{"title":"Cake cutting of CPU resources among multiple HPC agents on a cloud","authors":"Kausal Malladi, Debargha Ganguly","doi":"10.1109/ICRTIT.2013.6844172","DOIUrl":null,"url":null,"abstract":"“You cut, I choose” is a classical algorithm for fair sharing of resources among two agents which guarantees “envy-freeness”. In a multi-agent scenario, several algorithms were proposed for sharing resources fairly on a Cloud. However, no algorithm has been proposed till now for High Performance Computing (HPC) agents which are computational intensive, where not just the resources are to be fair-shared but used to the utmost. This paper proposes an algorithm that considers a specific number of HPC agents that can be run on a host machine and tries to do a fair-share of resources. The proposed algorithm assumes the agents demanding resources to be taking a game-theoretic approach and gives a decent proportion of the demand as the allocation value. This algorithm works for a real-world scenario in which, the agents keep getting added dynamically to a host machine and assumes that the agents will not depart after they are allocated.","PeriodicalId":113531,"journal":{"name":"2013 International Conference on Recent Trends in Information Technology (ICRTIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 International Conference on Recent Trends in Information Technology (ICRTIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICRTIT.2013.6844172","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
“You cut, I choose” is a classical algorithm for fair sharing of resources among two agents which guarantees “envy-freeness”. In a multi-agent scenario, several algorithms were proposed for sharing resources fairly on a Cloud. However, no algorithm has been proposed till now for High Performance Computing (HPC) agents which are computational intensive, where not just the resources are to be fair-shared but used to the utmost. This paper proposes an algorithm that considers a specific number of HPC agents that can be run on a host machine and tries to do a fair-share of resources. The proposed algorithm assumes the agents demanding resources to be taking a game-theoretic approach and gives a decent proportion of the demand as the allocation value. This algorithm works for a real-world scenario in which, the agents keep getting added dynamically to a host machine and assumes that the agents will not depart after they are allocated.