IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0679863
(2003-10-06)
|
발명자
/ 주소 |
|
출원인 / 주소 |
- VERITAS Operating Corporation
|
대리인 / 주소 |
Meyertons Hood Kivlin Kowert &
|
인용정보 |
피인용 횟수 :
3 인용 특허 :
30 |
초록
▼
A system and method for maintaining storage object consistency across a distributed storage network including a migratable repository of last resort which stores a last or only remaining data replica that may not be deleted. The method includes the steps of monitoring data requests to the repository
A system and method for maintaining storage object consistency across a distributed storage network including a migratable repository of last resort which stores a last or only remaining data replica that may not be deleted. The method includes the steps of monitoring data requests to the repository of last resort, deciding whether to move the repository of last resort, and migrating the repository of last resort.
대표청구항
▼
1. A system comprising:a plurality of connected nodes; and a storage object, wherein each node of the plurality of connected nodes is configured to maintain a storage object routing table; wherein a first node of the plurality of connected nodes is further configured to: identify one or more neighbo
1. A system comprising:a plurality of connected nodes; and a storage object, wherein each node of the plurality of connected nodes is configured to maintain a storage object routing table; wherein a first node of the plurality of connected nodes is further configured to: identify one or more neighbor nodes of the first node; send a message to each neighbor node of the one or more neighbor nodes, indicative of an availability of the storage object at the first node; and wherein each neighbor node of the one or more neighbor nodes is further configured to: create an entry for the storage object within a storage object routing table at the neighbor node in response to the message; store an indication of a path to the first node within the entry. 2. The system as recited in claim 1, wherein the message is sent during a publish process for the storage object.3. The system as recited in claim 1, wherein the one or more neighbor nodes are selected by the first node from a spanning tree for the plurality of connected nodes.4. The system as recited in claim 3, wherein the plurality of connected nodes comprise three or more connected nodes, wherein each neighbor node of the one or more neighbor nodes is further configured to propagate a message indicative of the availability of the storage object to an additional node selected from the spanning tree.5. The system as recited in claim 1, wherein the first node is a repository of last resort for the storage object.6. The system as recited in claim 1, wherein the storage object is a file.7. The system as recited in claim 1, wherein the storage object is an extent.8. The system as recited in claim 1, wherein the storage object is a data block.9. The system as recited in claim 1, wherein each node of the plurality of connected nodes comprises a cluster of connected devices, wherein each device of the cluster of connected devices includes at least a processor, a disk and a network interface.10. The system as recited in claim 1, wherein the message is sent over a virtual channel.11. The system as recited in claim 1, wherein the message is sent over a TCP/IP packet-switched network.12. The system as recited in claim 1, wherein the message is sent using partite addressing.13. The system as recited in claim 1, wherein the message is sent using a multicast operation.14. The system as recited in claim 1, further comprising a plurality of additional storage objects, wherein the storage object routing table at each node of the plurality of connected nodes includes a plurality of entries, and wherein each entry of the plurality of entries includes an indication of a path towards a repository of last resort for a corresponding storage object.15. The system as recited in claim 14, wherein each entry of the plurality of entries includes an indication of a path towards a shared copy of the corresponding storage object.16. The system as recited in claim 14, wherein each entry of the plurality of entries includes an indication of a path towards an exclusive owner of the corresponding storage object.17. The system as recited in claim 14, wherein each entry of the plurality of entries includes an indication of a validity of a cached copy of the corresponding storage object.18. A method comprising:maintaining a storage object routing table at each node of a plurality of connected nodes; identifying one or more neighbor nodes of a first node of the plurality of connected nodes; sending a message to each neighbor node of the one or more neighbor nodes from the first node, indicative of an availability of the storage object at the first node; creating an entry for the storage object within a storage object routing table at each neighbor node of the one or more neighbor nodes; and storing an indication of a path to the first node within the entry. 19. The method as recited in claim 18, wherein the message is sent as part of a publish process for the storage object.20. The method as recited in claim 18, wherein the one or more neighbor nodes are selected by the first node from a spanning tree for the plurality of connected nodes.21. The method as recited in claim 18, wherein the first node is a repository of last resort for the storage object.22. The method as recited in claim 18, wherein the storage object is a file.23. The method as recited in claim 18, wherein the storage object is an extent.24. The method as recited in claim 18, wherein the storage object is a data block.25. The method as recited in claim 18, wherein each node of the plurality of connected nodes comprises a cluster of connected devices, wherein each device of the cluster of connected devices includes at least a processor, a disk and a network interface.26. The method as recited in claim 18, wherein the message is sent over a virtual channel.27. The method as recited in claim 18, wherein the message is sent over a TCP/IP packet-switched network.28. The method as recited in claim 18, wherein the message is sent using partite addressing.29. The method as recited in claim 18, wherein the storage object routing table at each node of the plurality of connected nodes includes a plurality of entries, and wherein each entry of the plurality of entries includes an indication of a path towards a repository of last resort for a corresponding storage object.30. The method as recited in claim 29, wherein each entry of the plurality of entries includes an indication of a path towards a shared copy of the corresponding storage object.31. The method as recited in claim 29, wherein each entry of the plurality of entries include an indication of a path towards an exclusive owner of the corresponding storage object.32. The method as recited in claim 29, wherein each entry of the plurality of entries include an indication of a validity of a cached copy of the corresponding storage object.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.