Zodiac: Efficient impact analysis for storage area networks

Abstract

Currently, the fields of impact analysis and policy based management are two important storage management topics that are not being treated in an integrated manner. Policy-based storage management is being adopted by most storage vendors because it lets system administrators specify high level policies and moves the complexity of enforcing these policies to the underlying management software. Similarly, proactive impact analysis is becoming an important aspect of storage management because system administrators want to assess the impact of making a change before actually making it. Impact analysis is increasingly becoming a complex task when one is dealing with a large number of devices and workloads. Adding the policy dimension to impact analysis (that is, what policies are being violated due to a particular action) makes this problem even more complex. In this paper we describe a new framework and a set of optimization techniques that combine the fields of impact analysis and policy management. In this framework system administrators define policies for performance, interoperability, security, availability, and then proactively assess the impact of desired changes on both the system observables and policies. Additionally, the proposed optimizations help to reduce the amount of data and the number of policies that need to be evaluated. This improves the response time of impact analysis operations. Finally, we also propose a new policy classification scheme that classifies policies based on the algorithms that can be used to optimize their evaluation. Such a classification is useful in order to efficiently evaluate user-defined policies. We present an experimental study that quantitatively analyzes the framework and algorithms on real life storage area network policies. The algorithms presented in this paper can be leveraged by existing impact analysis and policy engine tools.