Model-based resource selection for efficient virtual cluster deployment

Yamasaki, Shohei; Maruyama, Naoya; Matsuoka, Satoshi

doi:10.1145/1408654.1408660

Cited by 10 publications

(5 citation statements)

References 14 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Again, the focus here has been on lower level details, such as selecting appropriate host nodes in distributed and/or federated systems [75], properly distributing and instantiating virtual machine images [76], and allowing for check-pointing parallel jobs [69,77].…”

Section: Discussionmentioning

confidence: 99%

Dynamic Fractional Resource Scheduling for cluster platforms

Stillwell

2010

2010 IEEE International Symposium on Parallel &Amp; Distributed Processing, Workshops and PHD Forum (IPDPSW)

View full text Add to dashboard Cite

Experiments presented in this paper were carried out using the Grid'5000 experimental testbed, being developed under the INRIA ALADDIN development action with support from CNRS, RENATER and several Universities as well as other funding bodies (see https://www.grid5000.fr).The experiments using our prototype system were carried out on machines owned by the Deparment of Computer Science and Engineering at the University of California, San Diego with the permission of Geoffrey Voelker. System administration and much assistance were provided by Gjergji Zyba. iv ABSTRACTThis research focuses on the problem of job scheduling on homogeneous computational clusters. Clusters are widely used today for a variety of purposes, including high-performance scientific computing and Internet service hosting. While clusters may have impressive aggregate performance metrics, they are really only collections of fairly modest machines, which makes scheduling jobs for the best performance a non-trivial problem. Most clusters also need to be shared among users to amortize their start-up and maintenance costs, and ensuring that these users are treated fairly further adds to the difficulty. Existing approaches to scheduling attempt to address both of these issues, but have several limitations.We propose a novel approach, called Dynamic Fractional Resource Scheduling (DFRS), to sharing homogeneous cluster computing platforms among competing jobs.The key features of DFRS are that it leverages existing virtual machine technology in order to share resources more efficiently and it defines and optimizes a user-centric metric that captures notions of both performance and fairness. In this dissertation we explain the principles behind DFRS and its advantages over the current state of the art, develop a theoretical model of resource sharing, design heuristics to optimize the proposed metric within the given framework, implement and run simulations comparing DFRS to traditional approaches using popular and accepted performance metrics, and finally develop and test a prototype implementation based on existing technologies. Our results show that it is possible to develop heuristic algorithms that give results reasonably close to theoretical bounds for a variety of cases, that resource requirements are well within the capabilities of modern systems, and that for some scenarios DFRS can provide orders-ofmagnitude levels of improvement in performance over current approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

Dynamic Fractional Resource Scheduling for cluster platforms

Stillwell

2010

2010 IEEE International Symposium on Parallel &Amp; Distributed Processing, Workshops and PHD Forum (IPDPSW)

View full text Add to dashboard Cite

show abstract

“…However, the system is modelled at a very abstract level and only rough performance estimates (average times only) are possible. Other approaches provide virtualization models, but focus only on the deployment of virtual machines or virtual clusters (Sotomayor et al, 2006), (Yamasaki et al, 2007). These approaches do not consider the performance of a virtualized application.…”

Section: Related Workmentioning

confidence: 99%

Towards Performance Prediction for Cloud Computing Environments Based on Goal-Oriented Measurements

Hauck

Happe

Reussner

2011

Proceedings of the 1st International Conference on Cloud Computing and Services Science

View full text Add to dashboard Cite

Scalability and performance are critical quality attributes of applications developed for the cloud. Many of these applications have to support hundreds or thousands of concurrent users with strongly fluctuating workloads. Existing approaches for software performance evaluation do not address the new challenges that arise for applications executed in cloud computing environments. The effects of virtualization on response times, throughput, and resource utilisation as well as the massive number of resources available require new platform and resource models for software performance evaluation. Modelling cloud environments using established approaches for software performance prediction is a cumbersome task that requires a detailed understanding of virtualization techniques and their effect on software performance. Additional complexity comes from the fact that cloud environments may combine multiple virtualization platforms which differ in implementation and performance properties. In this position paper, we propose an approach to infer performance models of cloud computing environments automatically through goal-oriented measurements. The resulting performance models can be directly combined with established model-driven performance prediction approaches. We outline the research challenges that have to be addressed in order to employ the approach for design-time performance predictions of software systems running in cloud computing environments.

show abstract

“…Opportunistic models for selecting the resources used in the deployment of virtual clusters and grids are described in [3]. In [4] solutions for the deployment of virtual cluster and grid infrastructures are described.…”

Section: Related Workmentioning

confidence: 99%

UnaGrid: On Demand Opportunistic Desktop Grid

Castro

Rosales

Villamizar

et al. 2010

2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing

View full text Add to dashboard Cite

This paper deals with the design and implementation of a virtual opportunistic grid infrastructure that allows taking advantage of the idle processing capabilities currently available in the computer labs of a university campus, ensuring local users to have priority in accessing the computational resources, while simultaneously, a virtual cluster takes the resources unused by them. A virtualization strategy is proposed to allow the deployment of opportunistic virtual clusters which integration provides a scalable grid solution capable of supplying the high performance computing (HPC) needs required for the development of e-Science projects. The proposed solution was implemented and tested through the execution of opportunistic virtual clusters with customized application environments for projects of different scientific disciplines, evidencing high efficiency in result generation.

show abstract

Model-based resource selection for efficient virtual cluster deployment

Cited by 10 publications

References 14 publications

Dynamic Fractional Resource Scheduling for cluster platforms

Dynamic Fractional Resource Scheduling for cluster platforms

Towards Performance Prediction for Cloud Computing Environments Based on Goal-Oriented Measurements

UnaGrid: On Demand Opportunistic Desktop Grid

Contact Info

Product

Resources

About