Fair scheduling of bag-of-tasks applications on large-scale platforms

Celaya, Javier; Arronategui, Unai

doi:10.1016/j.future.2015.03.002

Cited by 14 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Defining the fairness In earlier studies, the fairness of users was defined based on their performance slowdowns similar to our work, such as the maximum slowdown [31], [32] and the ratio of the maximum slowdown to the minimum slowdown [33]. With the fairness index [34], the best fairness is achieved when all users have the same degree of the performance slowdown [35].…”

Section: Related Workmentioning

confidence: 99%

“…With the fairness index [34], the best fairness is achieved when all users have the same degree of the performance slowdown [35]. However, the ideal performance of each application is computed as that when all the available resources are used without considering interference effects among its own tasks [32], or when an even share of each type of heterogeneous resources is used without reflecting different behaviors of application performance on platforms [20], [31]. Scheduling many-task applications In a heterogeneous computing system, several scheduling algorithms for manytask applications have been investigated to improve the efficiency [6], [20], [22], [36].…”

Section: Related Workmentioning

confidence: 99%

“…Resource allocation policies were proposed to achieve efficiency, fairness, and/or user satisfaction without considering the co-runner effects [20]. A fairness-aware scheduling policy for bag-of-task applications was studied for a large-scale platform in which the number of tasks for each application is much less than the number of nodes [32]. Scheduling independent tasks Techniques to map and schedule independent tasks on heterogeneous computing platforms have been investigated [37]- [39], in which the effects of different machine types on the performance are taken into account on scheduling.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Achieving Fairness-Aware Two-Level Scheduling for Heterogeneous Distributed Systems

Hwang

Kim

Choi

2021

IEEE Trans. Serv. Comput.

View full text Add to dashboard Cite

In a heterogeneous distributed system composed of various types of computing platforms such as supercomputers, grids, and clouds, a two-level scheduling approach can be used to effectively distribute resources of the platforms to users in the first-level, and map tasks of the users in nodes for each platform in the second-level for executing many-task applications. When scheduling heterogeneous resources, service providers of the system should consider the fairness among multiple users as well as the system efficiency. However, the fairness cannot be achieved by simply distributing an equal amount of resources from each platform to every user. In this paper, we investigate how to address the fairness issue among multiple users in a heterogeneous distributed system. We present three first-level resource allocation policies of a provider affinity first policy, an application affinity first policy, and a platform affinity based round-robin policy, and two second-level task mapping policies of a most affected first policy and a co-runner affinity based round-robin policy. Using trace-based simulations, we evaluate the performance of various combinations of the first and second level scheduling policies. Our extensive simulation results demonstrate that the first-level policy plays a crucial role to achieve relatively good fairness.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Achieving Fairness-Aware Two-Level Scheduling for Heterogeneous Distributed Systems

Hwang

Kim

Choi

2021

IEEE Trans. Serv. Comput.

View full text Add to dashboard Cite

show abstract

“…In a recent work, an algorithm is proposed for the fair scheduling of deadline‐constrained BoT workloads in computing environments (not cloud specific) . The objective is to minimize the slowdown of execution in a shared computing environment.…”

Section: Related Workmentioning

confidence: 99%

Online scheduling of deadline‐constrained bag‐of‐task workloads on hybrid clouds

Peláez¹,

Campos²,

García

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

The advent of hybrid cloud technologies and public Infrastructures as a Service (IaaS) allows service developers to offer services to their customers with little upfront investment and to adapt services to different workload sizes. The problem of minimizing the costs of the hired public infrastructure while providing the quality of service needed by the final customer arises when using hybrid clouds. Several scheduling strategies have been proposed to solve this problem for services dealing with deadline-constrained bag-of-tasks workloads. Most of these solutions do not consider the variable performance of the clouds, the provisioning delay of virtual machine instances that affects the elasticity, and the impracticality of having good processing time estimations in real systems. We propose a scheduler algorithm that overcomes previous limitations and can minimize the cost of the infrastructure while maximizing the number of deadlines met by the service. Our solution can work autonomously by using sampled observations of the processing times and considers the heterogeneity and the provisioning time of the virtual machine instances. An evaluation was conducted by simulating different scenarios and workload types. Simulation results show that our solution obtains better or similar results than previous techniques in most scenarios in terms of deadlines met. KEYWORDS bag-of-task workloads, cloud computing, hybrid cloud, scheduling 1 INTRODUCTION The adoption of the Cloud Computing Paradigm 1 has changed the provision of computational resources. 2 Platforms such as Amazon EC2, Microsoft Azure, or Google Compute Engine offer computational resources under the Infrastructure as a Service (IaaS) paradigm. The main characteristics of these services are 3 : on-demand and self-service resources, virtualized computational resources accessed over broad networks, resource pooling, rapid elasticity, and pay-per-use. IaaS allows service providers to have access to pools of resources under the financial model of pay-per-use. In this scenario, it is very important to optimize the use of the hired resources while meeting the quality of service expected by end-users. The main strategy for this resource optimization is the right management of hired resources and the execution of the application using a suitable scheduler. 4In the case of deadline-constrained applications and workloads, the quality of service is mainly determined by the processing deadline. Therefore, the problem for a service provider is to meet the processing deadline of the jobs submitted by end-users while minimizing the IaaS resources hired to run the service attending the workload (ie, the cost). This is similar to a deadline-constrained job scheduling problem with a dynamic number of heterogeneous machines for the execution of the jobs. The number of machine types is related to the number of virtual machine types available from IaaS providers.Workloads composed of sets of independent jobs or tasks are commonly known as Bag-of-Tasks (BoT) applications. 5 BoT work...

show abstract

“…To schedule concurrent BoT, Benoit et al [6] developed the online and off-line scheduling algorithms. Celaya and Arronategui [7] designed a decentralized scheduling algorithm to minimize the maximum stretch among user-submitted tasks. Yang et al [45] took the constraints of time, cost, and security into consideration, and designed a scheduling algorithm for data-intensive tasks.…”

Section: Introductionmentioning

confidence: 99%

Off-Line Time Aware Scheduling of Bag-of-Tasks on Heterogeneous Distributed System

Xuan

Wei

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The resource allocation for bag-of-tasks in the heterogeneous distributed system is to distribute the tasks to proper processors such that the makespan is minimized. It is a well-known NP-hard problem, and is even more complex and challenging when the processors have off-line time. To tackle this challenging problem, first, we set up a mathematical model for this problem which minimizes the makespan of the bag-oftasks with the off-line time segment of the processors. Second, to solve the model efficiently, we propose two new algorithms: a new scheduling algorithm referred to as sorting-allocation-pulling scheduling algorithm which first allocate the tasks to available time segment on proper processors and then pulls them to the formerly available time segment for the sake of minimizing the makespan, and an effective genetic algorithm with a novel local search operator and a well-designed modify operator. Finally, the numerical simulation experiments are conducted, and the two proposed algorithms are compared. The experimental results indicate the effectiveness of the proposed model and algorithms. INDEX TERMS Distributed computing, task scheduling, bag-of-tasks, generic algorithm.

show abstract

Fair scheduling of bag-of-tasks applications on large-scale platforms

Cited by 14 publications

References 17 publications

Achieving Fairness-Aware Two-Level Scheduling for Heterogeneous Distributed Systems

Achieving Fairness-Aware Two-Level Scheduling for Heterogeneous Distributed Systems

Online scheduling of deadline‐constrained bag‐of‐task workloads on hybrid clouds

Off-Line Time Aware Scheduling of Bag-of-Tasks on Heterogeneous Distributed System

Contact Info

Product

Resources

About