Learning from Before and After Recovery to Detect Latent Misconfiguration

Preventing system failure in cloud has become more important as a result of the prevalence of cloud use for mission-critical applications. One of the major causes of system failure in clouds is misconfiguration, as shown in recent studies. Hence, it is essential first to detect misconfiguration before it causes outage or degradation of service. Although cloud provides us flexible and auto-configurable infrastructure for expeditious implementation of systems, this also provokes frequent changes and complexity of the implementation, and leads to difficulty in verifying its configuration. In this paper, we present a method to detect latent misconfigurations. Our method is designed on the basis of our misconfiguration categorizations which gives us the capability to choose detection tactics by misconfiguration pattern, so the administrator can diagnose with less knowledge of configuration details. By generalized preprocessing of configuration data in which configuration files are input as-is, our method does not limit its target to a specific type of component. This enables us to diagnose system-wide misconfiguration while system configuration is frequently changed. The results of our experiment show that misconfiguration of a single configuration parameter is detected with over 90% F-measure.