A Parallel Job Execution Time Estimation Approach Based on User Submission Patterns within Computational Grids

Lu, Feng; Liu, Yunzhen; Liu, Hai; Ma, Shilong; Schnor, Bettina

doi:10.1007/s10766-013-0294-1

Cited by 9 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A job can be executed on multiple types and numbers of instances, as long as the total demand is satisfied. Estimating a job's demand which can also be understood as the runtime is a classic problem which attracts extensive studies (e.g., [32,33]), falling beyond the scope of our study. Threshold k i is used to limit job i's degrees of parallelism (DoPs), which means job i can be divided into at most k i independent tasks to run on different instances in parallel, without any overhead.…”

Section: These Different Types Of Heterogeneous Instances Have Differ...mentioning

confidence: 99%

Market-Oriented Online Bi-Objective Service Scheduling for Pleasingly Parallel Jobs with Variable Resources in Cloud Environments

Zheng

Pan

Liu

2021

Preprint

View full text Add to dashboard Cite

In this paper, we study the market-oriented online bi-objective service scheduling problem for pleasingly parallel jobs with variable resources in cloud environments, from the perspective of SaaS (Software-as-as-Service) providers who provide job-execution services. The main process of scheduling SaaS services in clouds is: a SaaS provider purchases cloud instances from IaaS providers to schedule end users' jobs and charges users accordingly. This problem has several particular features, such as the job-oriented end users, the pleasingly parallel jobs with soft deadline constraints, the online settings, and the variable numbers of resources. For maximizing both the revenue and the user satisfaction rate, we design an online algorithm for SaaS providers to optimally purchase IaaS instances and schedule pleasingly parallel jobs. The proposed algorithm can achieve competitive objectives in polynomial run-time. The theoretical analysis and simulations based on real-world Google job traces as well as synthetic datasets validate the effectiveness and efficiency of our algorithm.

show abstract

Section: These Different Types Of Heterogeneous Instances Have Differ...mentioning

confidence: 99%

Market-Oriented Online Bi-Objective Service Scheduling for Pleasingly Parallel Jobs with Variable Resources in Cloud Environments

Zheng

Pan

Liu

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The paper entitled "A Parallel Job Execution Time Estimation Mechanism Based on User Submission Patterns within Computational Grids" [7] by Feng Liang, Yunzhen Liu, Hai Liu, Shilong Ma, and Bettina Schnor presents and evaluate a novel execution time estimation approach for parallel jobs, the User-Behavior Clustering for Execution Time Estimation (UBCETE), which can give more accurate execution time estimation for parallel jobs through exploring the job similarity and revealing the user submission patterns to help finding the similar jobs. Compared to the state-of-art algorithms, their approach is shown to improve the accuracy of the job execution time estimation up to 5.6 %, meanwhile the time our approach spends on calculation can be reduced up to 3.8 %.…”

Section: Virtualization and Resource Managementmentioning

confidence: 99%

Network and Parallel Computing

Hsu

Shi

2014

Int J Parallel Prog

View full text Add to dashboard Cite

“…Their simulation results revealed that in terms of the considered criteria, admissible allocation strategies outperform algorithms that use all available sites for job allocation. Liang et al [9] used behavioural clustering of execution time to establish a pattern for users' jobs and used that to improve accuracy of overall job execution times. Batch approaches include algorithms such as: MinMin, where jobs with the minimum completion time are assigned to the processor that can complete the job the earliest; MaxMin, where jobs with maximum completion time are assigned to processors that can complete the job earliest; and Sufferage, where a machine is assigned to the task that would ''suffer'' most in terms of expected completion time if that particular machine is not assigned to it [3].…”

Section: Introductionmentioning

confidence: 99%

Group-based Parallel Multi-scheduler for Grid computing

Abraham

James

Yaacob

2015

Future Generation Computer Systems

View full text Add to dashboard Cite

With the advent in multicore computers, the scheduling of Grid jobs can be made more effective if scaled to fully utilize the underlying hardware, and parallelized to benefit from the exploitation of multicores. The fact that sequential algorithms do not scale with multicore systems nor benefit from parallelism remains a major obstacle to scheduling in the Grid. As multicore systems become ever more pervasive in our computing lives, over reliance on such systems for passive parallelism does not offer the best option in harnessing the benefits of their multiprocessors for Grid scheduling. An explicit means of exploiting parallelism for Grid scheduling is required. The Group-based Parallel Multi-scheduler, introduced in this paper, is aimed at effectively exploiting the benefits of multicore systems for Grid scheduling by splitting jobs and machines into paired groups and independently scheduling jobs in parallel from those groups. We implemented two job grouping methods, Execution Time Balanced (ETB) and Execution Time Sorted then Balanced (ETSB), and two machine grouping methods, Evenly Distributed (EvenDist) and Similar Together (SimTog). For each method, we varied the number of groups between 2, 4 and 8. We then executed the MinMin Grid scheduling algorithm independently within the groups. We demonstrated that by sharing jobs and machines into groups before scheduling, the computation time for the scheduling process drastically improved by magnitudes of 85% over the ordinary MinMin algorithm when implemented on a HPC system. We also found that our balanced group based approach achieved better results than our previous Priority based grouping approach.

show abstract

A Parallel Job Execution Time Estimation Approach Based on User Submission Patterns within Computational Grids

Cited by 9 publications

References 32 publications

Market-Oriented Online Bi-Objective Service Scheduling for Pleasingly Parallel Jobs with Variable Resources in Cloud Environments

Market-Oriented Online Bi-Objective Service Scheduling for Pleasingly Parallel Jobs with Variable Resources in Cloud Environments

Network and Parallel Computing

Group-based Parallel Multi-scheduler for Grid computing

Contact Info

Product

Resources

About