SCADY: Scalable and Dynamic Grid Computing

In this book, the author highlighted the need of a middle ware tool that can enhance the performance of computing. Several Grid Architectures and Middle ware API's are discussed. Findings from several research papers are given. Based on these it was found that It is not easy to provide a dynamically configurable environment that can help in ensuring that the computation does not fail even if any resource fails. To solve this problem, the author constructed a small grid toolkit - SCADY (Scalable & Dynamic) and tried to add and extend the existing API of the available middle ware. A Resource Allocation algorithm based on CPU usage is given. Tasks are allocated according to the CPU usage. This usage for each resource is checked regularly and if a resource is found to be failed, the task is allocated to the next available resource with less CPU load. A caching algorithm using write-through method is also given that helps in achieving high performance computing. At the end, based on result analysis of different grid middleware, it is concluded that Scady provides better performance in Grid computing.