Static Analysis, Code Transformation and Runtime Profiling for Self-healing

A self-healing application brings itself into a stable state after a failure put the software into an unstable state. For such self-healing software application, finding fix for a fault is a grand challenge. Asking the user to provide fixes for every fault is bad for productivity, especially when the users are non-savvy in technical aspect of computing. If failure scenarios come into existence, the user wants the runtime environment to handle those situations autonomically. This paper presents a new technique of finding self-healing actions by matching a fault scenario to already established fault models. By statically analyzing the code and transforming it in a way to allow the program to profile itself, it is possible to capture runtime parameters and execution pathways during runtime. The transformed program then can establish stable execution models that can be used later to match with an unstable execution scenario. Experimentation and results are presented that showed that even with additional overheads; this technique can prove beneficial for autonomically healing faults and reliving system administrators from repeated and routine troubleshooting situations. Index Terms-Self-adaptive application, Autonomic computing, Code transformation, Fault similarity.