Conference Paper

Harnessing Migrations in a Market-based Grid OS

DOI: 10.1109/GRID.2008.4662786 Conference: 9th IEEE/ACM International Conference on Grid Computing (Grid 2008), Tsukuba, Japan, September 29 - October 1, 2008
Source: DBLP

ABSTRACT Applying economic principles to grids is deemed promising to improve the overall value provided by such systems. End users can influence the allocation of resources by reporting valuations for these resources. Current market-based schedulers, however, are static, assume the availability of complete information about jobs (in particular with respect to processing times), and do not make use of the flexibility offered by advanced computing systems. In this paper, we present the implementation of economic resource allocation principles into MOSIX, a state-of-the-art management system for computing clusters and multi-cluster organizational grids. The system is designed so as to be able to work in large-scale settings with selfish agents. Facing incomplete information about jobspsila characteristics, it dynamically allocates jobs to computing machines by leveraging preemption and job migration, two distinct features offered by MOSIX. We validate and showcase the behavior of our economic model by means of experiments in the real system.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Cloud computing is a promising way providing users computing resources. These resources are provided by means of standard computing instances. Currently there are three price schemas including spot, reservation and on-demand in cloud market, but the average difference among these three pricing schema can be as much as 2.7 times even for the same instance type. In the premise of ensuring service level object, how many and which compute instance are needed, which price schema is needed is important for company. In this paper, an intelligent capacity planning model was proposed. Experimental result shows that our model can save more money while the quality of service does not degrade.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Market-based resource allocation is expected to be an effective mechanism to allocate resources in a cloud computing environment, where the resources are virtualized and delivered to users as services. In this paper we propose a market mechanism to efficiently allocate multiple computation/storage services among multiple participants, or the Cloud Service Exchange. The proposed mechanism enables users (1) to order a combination of arbitrary services in a co-allocation or a workflow manner, and (2) to receive future/current services at the forward/spot market. Keyword Cloud computing, Grid computing, Scheduling, Market-based resource allocation, Combinational auctions
  • [Show abstract] [Hide abstract]
    ABSTRACT: We believe that a market-based resource allocation will be effective in a cloud computing environment where resources are virtualized and delivered to users as services. We propose such a market mechanism to allocate services to participants efficiently. The mechanism enables users (1) to order a combination of services for workflows and co-allocations and (2) to reserve future/current services in a forward/spot market. The evaluation shows that the mechanism works well in probable setting.
    Applications and the Internet (SAINT), 2010 10th IEEE/IPSJ International Symposium on; 08/2010