Key points are not available for this paper at this time.
Two complementary methods which are employed in order to assure reliable computing are fault-intolerance and fault-tolerance. Fault-intolerance depends on the elimination of the causes of unreliability prior to the start of the computing process while fault-tolerance employs protective redunuancy during the computing process in order to detect and to correct unreliable functioning. A balanced allocation of reliability resources between the two methods appears to offer the best practical solution. The paper reviews current fault-tolerance practices in system architecture and discusses their relevance to software systems.
Algirdas Avižienis (Wed,) studied this question.