Service Level Agreement based Allocation of Cluster Resources: Handling Penalty to Enhance Utility

Yeo, Chee Shin; Buyya, Rajkumar

doi:10.1109/clustr.2005.347075

Cited by 94 publications

(66 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both reward and penalty must be agreed at negotiation time and must be defined specified in the SLA. Penalty can be specified in SLA as a penalty function [27], which not only penalizes the provider for service failures but also compensates the users for them. An example of a reward and the penalty function is as follows:…”

Section: Penalties and Rewardsmentioning

confidence: 99%

SLA‐Based Resource Management and Allocation

Guitart

Lloret

Rana

et al. 2009

Market‐Oriented Grid and Utility Computing

View full text Add to dashboard Cite

Section: Penalties and Rewardsmentioning

confidence: 99%

SLA‐Based Resource Management and Allocation

Guitart

Lloret

Rana

et al. 2009

Market‐Oriented Grid and Utility Computing

View full text Add to dashboard Cite

“…Large-scale scientific or engineering applications are usually mapped onto multiple distributed resources, so how to provide an efficient strategy without complicated coordination is a hard problem. Considering grid resource owners being similar to rational market participants, economic model becomes a topic of great interest in grid task scheduling strategies which are designed similarly to market supply-demand mechanisms [2] [3]. Although the grid resource provider, also being the scheduling decision maker, usually attempts to obtain maximum commercial profits, it has to design a seemingly fair allocation strategy since an obvious unreasonable allocation will arouse users' dissatisfaction.…”

Section: Introductionmentioning

confidence: 99%

A Global Benefit Maximization Task-Bundle Allocation

Zheng

et al. 2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Obtaining maximal benefit is usually the most important goal pursued by Grid resource/service provider. As providers and users being noncooperative inherently, it is a fundamental challenge to design a resource allocation strategy which seems to be fair. In order to adapt to large-scale Grid environment, we adopted a hierarchical grid structure with bundle tasks to describe the Grid system. A model called Intra-Site Cooperative-game of Taskbundle (ISCT) was proposed, in which all subordinate resources participated in making profits. We calculated task market price based on the theoretical proof that the system would gain maximal global benefit if and only if it was in a balanced state. Then we determined the task allocation solution with solving the task assignment amount vector. An Intra-Site Global Benefit Maximization Allocation for Task-bundle (ISGBMAT) was presented, which converted the Grid task-bundle allocation problem into an iteration process involving retail price, market price and assignment amount of tasks. Extensive simulation experiments with real workload traces were conducted to verify our algorithm. The experimental results indicated that ISGBMAT could provide an effective solution with global benefit and completion time optimization and also adapt to dynamic Grid market.

show abstract

“…Studies of alternative economic strategies [4][5][6] and failure scenarios [1] have shown that small variations in key system variables can lead to large differences in overall system performance. While large-scale simulations are more practical than operational testbeds, computational expense can increase dramatically with model size, a critical factor for studying large-scale systems such as the Internet.…”

Section: Introductionmentioning

confidence: 99%

“…(1,1) 0.680000 (1,2) 0.020000 (1,4) 0.020000 (1,5) 0.020000 (1,6) 0.040000 (1,7) 0.040000 (1,9) 0.020000 (1,11) 0.020000 (1,13) 0.040000 (1,14) 0.040000 (1,15) 0.020000 (1,17) 0.020000 (1,18) 0.020000 (2,24) 0.040000 (2,25) 0.020000 (2,28) 0.020000 (2,29) 0.020000 (2,31) 0.020000 (2,34) 0.020000 (2,35) 0.020000 (2,36) 0.020000 (2,38) 0.020000 (2,41) 0.020000 (2,42) 0.020000 (2,43) 0.020000 (2,44) 0.020000 (2,…”

mentioning

confidence: 99%

Improving efficiency of markov chain analysis of complex distributed systems

Dabrowski¹,

Hunt²,

Morrison³

2010

View full text Add to dashboard Cite

Abstract:In large-scale distributed systems, the interactions of many independent components may lead to emergent global behaviors with unforeseen, often detrimental, outcomes. The increasing importance of distributed systems such as clouds and computing grids will require analytical tools to understand and predict, complex system behavior to ensure system reliability. In previous work, we described how a piecewise homogeneous Discrete Time Markov chain representation of a computing grid can be systematically perturbed to predict situations that lead to performance degradations. While the execution time of this approach compared favorably with detailed large-scale simulation, a sizable number of perturbations of the model were needed to identify scenarios in which system performance degraded. Here, we evolve our original approach and describe two novel methods for quickly identifying portions of the Markov chain that are sensitive to perturbation. The first method involves finding minimal s-t cut sets, consisting of state transitions that disconnect all paths in a Markov chain from the initial to a desired end state. By perturbing state transitions in the cut set, it is possible to quickly identify scenarios in which system performance is adversely affected. We show this method can be applied to larger Markov models than the approach described in our earlier work. We then present a second method, in which the Spectral Expansion Theorem is used to analyze the eigensystem of a set of Markov transition probability matrices to predict which state transitions, if perturbed, are likely to adversely affect system performance. Results are presented for both methods to show that they can be used to identify the same failure scenarios presented in our earlier paper (as well as additional scenarios, using the first method), while reducing the number of perturbations needed. We argue that these methods provide a basis for creating practical tools for analysis of complex systems behavior in distributed systems.

show abstract

Service Level Agreement based Allocation of Cluster Resources: Handling Penalty to Enhance Utility

Abstract: Jobs submitted into a cluster have varying requirements depending on user-specific needs and expectations. Therefore, in utility-driven cluster computing, cluster Resource Management Systems (RMSs)

Cited by 94 publications

References 10 publications

SLA‐Based Resource Management and Allocation

SLA‐Based Resource Management and Allocation

A Global Benefit Maximization Task-Bundle Allocation

Improving efficiency of markov chain analysis of complex distributed systems

Contact Info

Product

Resources

About