IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
UP-0694890
(2007-03-30)
|
등록번호 |
US-7734669
(2010-06-29)
|
발명자
/ 주소 |
- Kottomtharayil, Rajiv
- Gokhale, Parag
- Lu, Jun
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
77 인용 특허 :
77 |
초록
▼
A method in a computer system for retrieving data from one of multiple copies of the data is provided, referred to as the data management system. The data management system receives a request identifying at least one data object to be accessed. Then, the data management system queries a metabase to
A method in a computer system for retrieving data from one of multiple copies of the data is provided, referred to as the data management system. The data management system receives a request identifying at least one data object to be accessed. Then, the data management system queries a metabase to locate data copies that contain the identified at least one data object, wherein the data copies are created from similar source data, and wherein for each data copy the metabase contains an indication of the availability of the copy relative to other copies. Next, the data management system determines one of the located data copies to use to access the identified at least one data object, wherein the determination is made based on the indicated availability contained in the metabase for each of the located data copies. Then, the data management system accesses the identified at least one data object using the determined one of the located data copies.
대표청구항
▼
We claim: 1. A method in a computer system for retrieving data from one of multiple copies of the data, wherein the computer system has a processor and memory, the method comprising: receiving a request identifying at least one data object to be accessed; querying, by the computer system, an index
We claim: 1. A method in a computer system for retrieving data from one of multiple copies of the data, wherein the computer system has a processor and memory, the method comprising: receiving a request identifying at least one data object to be accessed; querying, by the computer system, an index to locate two or more data copies that contain the identified at least one data object, wherein for each of the two or more data copies the index contains an indication of an availability of the data copy relative to other data copies, wherein the two or more data copies are respectively stored on two or more different and separate data storage devices, wherein the two or more different and separate data storage devices are substantially permanent or non-volatile storage devices, wherein the data storage devices are coupled to the computer system via a computer network, wherein a first indication of the availability of a first data copy includes a first indication related to a first time M for providing or accessing the at least one data object in response to an access request, and wherein a second indication of the availability of a second data copy includes a second indication related to a second time M+N for providing or accessing the at least one data object in response to the access request, where M and N are positive quantities of time; automatically determining one of the two or more data copies to use to access the identified at least one data object, wherein the determination is made based at least in part on the indicated availability contained in the index for each of the two or more data copies; and providing an access request for accessing the identified at least one data object using the determined one of the two or more data copies, wherein the access request is provided to one of the two or more different and separate data storage devices. 2. The method of claim 1 wherein the request specifies a purpose associated with the request and wherein the determination is made by automatically determining the priority of the purpose relative to the purpose of other scheduled requests to access the data, and wherein data copies having a higher availability are preferred for higher priority purposes. 3. The method of claim 1 wherein the index is distributed across multiple computer systems and wherein querying the index further comprises identifying one of the multiple systems to use to perform the query. 4. The method of claim 1 wherein the computer network includes a private computer network, and wherein, for data copies located on-site within the private computer network, the indicated availability contained in the index comprises an address of a computer system storing the data copy within a network topology of the private computer network, and wherein the determination is made based on the address of the computer system within the network topology. 5. The method of claim 1 wherein the request identifies an address of a requesting computer system within a network topology of an organization, wherein the indicated availability contained in the index comprises an address of a computer system storing the data copy within a network topology of the organization, and wherein the determination is made based on a proximity of the requesting computer system to each computer system storing each data copy. 6. The method of claim 1 wherein the indicated availability contained in the index comprises a media type used for storing each data copy and wherein the determination is made by preferring faster media types to slower media types for accessing the data, and wherein the media types include mounted disk and magnetic tape. 7. The method of claim 1 wherein the indicated availability contained in the index comprises a geographic location used for storing each data copy and wherein the determination is made by preferring on-site data copies over off-site data copies. 8. The method of claim 1 wherein the index further comprises properties identifying access control information associated with each data copy, and wherein the determination is made based on data copies to which a requesting user has permission to access. 9. The method of claim 1 wherein the data copies are created by first creating a primary copy of source data by accessing the source data, and then creating secondary copies of the source data using the primary copy and without accessing the source data. 10. The method of claim 1 wherein the data copies comprise data objects that contain application-specific data that has been processed, wherein the index includes properties describing the processed application-specific data, and wherein the determination is made based on the application-specific data stored within the index. 11. A computer system for managing multiple copies of data, comprising: a computing device configured for receiving data objects from applications that generate data objects, wherein the computing device includes at least a processor and a memory; a data management component configured for managing created copies of the generated data objects, wherein the created copies include a primary copy of the generated data objects, and one or more secondary copies of the generated data objects; a data storage component configured to store the primary copy of the generated data and the one or more secondary copies of the generated data; and a metabase component configured to store metadata information about each of the copies of the generated data including at least (a) a type of data storage media or data storage device on which each copy is stored, (b) data management operations performed to create the data copy, (c) a logical or geographic location of the copy, and (d) an indication of an availability of each copy, wherein a first indication of the availability of a first copy of the generated data includes a first indication related to a first time M for providing or accessing the first copy of the generated data in response to an access request, and wherein a second indication of the availability of a second copy of the generated data includes a second indication related to a second time M+N for providing or accessing the second copy of the generated data in response to the access request, where M and N are positive quantities of time, wherein the first copy of the generated data is stored on a first substantially permanent or non-volatile storage device, and wherein the second copy of the generated data is stored on a second substantially permanent or non-volatile storage device distinct from the first substantially permanent or non-volatile storage device. 12. The system of claim 11 wherein the data management component creates a secondary copy by accessing the primary copy and without accessing a computing device containing the generated data objects. 13. The system of claim 11 wherein the data management component creates a secondary copy by removing redundant instances of generated data contained within the primary copy. 14. The system of claim 11 wherein the data management component creates a secondary copy by encrypting the primary copy of the generated data. 15. The system of claim 11 wherein the data management component indexes the generated data within the primary copy while creating at least one of the one or more secondary copies, and stores an index of the generated data using the metabase component. 16. The system of claim 11 wherein the metabase component is further configured to receive requests to access copies of the generated data, and wherein the metabase component determines which copy to use to satisfy the request based at least in part on the type of media on which each copy is stored, data management operations performed to create each data copy, and the location of each data copy. 17. The system of claim 11 wherein the metabase component is further configured to receive requests to access copies of the generated data, and wherein the metabase component determines which copy to use to satisfy the request based at least in part on the information stored within the metabase. 18. A method in a computer system for retrieving data from one of multiple copies of the data, wherein the computer system has a processor and memory, the method comprising: receiving a request identifying at least one data object to be accessed; identifying multiple copies of the data object that satisfy the request; wherein each of the multiple data copies are respectively stored on one of multiple different and separate data storage devices, wherein the multiple different and separate data storage devices are substantially permanent or non-volatile storage devices, and wherein the multiple data storage devices are coupled to the computer system via a computer network, and for each identified copy, determining, by the computer system, an availability of the identified copy relative to the other identified copies, wherein a first availability of a first identified copy includes a first indication related to a first time M for accessing or providing the identified at least one data object in response to an access request, and wherein a second indication of the availability of a second identified copy includes a second indication related to a second time M+N for providing or accessing the identified at least one data object in response to the access request, where M and N are positive quantities of time; receiving a selection of one of the multiple identified copies to use for accessing the identified at least one data object, wherein the selection is based on the determined availability of the identified copies; and providing an access request for accessing the identified at least one data object using the selected copy, wherein the access request is provided to one of the multiple different and separate data storage devices. 19. The method of claim 18 wherein determining the availability of the copy comprises determining a type of media on which the copy is stored and identifying faster media as more available than slower media. 20. The method of claim 18 wherein determining the availability of the copy comprises determining a physical location where the copy is stored and identifying the copy as less available if it is stored at an offsite location than if it is stored at an onsite location. 21. The method of claim 18 wherein determining the availability of the copy comprises determining whether the copy is encrypted and if the copy is encrypted identifying the copy as less available than a decrypted copy. 22. The method of claim 18 wherein determining the availability of the copy comprises determining a tier of storage and type of hardware on which the copy is stored. 23. The method of claim 18 wherein determining the availability of the copy comprises determining a network topology and identifying the availability of the copy based on the subnet on which the copy is stored. 24. The method of claim 18 wherein determining the availability of the copy comprises determining a storage cell to which the copy belongs. 25. The method of claim 18 wherein determining the availability of the copy comprises determining one or more access rights associated with the request and identifying the copy as more available if it has a less restrictive access requirement. 26. The method of claim 18 wherein determining the availability of each copy comprises assigning an availability score to each copy and selecting an identified copy comprises selecting the copy having the greatest score. 27. The method of claim 18 wherein the request specifies a purpose associated with the request and wherein selecting an identified copy comprises selecting an identified copy based on a timeframe associated with the purpose associated with the request. 28. The method of claim 18 wherein the request is part of a storage operation to be performed on the identified at least one data object and wherein selecting an identified copy comprises selecting a copy on which to perform the storage operation. 29. The method of claim 18 wherein identifying multiple copies of the data object that satisfy the request comprises identifying older copies for which the identified at least one data object is up to date. 30. The method of claim 18 wherein identifying multiple copies of the data object that satisfy the request comprises determining one or more access restrictions of a requestor associated with the request and identifying copies that satisfy the one or more access restrictions. 31. The method of claim 18 wherein determining the availability of the copy comprises retrieving a predetermined availability indication from a metabase that stores metadata about each of the identified copies.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.