Realizing Multilevel Snapshots in Dynamically Changing Virtualized Storage Environments

The capability of making an immediate point-in-time copy of large data sets has become an essential feature for storage management solutions. These copies, also called snapshots, are required for backup purpose, recovery, and to work on real data for testing applications. Depending on an application’s needs, different capabilities, like one-level read-only snapshots or rewritable ones are required. Besides their functionality, snapshot implementations are also differentiated with respect to their location and how they enable different stages of access to the duplicated data. Significant problems, like preserving consistency, arise when using snapshots in distributed environments with multiple accessing servers, and in which the configuration might change at any time. This paper describes a useful way to integrate a snapshot implementation that provides multiple levels of data access. We introduce a consistency preserving protocol for the storage virtualization solution V:DRIVE and present benchmark results for various snapshot scenarios.