IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Analysis of Frequently Failing Tasks and Rescheduling Strategy in the Cloud System

Analysis of Frequently Failing Tasks and Rescheduling Strategy in the Cloud System
View Sample PDF
Author(s): Hongyan Tang (School of Software and Microelectronics, Peking University, Beijing, China), Ying Li (National Engineering Center of Software Engineering, Peking University, Beijing, China), Tong Jia (School of Software and Microelectronics, Peking University, Beijing, China), Xiaoyong Yuan (Department of Computer and Information Science and Engineering, University of Florida, Florida, USA)and Zhonghai Wu (National Engineering Center of Software Engineering, Peking University, Beijing, China)
Copyright: 2018
Volume: 9
Issue: 1
Pages: 23
Source title: International Journal of Distributed Systems and Technologies (IJDST)
Editor(s)-in-Chief: Nik Bessis (Edge Hill University, UK)
DOI: 10.4018/IJDST.2018010102

Purchase

View Analysis of Frequently Failing Tasks and Rescheduling Strategy in the Cloud System on the publisher's website for pricing and purchasing information.

Abstract

To better understand task failures in cloud computing systems, the authors analyze failure frequency of tasks based on Google cluster dataset, and find some frequently failing tasks that suffer from long-term failures and repeated rescheduling, which are called killer tasks as they can be a big concern of cloud systems. Hence there is a need to analyze killer tasks thoroughly and recognize them precisely. In this article, the authors first investigate resource usage pattern of killer tasks and analyze rescheduling strategies of killer tasks in Google cluster to find that repeated rescheduling causes large amount of resource wasting. Based on the above observations, they then propose an online killer task recognition service to recognize killer tasks at the very early stage of their occurrence so as to avoid unnecessary resource wasting. The experiment results show that the proposed service performs a 93.6% accuracy in recognizing killer tasks with an 87% timing advance and 86.6% resource saving for the cloud system averagely.

Related Content

Sherin Eliyas, P. Ranjana. © 2024. 10 pages.
Mei Gong, Bingli Mo. © 2024. 15 pages.
Honglong Xu, Zhonghao Liang, Kaide Huang, Guoshun Huang, Yan He. © 2024. 17 pages.
Jialan Sun. © 2024. 21 pages.
Shuang Li, Xiaoguo Yao. © 2024. 16 pages.
Sunil Kumar, Rashmi Mishra, Tanvi Jain, Achyut Shankar. © 2024. 12 pages.
Qian He, Ke Wang. © 2024. 19 pages.
Body Bottom