Collaborative restore in a networked storage system

摘要

A storage system according to certain embodiments includes a client-side signature repository that includes information representative of a set of data blocks stored in primary storage. During restore operations, the system can use the client-side signature repository to identify data blocks located in primary storage. The system can also use the client-side signature repository to identify multiple locations within primary storage where instances of some of the data blocks to be restored are located. Accordingly, during a restore operation of one client computing device, the system can source a data block to be restored to the client computing device from another client computing device that is in primary storage.

主权项

1. A method of restoring data to a first client computing device located in a primary storage subsystem using data blocks of primary data residing in a data store associated with a second client computing device located in the primary storage subsystem, the method comprising:
maintaining in a signature repository, data block signatures corresponding to data blocks of primary data and location information of the data blocks of primary data within the primary storage subsystem, the data blocks of primary data being generated by one or more corresponding source applications executing on at least one client computing device of a plurality of client computing devices located within a primary storage subsystem, the data blocks of primary data for each respective client computing device of the plurality of client computing devices stored in a native format of the one or more corresponding source applications in a data store associated with the respective client computing device, wherein one or more secondary copy data blocks of the data blocks of primary data are generated from the data blocks of primary data during a backup operation; receiving a set of data block signatures corresponding to a set of secondary copy data blocks maintained in a secondary storage subsystem, the set of secondary copy data blocks corresponding to a previous version of at least one file of primary data of a first client computing device of the plurality of client computing devices and being stored in a non-native format of the one or more corresponding source applications; querying, using one or more processors, the signature repository to identify at least a first group of data block signatures of the received set of data block signatures that reside in the signature repository, the first group of data block signatures corresponding to a first group of data blocks of primary data stored in the data store associated with a second client computing device of the plurality of client computing devices; retrieving the first group of data blocks of primary data from the data store associated with the second client computing device, wherein the first group of data blocks form at least a portion of one or more files stored in the native format of the one or more corresponding source applications; identifying a second group of data blocks of the of the set of secondary copy data blocks that do not reside in the primary storage subsystem; retrieving from secondary storage, the second group of data blocks; and restoring the set of secondary copy data blocks to the data store associated with the first client computing device using at least the first group of data blocks of primary data retrieved from the second client computing device and the second group of data blocks retrieved from the secondary storage.