Design Adn Implementation Of Extensive Availability Modeling Tool For Storage System

With the rapid development of information technology, the information resources on the network has been explosivly growing, it indicates that the big data era has come.The massive storage system is the most important part in storing big data.Not only does it have rigour requirement on capacity and performance, but it is also necessary to be highly available.So people have paid more and more attention to the research on the availability of massive storage systems.It’s a popular method to use availability models to estimate the availability of massive storage systems.And the availability assessment tools is necessary. In this paper, we do a lot of research on some classic availability assessment tools home and abroad,and found that classic tools does not support the top-down stepwise refinement of hierarchical modeling method,which lead to lack of ease in use.Besides,they haven’t done the corresponding optimization according to the characteristics of the storage system. In this paper, we design and implement an extensive availability modeling tool for storage.It support the hierarchical modeling method combining reliability block diagram with Markovmodel, and take the characteristics of storage system into account.It also covers the influence of failure rate, maintenance rate, fault detection time, coverage ratio, maintenance personnel response time and so on.The tool is divided into six modules: the main control module is responsible for controlling the execution of other modules, providing the user graphical interface. The graphical drawing module and parameter setting module are responsible for the drawing reliability block diagram and setting reliability and availability parameters. The model generating module is responsible for converting the layer data into internal definiting data structure. The availability calculation module is responsible for calculating the availability of each module and the system. The parameters sensitivity analysis module can analyze the failure sensitive section of the components and provide reference information for the upgrading and improvement of the system components in the future.Finally, we used the tool to model and calculate the IBM’s XIV high end disk storage system’s availability, and analyzed and explained the experimental results in detail.