Architectures for controller based CDP

Continuous Data Protection (CDP) is a recent storage technology which enables reverting the state of the storage to previous points in time. We propose four alternative architectures for supporting CDP in a storage controller, and compare them analytically with respect to both write performance and space usage overheads. We describe exactly how factors such as the degree of protection granularity (continuous or at fixed intervals) and the temporal distance distribution of the given workload affect these overheads. Our model allows predicting the CDP overheads for arbitrary workloads and concluding the best architecture for a given scenario. Our analysis is verified by running a prototype CDP enabled block device on both synthetic and traced workloads and comparing the outcome with our analysis. Our work is the first to consider how performance is affected by varying the degree of protection granularity, both analytically and empirically. In addition it is the first to precisely quantify the natural connection between CDP overheads and a workload's temporal locality. We show that one of the architectures we considered is superior for workloads exhibiting high temporal locality w.r.t. granularity, whereas another of the architectures is superior for workloads exhibiting low temporal locality w.r.t. granularity. We analyze two specific workloads, an OLTP workload and a file server workload, and show which CDP architecture is superior for each workload at which granularities.