Automated Management of Disaster Recovery Systems Using Adaptive Scheduling

Disaster recovery (DR) is an extremely important solution for all organizations. All DR solutions have a myriad of solution specific tweaks, however, each of them have a set of common underlying routine processes/tasks, namely, i) data backup/archive, ii) secondary/offsite replica generation, iii) data migration across storage pools, iv) metadata expiration and v) tape-reclamation. A complete solution needs to judiciously run the above mentioned tasks in the most effective manner. The problem of architecting a balanced schedule considering the constraints of time and bandwidth along with the relative importance of each process/task is a non-trivial one. Designing of schedules is a labor intensive task and often the schedules are far from optimal. In this work we have proposed a solution which automatically generates the most beneficial schedule based on an optimization problem with resource outage risk minimization as the objective and available time and resource capacities as the constraints. The solution is driven by models of the common underlying processes and their relative importance to keep the service up and running.