IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0324817
(2011-12-13)
|
등록번호 |
US-8954446
(2015-02-10)
|
발명자
/ 주소 |
- Vijayan Retnamma, Manoj Kumar
- Attarde, Deepak Raghunath
- Joshi, Hetalkumar N.
|
출원인 / 주소 |
|
대리인 / 주소 |
Knobbe, Martens, Olson & Bear, LLP
|
인용정보 |
피인용 횟수 :
29 인용 특허 :
129 |
초록
▼
A storage system according to certain embodiments includes a client-side repository (CSR). The CSR may communicate with a client at a higher data transfer rate than the rate used for communication between the client and secondary storage. During copy operations, for instance, some or all of the data
A storage system according to certain embodiments includes a client-side repository (CSR). The CSR may communicate with a client at a higher data transfer rate than the rate used for communication between the client and secondary storage. During copy operations, for instance, some or all of the data being backed up or otherwise copied to secondary storage is stored in the CSR. During restore operations, copies of the data stored in the CSR is accessed from the CSR instead of from secondary storage, improving performance. Remaining data blocks not stored in the CSR can be restored from secondary storage.
대표청구항
▼
1. A method of modifying a client-side repository usable for restore operations in a de-duplicated storage system, the method comprising: performing a secondary copy operation with a storage manager that copies a plurality of data blocks associated with primary storage in a client system to secondar
1. A method of modifying a client-side repository usable for restore operations in a de-duplicated storage system, the method comprising: performing a secondary copy operation with a storage manager that copies a plurality of data blocks associated with primary storage in a client system to secondary storage located remotely from the primary storage, wherein the client system communicates with the secondary storage via a wide area network;during performance of the secondary copy operation, creating a deduplication hash signature for each of the plurality of data blocks according to a deduplication scheme;associating a first group of a plurality of client computers in the client system with a client-side repository that comprises at least computer memory, wherein the first group has a first storage priority in the client-side repository, wherein the client-side repository is different than the secondary storage, and wherein the client system communicates with the client-side repository over a local area network;associating a second group of the plurality of client computers in the client system with the client-side repository, wherein the second group has a second storage priority in the client-side repository that is lower in priority than the first storage priority associated with the first group;during performance of the secondary copy operation, populating the client-side repository with at least a portion of the plurality of data blocks copied from the first and second groups of the plurality of client computers to the secondary storage based at least in part on the first and second storage priorities; during performance of the secondary copy operation, populating the client-side repository with a first copy of the deduplication hash signatures corresponding to the portion of the plurality of data blocks that are stored in the client-side repository;during performance of the secondary copy operation, populating an index that comprises at least computer memory, the index in communication with the storage manager with a second copy of the deduplication hash signatures corresponding to the portion of the plurality of data blocks that are stored in the client-side repository;for at least one restore operation in which restore data blocks are restored to at least one client computer of the plurality of client computers: accessing with the storage manager the second copy of the deduplication hash signatures in the index to determine which restore data blocks are stored in the client-side repository,when the second copy of the deduplication hash signatures in the index indicate which restore data blocks are in the client-side repository, using the first copy of the deduplication hash signatures to access the restore data blocks in the client-side repository via the local area network,when the second copy of the deduplication hash signatures in the index indicate which restore data blocks are not stored in the client-side repository, using the storage manager to access the restore data blocks from the secondary storage via the wide area network;determining a usage metric relating to the usage of the client-side repository by the first group and second group of the plurality of client computers; andbased at least on the metric, increasing the use of the client-side repository during restores by changing the second storage priority of at least one of the second group of client computers to have the first storage priority of the first group of the plurality of client computers. 2. The method of claim 1, wherein the usage metric is related to at least one of an amount of data transmitted between the client-side repository and the client system during the at least one restore operation and an amount of data transmitted between the client system and the secondary storage during the at least one restore operation. 3. The method of claim 1, wherein the usage metric is related to at least one of network bandwidth utilization during the at least one restore operation and an amount of time consumed during the at least one restore operation. 4. The method of claim 1, wherein queries are sent to the client-side repository only for the restore data blocks corresponding to the first group of the plurality of client computers. 5. The method of claim 4, wherein the queries are sent only for the restore data blocks that were copied to the secondary storage within a predetermined time period prior to the restore operation. 6. The method of claim 4, wherein at least some of the queries are transmitted to the client-side repository together in groups of more than one query. 7. The method of claim 1, wherein determining which of the plurality of data blocks are stored in the client-side repository comprises comparing the deduplication signatures stored in the client-side repository with deduplication signatures received during the at least one restore operation. 8. A storage system comprising: a storage manager that communicates with primary storage in a client system wherein the primary storage stores a plurality of data blocks created by the client system, wherein the storage manager performs at least secondary copy operations associated with the plurality of data blocks;secondary storage located remotely from the primary storage, the secondary storage in communication with the client system via a wide area network, the secondary storage stores in response to the secondary copy operation, a secondary copy of the plurality of data blocks according to a deduplication scheme that creates a deduplication hash signature for each of the data blocks;a client-side repository that comprises at least computer memory, the client-side repository is in communication with the client system via a local area network, the client-side repository further comprising: a data repository that stores during performance of the secondary copy operation at least a portion of the plurality of data blocks copied from the plurality of client computers to secondary storage according to the deduplication scheme,a deduplication hash signature repository that stores during performance of the secondary copy operation, a first copy of the deduplication hash signatures corresponding to the portion of the plurality of data blocks stored in the data repository, the data repository and the deduplication hash signature repository remote from the secondary storage;a first group of the plurality of client computers in the client system associated with the client-side repository, wherein the first group has a first storage priority in the client-side repository;second group of the plurality of client computers in the client system associated with the client-side repository, wherein the second group has a second storage priority in the client-side repository that is lower in priority than the first storage priority associated with the first group;wherein during the performance of the secondary copy operation, the storage manager directs at least a portion of the plurality of data blocks copied from the first and second groups of the plurality of client computers to the client repository based at least in part on the first and second storage priorities;an index comprises at least computer memory, the index in communication with the storage manager, wherein during the secondary copy operation the index is populated with a second copy of the deduplication hash signatures corresponding to the portion of the plurality of data blocks stored in the data repository;wherein the storage manager is configured to: monitor at least one restore operation, in which restore data blocks are restored to at least one client computer of the client system;access the second copy of the deduplication hash signatures in the index to determine which restore data blocks are stored in the client-side repository;when the second copy of the deduplication hash signatures indicate that the restore data blocks are stored in the client-side repository, using the first copy of the deduplication hash signatures in the deduplication hash signature repository to retrieve the restore data blocks from the client-repository via the local area network;when the second copy of the deduplication hash signatures indicate that the restore data blocks are not stored in the client-side repository, the storage manager retrieves the restore data blocks from secondary storage via the wide area network;based at least on the monitoring, determine a usage metric associated with the amount of use of the client-side repository; andbased at least on the determined usage metric, increasing the use of the client-side repository during restores by changing the second storage priority of at least one of the second group of client computers to have the first storage priority of the first group of plurality of client computers . 9. The storage system of claim 8, wherein the usage metric is related to at least one of an amount of data transmitted between the client-side repository and the client system during the at least one restore operation and an amount of data transmitted between the client system and the secondary storage during the at least one restore operation. 10. The storage system of claim 8, wherein the usage metric is related to at least one of network bandwidth utilization during the at least one restore operation and an amount of time consumed during the at least one restore operation. 11. The storage system of claim 8, wherein the client system communicates with the client-side repository via a local area network and the client system communicates with the secondary storage via a wide area network. 12. The storage system of claim 8, wherein queries are sent to the client-side repository to determine which only for the portion of the restore data blocks corresponding to the first group of the plurality of client computers. 13. The storage system of claim 12, wherein the queries are sent only for the restore data blocks that were copied to the secondary storage within a predetermined time period prior to the restore operation. 14. The storage system of claim 12, wherein at least some of the queries are transmitted to the client-side repository together in groups of more than one query.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.