Gang scheduling and adaptive resource allocation to mitigate advance reservation impact

Sodan, Angela C.; Doshi, C.; Barsanti, Lawrence; Taylor, Daniel B.

doi:10.1109/ccgrid.2006.47

Cited by 24 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of these strategies include static [18] or dynamic [47] gang-scheduling using advance reservation [38] and middleware mechanisms favouring simultaneous allocation such as the EGEE DAG job type. Grid advance reservation suffer from two drawbacks: first, planning is not consistent with the goal of seamless integration with everyday computing practice, for instance the use cases described in Section 2; second, reservation is inherently not work-conserving, meaning that processors might idle while eligible jobs are queued [46].…”

Section: Virtual Reservationsmentioning

confidence: 99%

Scheduling for Responsive Grids

Germain-Renaud

Loomis²,

Mościcki

et al. 2007

J Grid Computing

View full text Add to dashboard Cite

Abstract. Grids are facing the challenge of seamless integration of the grid power into everyday use. One critical component for this integration is responsiveness, the capacity to support on-demand computing and interactivity. Grid scheduling is involved at two levels in order to provide responsiveness: the policy level and the implementation level. The main contributions of this paper are as follows. First, we present a detailed analysis of the performance of the EGEE grid with respect to responsiveness. Second, we examine two user-level schedulers located between the general scheduling layer and the application layer. These are the DIANE (DIstributed ANalysis Environment) framework, a general-purpose overlay system, and a specialized, embedded scheduler for gPTM3D, an interactive medical image analysis application. Finally, we define and demonstrate a virtualization scheme, which achieves guaranteed turnaround time, schedulability analysis, and provides the basis for differentiated services. Both methods target a brokering-based system organized as a federation of batch-scheduled clusters, and an EGEE implementation is described.

show abstract

Section: Virtual Reservationsmentioning

confidence: 99%

Scheduling for Responsive Grids

Germain-Renaud

Loomis²,

Mościcki

et al. 2007

J Grid Computing

View full text Add to dashboard Cite

show abstract

“…However, advance reservation can only ensure the availability of resources at required time, but cannot provide guarantees to deadline [3,15]. In addition, many studies [16][17] show that excessive advance reservation will degrade the system's performance, for instance, high rejection rate and low resource utilization.…”

Section: Related Workmentioning

confidence: 99%

Deadline-Guarantee-Enhanced Co-Allocation for Parameter Sweep Application in Grid

2009

2009 IEEE International Conference on Communications

View full text Add to dashboard Cite

In grid computing, deadline-guarantee is one of the most mentioned QoS requirements for applications. However, the resource heterogeneity and the unpredictable workloads make it difficult for grid system to provide deadline-guarantee. In this paper, a novel approach is proposed to evaluate the deadlineguarantee of various co-allocation policies. By this approach, a hybrid-policy co-allocation model is also proposed to address the issue of deadline-constrained resource co-allocation in grid environments. The proposed model integrates multiple coallocation policies to generate different co-allocation schemes, and selects the optimal deadline-guarantee scheme for grid applications. By this way, the hybrid-policy model combines the merits of different co-allocation policies, and overcomes the shortcomings of those policies. Extensive simulations are conducted to verify the effectiveness and the performance of the proposed model in terms of deadline-miss rate. Experimental results show that it can provide co-allocation scheme with enhanced deadline-guarantee as well as lower deadline-miss rate.

show abstract

“…By conducting extensive simulations, Kaushik concluded that when the size of reservation window equal to the average waiting time in on-demand queue, the reservation blocking probability (rejection rate) can be minimized near to zero. In [8], Sodan et al incorporated gang scheduling and adaptive resource allocation into SCOJO scheduler [11] to mitigate the negative effects brought about by advance reservation.…”

Section: Related Workmentioning

confidence: 99%

“…Although reservation has been proven effective in many situations, it also brings several negative effects on resources sharing and scheduling in Grid computing [4][5][6][7][8][9][10]. Many studies indicate that conventional reservation will result in low resource utilization, and excessive reservation can lead to high rejection rate of requests.…”

Section: Introductionmentioning

confidence: 99%

A Novel Statistic-based Relaxed Grid Resource Reservation Strategy

Liu

2008

2008 the 9th International Conference for Young Computer Scientists

View full text Add to dashboard Cite

In Grid environments, advance reservation mechanism is to provide reliable resource coallocation and scheduling for applications. However, excessive advance reservation will bring about many negative effects for system's performance, such as lower resource utilization and higher rejection rate. To mitigate these negative effects of advance reservation, a relaxed reservation strategy is proposed, in which the reservation admission criteria is more relaxing than that of conventional reservation. The strategy is based on the facts that grid applications tend to overestimate reservation duration to ensure their completion. In the proposed relaxed reservation strategy, reservation manager might accept those reservations that are overlapping with existing ones. Experimental results show that the strategy can bring about remarkably higher resource utilization and lower rejection rate at the price of a slightly increasing of reservation violations.

show abstract

Gang scheduling and adaptive resource allocation to mitigate advance reservation impact

Cited by 24 publications

References 13 publications

Scheduling for Responsive Grids

Scheduling for Responsive Grids

Deadline-Guarantee-Enhanced Co-Allocation for Parameter Sweep Application in Grid

A Novel Statistic-based Relaxed Grid Resource Reservation Strategy

Contact Info

Product

Resources

About