viaiz_dsd06

Mapping of Fault-Tolerant Applications with Transparency on Distributed Embedded Systems

Viacheslav Izosimov Author homepage
 
Paul Pop Author homepage
Petru Eles Author homepage
 
Zebo Peng Author homepage

9th Euromicro Conference on Digital System Design (DSD 2006), Cavtat near Dubrovnik, Croatia, August 30 - September 1, 2006, pp. 313-320

ABSTRACT
In this paper we present an approach for the mapping optimization of fault-tolerant embedded systems for safety-critical applications. Processes and messages are statically scheduled. Process re-execution is used for recovering from multiple transient faults. We call process recovery transparent if it does not affect operation of other processes. Transparent recovery has the advantage of fault containment, improved debugability and less memory needed to store the fault-tolerant schedules. However, it will introduce additional delays that can lead to violations of the timing constraints of the application. We propose an algorithm for the mapping of fault-tolerant applications with transparency. The algorithm decides a mapping of processes on computation nodes such that the application is schedulable and the transparency properties imposed by the designer are satisfied. The mapping algorithm is driven by a heuristic that is able to estimate the worst-case schedule length and indicate whether a certain mapping alternative is schedulable.


Related files:
viaiz_dsd06.corrected.pdf, Adobe Acrobat portable document


[IPEP06] Viacheslav Izosimov, Paul Pop, Petru Eles, Zebo Peng, "Mapping of Fault-Tolerant Applications with Transparency on Distributed Embedded Systems", 9th Euromicro Conference on Digital System Design (DSD 2006), Cavtat near Dubrovnik, Croatia, August 30 - September 1, 2006, pp. 313-320
( ! ) perl script by Giovanni Squillero with modifications from Gert Jervan   (v3.1, p5.2, September-2002-)
Last modified on Monday December 04, 2006 by Gert Jervan