The development of the system for arc nordugrid based grid-computing organization using virtual environments of the docker platform

Olga Prila,Volodymyr Bazylevych,Oleksandr Sysa,Volodymyr Kazymyr

doi:10.15587/1729-4061.2021.249462

Abstract

The study of modern frameworks and means of using virtualization in a grid environment confirmed the relevance of the task of automated configuration of the environment for performing tasks in a grid environment. Setting up a task execution environment using virtualization requires the implementation of appropriate algorithms for scheduling tasks and distributed storage of images of virtual environments in a grid environment. Existing cloud infrastructure solutions to optimize the process of deploying virtual machines on computing resources do not have integration with the Arc Nordugrid middleware, which is widely used in grid infrastructures. An urgent task is to develop tools for scheduling tasks and placing images of virtual machines on the resources of the grid environment, taking into account the use of virtualization tools. The results of the implementation of services of the framework are presented that allow to design and perform computational tasks in a grid environment based on ARC Nordugrid using the virtual environment of the Docker platform. The presented results of the implementation of services for scheduling tasks in a grid environment using a virtual computing environment are based on the use of a scheduling algorithm based on the dynamic programming method. Evaluations of the effectiveness of the solutions developed on the basis of a complex of simulation models showed that the use of the proposed algorithm for scheduling and replicating virtual images in a grid environment can reduce the execution time of a computational task by 88 %. Such estimates need further refinement; it is predicted that planning efficiency will increase over time with an increase in the number of running tasks due to the redistribution of the storage of virtual images

Highlights

The use of distributed computing to perform large-scale tasks in various applied industries is relevant and cost-effective
The study is focused on an overview of solutions for using virtual images in a grid environment based on the ARC Nordugrid middleware [4], which is the most popular for building grid infrastructures, on the one hand
The results of the experiments showed that the use of the proposed algorithms for scheduling and replicating virtual images can reduce the execution time of a computational task in a grid environment by 88 % compared to the random scheduling of the developed approaches by the criterion of the execution time of computations Using the replication mechanism of virtual images, shown in Fig. 2 and formula (2), minimizes the cost of sending images of virtual machines

Summary

Introduction

The use of distributed computing to perform large-scale tasks in various applied industries is relevant and cost-effective. There is no significant incompatibility between the definitions of grid [2] and cloud [3], the main difference is in purpose and scale This confirms the possibility of integrating these technologies, which will allow to consider grid resources as distributed and heterogeneous resources for storing data and performing computations, and cloud computing as services deployed on these resources. This principle focuses on the infrastructure aspects of cloud computing, defined as IaaS (Infrastructure as a Service). The combination of grid and cloud computing concepts will effectively solve large-scale problems of various applied industries using distributed computing resources and the ability to flexibly configure the task execution environment

Literature review and problem statement

The aim and objectives of research

Findings

Conclusions