Preemption-aware Admission Control in a Virtualized Grid Federation

Salehi, Mohsen Amini; Javadi, Bahman; Buyya, Rajkumar

doi:10.1109/aina.2012.52

Cited by 4 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other researchers have proposed to steer admission control with neural controller and support vector machines (Mohana and Thangaraj 2013), and use scheduling algorithms based on meta-heuristic optimisation Hoang et al (2016). Database access with profit-oriented control has been researched by Xiong et al (2011), while requests preemption in admission control context was studied by (Salehi, Javadi, and Buyya 2012).…”

Section: Related Workmentioning

confidence: 99%

Neural adaptive admission control framework: SLA-driven action termination for real-time application service management

Sikora

Magoulas

2019

Enterprise Information Systems

View full text Add to dashboard Cite

Although most modern cloud-based enterprise systems, or operating systems, do not commonly allow configurable/automatic termination of processes, tasks or actions, it is common practice for systems administrators to manually terminate, or stop, tasks or actions at any level of the system. The paper investigates the potential of automatic adaptive control with action termination as a method for adapting the system to more appropriate conditions in environments with established goals for both system's performance and economics. A machine-learning driven control mechanism, employing neural networks, is derived and applied within data-intensive systems. Control policies that have been designed following this approach are evaluated under different load patterns and service level requirements. The experimental results demonstrate performance characteristics and benefits as well as implications of termination control when applied to different action types with distinct run-time characteristics. An automatic termination approach may be eminently suitable for systems with harsh execution time Service Level Agreements, or systems running under conditions of hard pressure on power supply or other constraints. The proposed control mechanisms can be combined with other available toolkits to support deployment of autonomous controllers in high-dimensional enterprise information systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Neural adaptive admission control framework: SLA-driven action termination for real-time application service management

Sikora

Magoulas

2019

Enterprise Information Systems

View full text Add to dashboard Cite

show abstract

“…In systems that function on the basis of VMs, preemption mechanism is preferable to resolve resource contention, because it removes the burden of partitioning or managing several queues from a resource management system. Although preemption mechanism has not been studied extensively in the distributed computing systems previously [11], dominance of the VM technology as the provisioning model has led to undertake several studies in this area [12][13][14][15]. In this section, we review recent studies that have applied preemption mechanism to resolve the contention between requests.…”

Section: Introductionmentioning

confidence: 99%

Contention management in federated virtualized distributed systems: implementation and evaluation

2013

Self Cite

View full text Add to dashboard Cite

SUMMARYThe paper describes creation of a contention‐aware environment in a large‐scale distributed system where the contention occurs to access resources between external and local requests. To resolve the contention, we propose and implement a preemption mechanism in the InterGrid platform, which is a platform for large‐scale distributed system and uses virtual machines for resource provisioning. The implemented mechanism enables the resource providers to increase their resource utilization through contributing resources to the InterGrid platform without delaying their local users. The paper also evaluates the impact of applying various policies for preempting user requests. These policies affect resource contention, average waiting time, and imposed overhead to the system. Experiments conducted in real settings demonstrate efficacy of the preemption mechanism in resolving resource contention and the influence of preemption policies on the amount of imposed overhead and average waiting time. Copyright © 2013 John Wiley & Sons, Ltd.

show abstract