On affirmative adaptive failure detection

Fault detection methodology is a crucial part in providing a scalable, dependable and high availability of grid computing environment. The most popular technique that used in detecting fault is heartbeat mechanism where it monitors the grid resources in a very short interval. However, the heartbeat...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohd Noor, Ahmad Shukri, Mat Deris, Mustafa, Herawan, Tutut, Nor Hassan, Mohamad
Format: Conference or Workshop Item
Published: 2012
Subjects:
Online Access:http://dx.doi.org/10.1007/978-3-642-33065-0_13
http://dx.doi.org/10.1007/978-3-642-33065-0_13
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fault detection methodology is a crucial part in providing a scalable, dependable and high availability of grid computing environment. The most popular technique that used in detecting fault is heartbeat mechanism where it monitors the grid resources in a very short interval. However, the heartbeat mechanism-based technique for fault detection suffers from weaknesses of either fast detection with low accuracy or completeness in detecting failures with a lengthy timeout. In this paper, we propose Affirmative Adaptive Failure Detection (AAFD). In this technique, the integration of newly proposed failure detection algorithm and the ping service is essential not only for dynamically improving certainty level of accuracy, but it is also very significant in verifying the aliveness of a site for strong completeness failure detection and reduces waiting time. The model outperforms the existing techniques by 18% to 39% in term of algorithm performance. On the average, AAFD detection is about 30% better than other detection algorithms.