Recovering multi-volume data sets during volume recovery

Abstract

A system for recovering multi-volume data sets that are stored in one or more volumes that have failed with a substantial level of automation and flexibility. Data can be recovered from backup storage when multiple volumes fail, as in a 'catastrophic' data loss. For each volume, all data sets partially or completely stored on the selected volume prior to a failure of that volume are identified. Each single-volume data set stored on the selected volume prior to the failure is restored from backup storage. Upon identifying a multi-volume data set whose beginning segment was stored on the selected volume, the entire data set is restored. Data can also be recovered from backup storage when a particular volume fails, such as after a 'head crash.' All data sets partially or completely stored on the selected volume prior to a failure of that volume are identified. Each single volume data set stored on the selected volume prior to the failure is recovered from backup storage. For each multi-volume data set having a segment stored on the selected volume prior to the failure, a predetermined message is issued to a human operator. Alternatively, multi-volume data sets are recovered if consistent. Otherwise, if valid data has been lost, a warning message is issued.