Effective scheduling of local interactive processes and parallel processes in a non-dedicated cluster environment

Mnaouer, Adel Ben; Al-Riyami, Badriya

doi:10.1016/j.jpdc.2005.01.005

Cited by 4 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [43] evaluate a scheduling scheme that helps regulate the CPU cycle stealing by parallel tasks in a nondedicated cluster environment. This scheme is used to control the interactions between local IPs and processes running on behalf of a parallel job executed on the cluster.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid reliable load balancing with MOSIX as middleware and its formal verification using process algebra

Mishra

Kushwaha

Misra

2011

Future Generation Computer Systems

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

“…Few of these researches actually focus upon mix scheduling of local and remote jobs [50]. Authors in [51] claim that Multilevel Feedback Queue (MLFQ) scheduling proves viable for general purpose systems, however in this scheme CPU intensive processes suffers from starvation.…”

Section: Related Workmentioning

confidence: 99%

Hybrid reliable load balancing with MOSIX as middleware and its formal verification using process algebra

Mishra

Kushwaha

Misra

2011

Future Generation Computer Systems

View full text Add to dashboard Cite

“…communication characteristics of the application and do not consider the system and network loads. Few efforts consider scheduling of applications in non-dedicated environments [7,23,38]. Grid Harvest system [38] considers the arrival rate of jobs, machine utilization, service time and machine capacity for scheduling applications.…”

Section: Single-site Vs Multi-site Schedulingmentioning

confidence: 99%

“…Various efforts exist for scheduling parallel applications on multiple resources [1][2][3][4][5][6][7]. Some parallel applications are loosely coupled [8][9][10] where the interactions among the parallel tasks are negligible whereas some parallel applications are tightly coupled [11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

A strategy for scheduling tightly coupled parallel applications on clusters

Sanjay

Vadhiyar

2009

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARYAlthough various strategies have been developed for scheduling parallel applications with independent tasks, very little work exists for scheduling tightly coupled parallel applications on cluster environments. In this paper, we compare four different strategies based on performance models of tightly coupled parallel applications for scheduling the applications on clusters. In addition to algorithms based on existing popular optimization techniques, we also propose a new algorithm called Box Elimination that searches the space of performance model parameters to determine the best schedule of machines. By means of real and simulation experiments, we evaluated the algorithms on single cluster and multi-cluster setups. We show that our Box Elimination algorithm generates up to 80% more efficient schedules than other algorithms. We also show that the execution times of the schedules produced by our algorithm are more robust against the performance modeling errors.

show abstract

“…Although various scheduling mechanisms have been proposed and implemented by previous researchers, few of these [19,20] discusses about the mix scheduling of local and remote processes. Usually, it is seen that local processes get priority over remote process and hence migrated (remote) processes begin to starve.…”

Section: Introduction and Related Workmentioning

confidence: 99%

An optimized scheduling algorithm for migrated jobs in trusted distributed systems

Mishra

Kushwaha

Misra

2010

2010 International Conference on Computer and Communication Technology (ICCCT)

View full text Add to dashboard Cite

In present computing plethora, the cluster technology seems to gain popularity day by day. The prime reason for this popularity is high availability, increased reliability and high performance through efficient resource usage. To realize these benefits, the processing capacity of various nodes in a cluster must be allocated fairly. Often the clusters suffer from under utilization due to inappropriate choice of scheduling policy. The goal of the scheduling is to exploit the true potential of the system. Hence, finding the appropriate granularity of tasks and distributing them in such a way so that each machine is assigned equal work and thus, balancing the load across the cluster, is major issue of concern. Usually, it is seen that local processes get priority over remote processes and migrated (remote) processes begin to starve. We propose an optimized scheduling approach for migrated processes that ensures reduced latency time along with no starvation policy for any (local or remote) process. Our experimental results have been able to establish that priority and criticality based scheduling approach can increase overall system throughput by about 30-50 percent.

show abstract

Effective scheduling of local interactive processes and parallel processes in a non-dedicated cluster environment

Cited by 4 publications

References 21 publications

Hybrid reliable load balancing with MOSIX as middleware and its formal verification using process algebra

Hybrid reliable load balancing with MOSIX as middleware and its formal verification using process algebra

A strategy for scheduling tightly coupled parallel applications on clusters

An optimized scheduling algorithm for migrated jobs in trusted distributed systems

Contact Info

Product

Resources

About