Join-the-shortest-queue scheduling with delay

Mehdian, Saied; Zhou, Zhengyuan; Bambos, Nicholas

doi:10.23919/acc.2017.7963205

Cited by 6 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar balancing approaches are widely adopted such as Least Connection (LC) weighted algorithms, Round Robin (RR) weighted algorithms [27], Random selection, and Shortest-Queue [28,29]. These balancing approaches are provided as a service by popular cloud providers such as Windows Azure, Amazon ELB, and HP-CLB [30].…”

Section: Background and Related Workmentioning

confidence: 99%

QOS-Driven Job Scheduling: Multi-Tier Dependency Considerations

Suleiman¹,

Basir²

2019

9th International Conference on Computer Science, Engineering and Applications (CCSEA 2019)

View full text Add to dashboard Cite

For a cloud service provider, delivering optimal system performance while fulfilling Quality of Service (QoS) obligations is critical for maintaining a viably profitable business. This goal is often hard to attain given the irregular nature of cloud computing jobs. These jobs expect high QoS on an on-demand fashion, that is on random arrival. To optimize the response to such client demands, cloud service providers organize the cloud computing environment as a multi-tier architecture. Each tier executes its designated tasks and passes the job to the next tier; in a fashion similar, but not identical, to the traditional job-shop environments. An optimization process must take place to schedule the appropriate tasks of the job on the resources of the tier, so as to meet the QoS expectations of the job. Existing approaches employ scheduling strategies that consider the performance optimization at the individual resource level and produce optimal single-tier driven schedules. Due to the sequential nature of the multi-tier environment, the impact of such schedules on the performance of other resources and tiers tend to be ignored, resulting in a less than optimal performance when measured at the multi-tier level. In this paper, we propose a multi-tier-oriented job scheduling and allocation technique. The scheduling and allocation process is formulated as a problem of assigning jobs to the resource queues of the cloud computing environment, where each resource of the environment employs a queue to hold the jobs assigned to it. The scheduling problem is NP-hard, as such a biologically inspired genetic algorithm is proposed. The computing resources across all tiers of the environment are virtualized in one resource by means of a single queue virtualization. A chromosome that mimics the sequencing and allocation of the tasks in the proposed virtual queue is proposed. System performance is optimized at this chromosome level. Chromosome manipulation rules are enforced to ensure task dependencies are met. The paper reports experimental results to demonstrate the performance of the proposed technique under various conditions and in comparison with other commonly used techniques.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

QOS-Driven Job Scheduling: Multi-Tier Dependency Considerations

Suleiman¹,

Basir²

2019

9th International Conference on Computer Science, Engineering and Applications (CCSEA 2019)

View full text Add to dashboard Cite

show abstract

“…Previous works on stability of queuing networks are typically based on full knowledge of model data [1,[8][9][10][11][12][13]. So far, the best-studied MDI control policy is the join-the-shortestqueue (JSQ) routing policy for parallel queues [14][15][16][17][18][19][20][21] or simple networks [22], which requires only the queue lengths and does not rely on model data [23]. When and only when the network is stabilizable, i.e., the demand is less than capacity (service rate), the JSQ policy guarantees the stability of parallel queues/simple networks [22,24] and the optimality of homogeneous servers [15].…”

Section: Introductionmentioning

confidence: 99%

Stabilizing Queuing Networks with Model Data-Independent Control

Quan¹,

Li²

2020

Preprint

View full text Add to dashboard Cite

Classical queuing network control strategies typically rely on accurate knowledge of model data, i.e. arrival and service rates. However, such data are not always available and may be time-variant. To address this challenge, we consider a class of model data-independent (MDI) control policies that only rely on traffic state observation and network topology. Specifically, we focus on the MDI control policies that can stabilize multi-class Markovian queuing networks under centralized and decentralized policies. Control actions include routing, sequencing, and holding. By expanding the routes and constructing piecewise-linear test functions, we derive an easy-to-use criterion to check the stability of a multi-class network under a given MDI control policy. For stabilizable multi-class networks, we show that a centralized, stabilizing MDI control policy exists. For stabilizable single-class networks, we further show that a decentralized, stabilizing MDI control policy exists. In addition, for both settings, we construct explicit policies that attain maximal throughput and present numerical examples to illustrate the results.

show abstract