Fault tolerance is a key factor of industrial computing systems design. But in practical terms, these systems, like every commercial product, are under great financial constraints and they have to remain in operational state as long as possible due to their commercial attractiveness. This work provides an analysis of the instantaneous failure rate of these systems at the end of their life-time period. On the basis of this analysis, we determine the effect of a critical increase in the system failure rate and the basic condition of its existence. The next step determines the maintenance scheduling which can help to avoid this effect and to extend the system life-time in fault-tolerant mode.