ANALYTIC MODELING AND COMPARISONS OF STRIPING STRATEGIES FOR REPLICATED DISK ARRAYS

Data replication has been widely used as a means of increasing the dat a availability for critical applications in the event of disk failure, There are different ways of organizing the two copies of the data acr oss a disk array. This paper compares strategies for striping data of the two copies in the context of database applications, By keeping bot h copies active, we explore strategies that can take advantage of the additional copy to improve not only availability, but also performance during both normal and failure modes, We consider the effects of smal l and large stripe sizes on the performance of disk arrays with two ac tive copies of data under a mixed workload of queries and transactions with a skewed access pattern, We propose a dual (hybrid) striping str ategy which uses different stripe sizes for the two copies and a disk queuing policy designed to exploit this organization for optimal perfo rmance, An analytical model is devised for this scheme, by treating th e individual disks as independent, and applying an M/G/1 queuing model , Disks on which a large query scan is running are modeled by a variat ion of the queue with permanent customers, which leads to an iterative functional equation for the query scan delay distribution, A solution for this equation is given, The results are validated against simulat ions and are shown to match well. Comparison with uniform striping str ategies show that the dual striping scheme yields the most stable perf ormance in a variety of workloads, out-performing the uniform striping strategy using either mirrored or chained declustering under both nor mal and failure mode operations.