Time and cost-effective recovery mechanism for unhealthy resources in proactive fault tolerance framework

Author(s):  
T. Tamilvizhi ◽  
R. Surendran
Author(s):  
Anjushi Verma ◽  
Ankur Ghartaan ◽  
Tirthankar Gayen

Real time systems are those systems which must guarantee to response correctly within strict time constraint or within deadline. Failures can arise from both functional errors as well as timing bugs. Hence, it is necessary to provide temporal correctness of programs used in real time applications in addition to providing functional correctness. Although, there are several researches concerned with achieving fault tolerance in the presence of various functional and operational errors but many of them did not address the problem concerned with the timing bugs which is an important issue in real time systems. As for real time systems, many times it becomes a necessity for a given service to be delivered within the specified time deadline. Therefore, this paper reviews the existing approaches from the perspective of  real time systems to analyse the shortcomings of these approaches to  present a versatile and cost effective approach in the presence of timing bugs for providing fault tolerance to enhance the reliability of the real time software applications.


2000 ◽  
Vol 01 (04) ◽  
pp. 315-329 ◽  
Author(s):  
PETER KOK KEONG LOH ◽  
WEN JING HSU

Hierarchical interconnection networks with n-dimensional hypercube clusters can strike a balance between wide application suitability, size scalability as well as reliability. Cluster communications support for such networks must therefore be reliable and efficient without incurring large overheads. This paper proposes a reliable and cost-effective intra-cluster communications strategy for such a class of interconnection networks. The routing algorithm can tolerate up to (n - 1) component faults in the cluster and generates routes that are cycle-free and livelock-free. The message is guaranteed to be optimally (respectively, sub-optimally) delivered within a maximum of n (respectively, 2n - 1) hops. The message overhead incurred is one of the lowest reported for the specified fault tolerance level – with only a single n-bit routing vector accompanying the message to be communicated. Finally, routing hardware support may be simply achieved with standard components, facilitating integration with the host network.


Author(s):  
Anjushi Verma ◽  
Ankur Ghartaan ◽  
Tirthankar Gayen

Real time systems are those systems which must guarantee to response correctly within strict time constraint or within deadline. Failures can arise from both functional errors as well as timing bugs. Hence, it is necessary to provide temporal correctness of programs used in real time applications in addition to providing functional correctness. Although, there are several researches concerned with achieving fault tolerance in the presence of various functional and operational errors but many of them did not address the problem concerned with the timing bugs which is an important issue in real time systems. As for real time systems, many times it becomes a necessity for a given service to be delivered within the specified time deadline. Therefore, this paper reviews the existing approaches from the perspective of  real time systems to analyse the shortcomings of these approaches to  present a versatile and cost effective approach in the presence of timing bugs for providing fault tolerance to enhance the reliability of the real time software applications.


Sign in / Sign up

Export Citation Format

Share Document