meet the practical application requirements. In this paper, an efficient virtualization solution for desktop transferring is presented for sharing resources. Our strategy is not limited to transfer desktops between virtual machines (VMs), transmission between virtual and physical machines is also achieved. A three-layer systemic structure based on web environment is proposed in the study. We employ the application program library Libvirt and kernel-based virtual machine (KVM) technique to manage VMs with dynamic customization scheme, which gains better virtualization performance. Moreover, we present two different schemes for desktop graphics transferring. One is based on the transport protocol virtual network computing (VNC), and the other adopts the simple protocol for independent computing environment (SPICE), which both achieve more satisfactory results. The validity of our scheme is demonstrated on some experimental results and systemic qualitative evaluation is also provided.

Cloud computing brings incipient transmutations in different fields of life and consists of different characteristics and virtualization is one of them. Virtual machine (VM) is one of the main elements of virtualization. VM is a process in which physical server changes into the virtual machine and works as a physical server. When a user sends data or request for data in cloud data center, a situation can occur that may cause the virtual machines to underload data or overload data. The aforementioned situation can lead to failure of the system or delay the user task. Therefore, appropriate load balancing techniques are required to surmount the above two mentioned problems. Load balancing is a technique utilized in cloud computing for management of the resource by a condition such that a maximum throughput is achieved with slightest reaction time and additionally dividing the traffic between different servers or VM so that it can get data without any delay. For the amelioration of load balancing technique in this study, a novel technique is used which is coalescence of BAT and ABC algorithms both of which are nature-inspired algorithms. When the ABC algorithm local search section changes with BAT algorithm local search section, a second modification takes place in the fitness function of BAT algorithm. The proposed technique is known as HBATAABC algorithm. The novel technique implemented by utilizing transfer strategy policy in VM improves the performance of data allocation system of VM in the cloud data center. To check the performance of the proposed algorithm, three main parameters are used which are network average time, network stability and throughput. The performance of the proposed novel technique is verified and tested with the help of cloudsim simulator. The result shows that the suggested modified algorithm increases performance by 1.30% of network average time, network stability and throughput as compared with BAT algorithm, ABC algorithm and RRA algorithm. Nevertheless, the proposed algorithm is more precise and expeditious as compared with the three models.

In the future, the data center of the network is urgently needed for the support of a router device which has the security isolation and virtual nature. The virtual router based on the security isolation can construct a virtual network on a physical network, which has the ability to improve the security of data transmission and the ability to prevent the transmission from the virus. Compared with the traditional router, the security isolation based on the virtual router has the characteristics of security isolation and virtualization.

Currently, there is an increasing dependence on the educational administration system in colleges and universities. As the educational administration system supports the school teaching resources, the massive access pressure during course selection is a problem that is becoming increasingly prominent. We propose the construction of a cloud platform to pool all physical servers and the setting up of virtual machines. During course selection, the cloud platform can increase or decrease the number of virtual machines automatically through the load elastic flexible configuration and the monitoring of parameters such as the number of requests and CPU usage. This greatly improves the efficiency of course selectionand student satisfaction while significantly reducing server hardware expenditure and raising the efficiency of maintenance and operations.

With the development of the dynamic analysis algorithm and behavior detection method, it has become increasingly important to design an effective system to manage and control behavior detecting resources. This paper introduces a design and architecture of a resource management system to manage the virtual environment for malware behavior detection, including its resource management algorithm, network design, system architecture, et al. The design introduced here focuses on the high standards placed on performance, reliability and scalability of malware behavior detection system. From the results obtained from both experimental simulations and real world implementation, this system has proved to be competent and fulfil those requirements.

Virtual machine technique is employed to improve system utilization and energy efficiency. However, isolation effect of virtualization imposes challenges to power management. A multi-level power behavior statistic framework is introduced to support power profiling of virtual device, virtual machine and host. Power management mechanisms are virtualized to map power management operations between virtual device and physical device. The power consumption of a virtual device is virtualized according to its performance share from the physical device. The experiments demonstrated that our power management virtualization solution has negligible decline of system performance.