loading...
A CoS-enabled Request Scheduling Policy
Hong Kong, China October 16-October 20
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/EDOCW.2006.610th IEEE International Enterprise Di ...
 This Article 
 
PDF
HTML
 
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Yubin Yang, Xi?an Jiaotong University, Xi?an Shaanxi 710049, China
Yazhe Tang, Xi?an Jiaotong University, Xi?an Shaanxi 710049, China
Ming Zhao, Xi?an Jiaotong University, Xi?an Shaanxi 710049, China
Lei Yao, Xi?an Jiaotong University, Xi?an Shaanxi 710049, China
As a lightweight SLA between service providers and consumers, class of service (CoS) can avoid the runtime overhead brought by multiple negotiation of service agreements. This is especially important in grid environment where lots of transient services exist. We bring CoS into grid environment and propose a QoS-enabled framework named CQEF for grid service. In this paper, we present a CoSenabled request scheduling policy for CoS deployment in CQEF. According to this policy, incoming requests can be identified and classified based on the CoS information attached to them and subsequently be assigned to different waiting queues with different priorities. Besides, queuing scheduling algorithm is used to achieve the CoS enabling purpose. A prototype has been developed over the Globus platform. The test results show that, by using this policy, service providers are able to offer differentiated services for different CoS and QoS of premium CoSs will be guaranteed preferentially.
Citation:
Yubin Yang, Yazhe Tang, Ming Zhao, Lei Yao, "A CoS-enabled Request Scheduling Policy," edocw, pp.13, 10th IEEE International Enterprise Distributed Object Computing Conference Workshops (EDOCW'06), 2006
Usage of this product signifies your acceptance of the Terms of Use.