DocumentCode :
3171351
Title :
A Time Balanced Job Scheduling Using Divisibility Property for High Throughput Computing in Hybrid Peer-to-Peer Networks
Author :
Moon, Yong-Hyuk ; Nah, Jae-Hoon ; Youn, Chan-Hyun
Author_Institution :
Electron. & Telecommun. Res. Inst., Daejeon
fYear :
2008
fDate :
13-15 Oct. 2008
Firstpage :
200
Lastpage :
205
Abstract :
A tractable and flexible job scheduling algorithm is very significant in HTC because most mission critical job tends to not only occupy resources for a long time but also demands fast completion as possible. Therefore with divisibility property of job, we design a time balanced job scheduling algorithm to assign the time-constraint jobs to resources efficiently. In our simulation, this technical approach shows that each resource is fairly used in terms of time, and proposed scheme achieves the optimally minimized completion time of job processing, as compared with other conventional algorithms.
Keywords :
peer-to-peer computing; resource allocation; scheduling; divisibility property; high throughput computing; minimized completion time; peer-to-peer network; time balanced job scheduling algorithm; time constraint job; Computer architecture; Computer networks; Distributed computing; Job design; Multimedia computing; Peer to peer computing; Performance analysis; Processor scheduling; Scheduling algorithm; Throughput; Divisible Job; Job Scheduling; Peer-to-Peer;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Ubiquitous Multimedia Computing, 2008. UMC '08. International Symposium on
Conference_Location :
Hobart, ACT
Print_ISBN :
978-0-7695-3427-5
Type :
conf
DOI :
10.1109/UMC.2008.47
Filename :
4656544
Link To Document :
بازگشت