Research and Application of the Queuing Theory of the Virtualization Technology Resource Sharing Mode

Abstract Modern workloads often exceed the processing and I/O capabilities provided by resource virtualization, requiring direct access to the physical hardware in order to reduce latency and computing overhead. For computers interconnected in a cluser, access to remote hardware resources often requires facilitation both in hardware and specialized drivers with virtualization support. This limits the availability of resources to specific devices and drivers that are supported by the virtualization technology being used, as well as what the interconnection technology supports. For PCI Express (PCIe) clusters, we have previously proposed Device Lending as a solution for enabling direct low latency access to remote devices. The method has extremely low computing overhead, and does not require any application- or device-specific distribution mechanisms. Any PCIe device, such as network cards disks, and GPUs, can easily be shared among the connected hosts. In this work, we have extended our solution with support for a virtual machine (VM) hypervisor. Physical remote devices can be “passed through” to VM guests, enabling direct access to physical resources while still retaining the flexibility of virtualization. Additionally, we have also implemented multi-device support, enabling shortest-path peer-to-peer transfers between remote devices residing in different hosts.Our experimental results prove that multiple remote devices can be used, achieving bandwidth and latency close to native PCIe, and without requiring any additional support in device drivers. I/O intensive workloads run seamlessly using both local and remote resources. With our added VM and multi-device support, Device Lending offers highly customizable configurations of remote devices that can be dynamically reassigned and shared to optimize resource utilization, thus enabling a flexible composable I/O infrastructure for VMs as well as bare-metal machines.

Download Full-text

Lower bound for average delay in unblocked random access algorithm with orthogonal preambles

Information and Control Systems ◽

10.31799/1684-8853-2020-3-79-85 ◽

2020 ◽

pp. 79-85

Author(s):

Artem Burkov ◽

Seva Shneer ◽

Andrey Turlikov

Keyword(s):

Lower Bound ◽

Resource Sharing ◽

Queuing Theory ◽

Multiple Access ◽

System Analysis ◽

Random Access ◽

Arrival Rate ◽

High Energy ◽

Average Delay ◽

Closed Expression

Introduction: Currently, the first versions of 5G communication standard networks are being deployed and discussions are underway on the further development of cellular networks and the transition to the 6G standard. The work of the currently popular idea of the Internet of Things (IoT) is supposed to be in the framework of a Massive Machine-Type Communications scenario, which has a number of requirements for operation characteristics: very high energy efficiency, relatively low delay and fairly reliable communication. It is assumed that random multiple access procedures are used, since, due to the nature of the traffic, it is impossible to develop a channel resource sharing policy. To increase the efficiency of random access, a class of unblocked algorithms using orthogonal preambles can be used. Purpose: to calculate the lower bound of the average delay for the class of unblocked random multiple access algorithms using orthogonal preambles. Methods: system analysis, a theory of random processes, queuing theory, and simulation. Results: A model of a system with a potentially unlimited number of users who use random unblocked access to transmit data over a common communication channel using orthogonal preambles is proposed. A closed expression is obtained for calculating the lower bound of the average delay in such a system depending on the intensity of the input arrival rate. The limit value of the intensity of the input arrival rate to which the system operates stably is determined. Shown are the results of simulation with respect to the obtained bound. Practical relevance: the obtained boundary allows us to estimate the lower average delay in the described class of algorithms. Its application allows us to determine the possibility of using the considered class of algorithms from the point of view of limitations on the average delay at the stage of designing random multiple access systems.

Download Full-text

Construction on Virtualized Environment for Digital Library Based on Cloud Computing Technology

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.687-691.3019 ◽

2014 ◽

Vol 687-691 ◽

pp. 3019-3022 ◽

Cited By ~ 1

Author(s):

Jun Jun Liu

Keyword(s):

Cloud Computing ◽

Digital Library ◽

Resource Sharing ◽

Virtual Machines ◽

Computing Environment ◽

Computing Technology ◽

Cloud Computing Environment ◽

Key Technology ◽

Virtualization Technology

Cloud computing technology is emerging technology in the field of information technology, and its technical advantage has brought new opportunities and challenges for the development and service of digital library in the Internet era. Virtualization is the key technology of cloud computing, and the paper discusses the virtualization of digital library in the cloud computing environment from technical level. Firstly, the paper introduced cloud computing and virtualization technology; then created a virtualized environment for digital library based on the cloud computing technology, and described the function of various levels; finally, the capacity of virtual machines appointment scheduling can be calculated according to formulas. The paper has great significance in enhancing the efficiency and quality of library service, constructing resource sharing system of digital library.

Download Full-text

Mathematical Model of the Consumption of Computer Resources During Their Incomplete Release

Bulletin of Science and Practice ◽

10.33619/2414-2948/55/01 ◽

2020 ◽

Vol 6 (6) ◽

pp. 10-14

Author(s):

M. Nosova ◽

V. Sadykov

Keyword(s):

Mathematical Model ◽

Virtual Machine ◽

Method Of Moments ◽

Service Time ◽

Queuing Theory ◽

Incoming Flow ◽

Performance Parameters ◽

Virtualization Technology ◽

The Mathematical Model ◽

Computer Resources

The article develops a mathematical model of the process of consuming computing resources when they are incompletely released using virtualization technology. The mathematical model is presented in the form of a queuing system with an unlimited number of devices, with a simple incoming flow of applications and exponential service time for them on the devices. The study of the model is performed by the methods of queuing theory. Using the method of moments, the main probabilistic characteristics of the amount of free resources are found mathematical expectation and variance. The proposed mathematical model of the process of consuming computing resources allows us to evaluate and predict the process of changing the amount of free resources of a virtual machine in time and analyze its performance parameters.

Download Full-text

A Virtualized Target Queuing Balanced Model Using Vmax/M/G-Load(Min)/Cache-P2λM for Reducing Queuing Time Expectation of Customer Delay Tolerance

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2020.9448 ◽

2020 ◽

Vol 17 (12) ◽

pp. 5520-5527

Author(s):

A. Andrew Michael ◽

M. Thiagarajan

Keyword(s):

Resource Sharing ◽

Queuing Theory ◽

Service Performance ◽

Late Response ◽

Distributed Resources ◽

Delay Tolerance ◽

Model Complex ◽

Balanced Model ◽

Load Balancer ◽

Customer Delay

Queuing theory is a formal mathematical model of late response arrival of customer waiting in various access services, accepting processes management as a whole field. Often multiple server sorting can be used to estimate the number of servers and service rates be high due too lacking of time, with an average delay sequence in the analysis. Using these sequence models to read more than one sequence during execution approximates system sorting performance. To resolve this problem we modulated the distributed process into Virtualized Target Queuing Balanced Model (VTQBM) using Vmax/M/G-Load (Min)/Cache-P2λM for reducing queuing time expectation of customer delay tolerance. The Virtual Resource queuing System is optimized with fork-join queue by creating single to multimodal service performance using target request load balancer in a shared distribution mode. Sorting the request buffer cache is created based on Customer Request Arrival Rate (CRAR) and resource output preferred to check with target rule waiting in the Load balancer. To improve the use of model complex virtual resource sharing shared with customer arrival to Cache Target Load Allocator (CTLA) on queuing distributed resources, This fork joiner target the service performance to reduce the customer waiting time in queuing and produce outputs can achieve a different parameter input transformation on queuing theory.

Download Full-text

Qingdao Integration Practice of E-Cloud and Cloud Computing Disaster Recovery

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.519-520.450 ◽

2014 ◽

Vol 519-520 ◽

pp. 450-457

Author(s):

Yan Zhang ◽

Zhao Jing Wang ◽

Xue Bing Dai ◽

Zhi Qiang Wei ◽

Mei Ling Li

Keyword(s):

Cloud Computing ◽

Resource Sharing ◽

Cloud Storage ◽

Comprehensive Analysis ◽

Data Synchronization ◽

Cloud Environment ◽

Storage Virtualization ◽

Virtualization Technology ◽

Office Systems ◽

Construction Practice

The comprehensive analysis of Qingdao Development of e-government is presented in this paper. E-government is to resolve the current construction of the "resource sharing" and "business disaster" problem.By using the structure of the two three-center model for Qingdao,an e-government platform is built for cloud computing resources. Information resources for e-government integration provides a unified cloud environment, and the use of cloud storage virtualization technology to solve more than 120 kilometers of remote data synchronization and application-level redundant disaster problems, combined with the "Hong Jin e-office systems business". The testing and construction practice has proved the feasibility of the model.

Download Full-text