Abstract:

Cluster computing is becoming increasingly practical for high performance computing research and development. A computer cluster is a set of connected computers that work together so that, they can be viewed as a single system. Clusters o®er a scalable means of linking computers together to provide an expansive environment for hosting enterprise applications. As the number of nodes in cluster con¯gurations grows, the cluster administration becomes more challenging. We need to study the challenges of cluster management and to provide a solution. To have an e®ective cluster management we need to have an e®ective task scheduling algorithm. With the explosive growth of information, the demand on computing is sharply increasing. Due to a large number of computing tasks, the scheduling algorithm is an important part of cluster computing and has a great in°uence on the quality of claster service. In cluster computing, some large tasks may occupy too many resources and some small tasks may wait for a long time based on First-In-First-Out (FIFO) scheduling algorithm. This paper provides an overview of an improved scheduling algorithm that shortens the execution time of tasks and increases the resource utilization.
; В статье вводится улучшенную модель алгоритма планирования, которая уменьшает время выполнения задач и увеличивает использование ресурсов системы. В вышеупомянутом алгоритме каждая задача характеризуется параметрами ((3, и), где °-количество узлов кластера, необходимых для выполнения этой задачи, (3-максимальное время, необходимое для выполнения этой задачи, а и -максимальное время, что эта задача может подождать до назначения для запуска.

Publisher:

Improved Model of The Scheduling Algorithm

Identifier:

oai:noad.sci.am:135958

DOI:

10.51408/1963-0027

ISSN:

0131-4645

Language:

English ; Английский

Journal or Publication Title:

Mathematical Problems of Computer Science

Volume:

50

Additional Information:

artvardanyan@asnet.am

Affiliation:

Institute for Informatics and Automation Problems

Country:

Armenia

Year:

2018

Indexing:

ASCI