Experimental validation of distributed recovery block

Presents the experimental validation of distributed execution of recovery blocks, in short distributed recovery blocks (DRB). The experiment was conducted on a tightly coupled network (TCN) and a time-critical application was used as a testbed for the experiment. The concept of the DRB is the combination of distributed processing and RB (recovery block). It is also an approach for unified treatment of both hardware and software faults. The primary objective of this experiment was to demonstrate the efficiency of the DRB scheme in a tightly coupled real-time distributed computing environment. This experiment required employing the DRB scheme in an application program and measuring its impact on the system performance. The main interest in measurements is to find the time overhead of the DRB scheme, i.e., the overhead of the error detection and recovery activity.<
>