Extending GridSim with an architecture for failure detection

Caminero, Agustín C.; Sulistio, Anthony; Caminero, Blanca; Carrión, Carmen; Buyya, Rajkumar

doi:10.1109/icpads.2007.4447756

Cited by 28 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The new release of GridSim version 4.0 adds package gridsim.resFailure for resource failure detection that uses pull mechanism [5]. Therefore this package was used in our simulation.…”

Section: Simulation Designmentioning

confidence: 99%

Checkpointing in selected most fitted resource task scheduling in grid computing

Latip

San

Chanchary

2012

2012 7th International Conference on Computer Science &Amp; Education (ICCSE)

View full text Add to dashboard Cite

Grid applications run on environment that is prone to different kinds of failures. Fault tolerance is the ability to ensure successful delivery of services despite faults that may occur. Our research adds fault tolerance capacity with checkpointing and machine failure, to the current research, Selected Most Fitted (SMF) Task Scheduling for grid computing. This paper simulates one of fault tolerance techniques for grid computing, which is implementing checkpointing into Select Most Fitting Resource for Task Scheduling algorithm (SMF). We applied the algorithm of MeanFailure with Checkpointing in the SMF algorithm and named it MeanFailureCP-SMF. The MeanFailureCP-SMF is simulated using Gridsim with initial checkpointing interval at 20% job execution time. Results show that with MeanFailureCP-SMF has reduce the average execution time (AET) compare to the current SMF and MeanFailure Algorithm.

show abstract

“…The new release of GridSim version 4.0 adds package gridsim.resFailure for resource failure detection that uses pull mechanism [5]. Therefore this package was used in our simulation.…”

Section: Simulation Designmentioning

confidence: 99%

Checkpointing in selected most fitted resource task scheduling in grid computing

Latip

San

Chanchary

2012

2012 7th International Conference on Computer Science &Amp; Education (ICCSE)

View full text Add to dashboard Cite

show abstract

“…A fault tolerant resource broker architecture for economy based computational grid, which combines check-pointing and transaction to provide fault-tolerant scheduling is implemented in [9]. Failure models are created by means of probabilistic distributions with fully configurable parameters [10].…”

Section: Related Workmentioning

confidence: 99%

Resource Failure Impact on Job Execution in Grid

Suri

Singh²

2009

2009 International Conference on Advances in Recent Technologies in Communication and Computing

View full text Add to dashboard Cite

Grid environment, being a collection of heterogeneous and geographically distributed resources, is prone to many kinds of failures such as process failures, resource and network failures. In this paper, we address the problem of resource failure. Resources in grid oscillate between being available and unavailable to the grid. When and how they do so, depends on the failure characteristics of the machines, the policies of resource owners and the scheduling policies. The research work involves implementation of job scheduling in a grid based on pull method for handling resource failure using GridSim simulation toolkit. We also demonstrate how the job execution time varies under different resource failure conditions using different failure patterns.

show abstract

“…It allows modeling of heterogeneous types of resources, Resource capability can be defined in the form of MIPS (Million Instructions Per Second) as per SPEC (Standard Performance Evaluation Corporation) benchmark, There is no limit on the number of application jobs that can be submitted to a resource, It supports simulation of both static and dynamic schedulers. GridSim had been used in many researches to evaluate the results such as [4,7].…”

Section: Performance Evaluationmentioning

confidence: 99%

HPGRID

Miriam

Easwarakumar

2011

Proceedings of the 2011 International Conference on Communication, Computing &Amp; Security - ICCCS '11

View full text Add to dashboard Cite

We propose an efficient P2P Grid resource management architecture using a hypercube network topology with additional neighbourhood links, which enhances resource discovery and scheduling of applications. The proposed architecture, the hypercubic P2P Grid presents the essential characteristics for efficient resource search self configuring, fault tolerance and abilities to handle dynamic attributes. The Hypercubic Peer to Peer Grid(HPGRID) system contains two layers. The top layer consists of Cubic Grid Peer(CGP) which transfers information in peer to peer technique. The bottom layer behaves like a traditional grid. Every CGP contains a header that contains the information about its own grid and a resource table. The definition for CGP parameters are described. An algorithm is presented for node arrival and node departure in the HPGRID system. This architecture can adapt to a complex, heterogeneous and dynamic resources of the grid environment, and has a better scalability. Performance evaluation is presented in terms of message forwarding scheme taking into consideration the optimal link added to hypercube which results in faster routing from any source to any destination in the CGP nodes.

show abstract

Extending GridSim with an architecture for failure detection

Abstract: Abstract

Cited by 28 publications

References 23 publications

Checkpointing in selected most fitted resource task scheduling in grid computing

Checkpointing in selected most fitted resource task scheduling in grid computing

Resource Failure Impact on Job Execution in Grid

HPGRID

Contact Info

Product

Resources

About