{"title":"Bag of Tasks Rescheduling within Real Grid Environments: Different Approaches","authors":"Luis Tomás, María Blanca Caminero, C. Carrión","doi":"10.1109/PDP.2013.38","DOIUrl":null,"url":null,"abstract":"Providing Quality of Service (QoS) in Grid environments is still a challenging task because advance reservation of resources is not always possible. By contrast, scheduling the use of resources in advance is a way of enhancing the provision of QoS, without physically reserving them. However, in a Grid scenario fragmentation may appear as a logic result of the allocation process, leading to poor resource utilization. To try to avoid that problem a rescheduling technique has been developed and applied periodically depending on the existing fragmentation. Nevertheless, reallocating jobs in an optimal way is an NP-Hard problem. Consequently, simple and scalable ways of distributing and allocating those jobs into the resources are presented and evaluated in a real Grid environment involving heterogeneous computing resources distributed across different national organizations, highlighting the benefits of using them to increase the resource usage.","PeriodicalId":202977,"journal":{"name":"2013 21st Euromicro International Conference on Parallel, Distributed, and Network-Based Processing","volume":"46 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 21st Euromicro International Conference on Parallel, Distributed, and Network-Based Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PDP.2013.38","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Providing Quality of Service (QoS) in Grid environments is still a challenging task because advance reservation of resources is not always possible. By contrast, scheduling the use of resources in advance is a way of enhancing the provision of QoS, without physically reserving them. However, in a Grid scenario fragmentation may appear as a logic result of the allocation process, leading to poor resource utilization. To try to avoid that problem a rescheduling technique has been developed and applied periodically depending on the existing fragmentation. Nevertheless, reallocating jobs in an optimal way is an NP-Hard problem. Consequently, simple and scalable ways of distributing and allocating those jobs into the resources are presented and evaluated in a real Grid environment involving heterogeneous computing resources distributed across different national organizations, highlighting the benefits of using them to increase the resource usage.