Pathname caching and protection of the root directory in a nested multilayer directory structure

• US 20060074925A1
• Filed: 09/21/2004
• Published: 04/06/2006
• Est. Priority Date: 09/21/2004
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Faibish, Sorin, Jiang, Xiaoye, Gupta, Uday K., Bixby, Peter C.
• Granted Patent: US 8,166,005 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/10 File systems; File servers
• CPC Class Codes: Y10S 707/966 Distributed

Abstract

Servers in a storage system store a nested multilayer directory structure, and a global index that is an abstract of the directory structure. The global index identifies respective portions of the directory structure that are stored in respective ones of the servers, and the global index identifies paths through the directory structure linking the respective portions. Upon performing a top-down search of the directory structure in response to a client request and finding that a portion of it is offline, the global index is searched to discover portions of the directory structure that are located below the offline portion. The global index may also identify the respective server storing each of the respective portions of the directory structure, and may indicate whether or not each of the respective portions of the directory structure is known to be offline.

Claims

1. A storage system comprising a plurality of servers for interconnection in a data network for servicing client requests for data, the servers storing a nested multilayer directory structure distributed among the servers and indexing the data,

wherein the storage system is programmed to store a global index to the nested multilayer directory structure, the global index is an abstract of the nested multilayer directory structure, the global index identifies respective portions of the nested multilayer directory structure that are stored in respective ones of the servers, and the global index identifies paths through the nested multilayer directory structure linking the respective portions of the nested multilayer directory structure.

2. The storage system as claimed in claim 1, which is further programmed to perform a top-down search of the nested multilayer directory structure in response to a client request, and upon finding that a portion of the nested multilayer directory structure is offline, to search the global index for portions of the nested multilayer directory structure that are located below the offline portion of the nested multilayer directory structure.

3. The storage system as claimed in claim 2, which is further programmed to perform the search by passing search requests to the servers containing portions of the nested multilayer directory structure that are located on a search path specified by the client request.

4. The storage system as claimed in claim 1, wherein the respective portions of the nested multilayer directory structure are respective file systems, and the global index includes pathnames of the respective portions of the nested multilayer directory structure.

5. The storage system as claimed in claim 4, which is further programmed to perform a search through the nested multilayer directory structure for a file specified by a pathname, and to access the global index to continue the search upon finding that a directory in the pathname is offline.

6. The storage system as claimed in claim 5, wherein the search is performed in response to a client request to open a file.

7. The storage system as claimed in claim 4, wherein the nested multilayer directory structure includes directories, some of the directories are named in the pathnames of the respective portions of the nested multilayer directory structure, some of the directories are not named in the pathnames of the respective portions of the nested multilayer directory structure, and the global index excludes the directories that are not named in the pathnames of the respective portions of the nested multilayer directory structure.

8. The storage system as claimed in claim 1, wherein the global index identifies the respective server storing each of the respective portions of the nested multilayer directory structure.

9. The storage system as claimed in claim 1, wherein the global index indicates whether or not each of the respective portions of the nested multilayer directory structure is known to be offline.

10. The storage system as claimed in claim 1, wherein more than one of the servers stores a respective copy of the global index.

11. The storage system of claim 1, wherein at least one of the servers is programmed to take over responsibility for maintenance of a respective portion of the nested multilayer directory structure by requesting permission from another of the servers having responsibility for maintenance of the respective portion of the multilayer directory structure, and taking over responsibility for maintenance of the respective portion of the nested multilayer directory structure upon obtaining permission from said another of the servers having responsibility for maintenance of the respective portion of the multilayer directory structure.

12. The storage system of claim 1, wherein at least one of the servers is programmed to take over responsibility for maintenance of a respective portion of the nested multilayer directory structure by requesting permission from another of the servers having responsibility for maintenance of the respective portion of the multilayer directory structure, and taking over responsibility for maintenance of the respective portion of the nested multilayer directory structure upon failing to receive a reply from said another of the servers having responsibility for maintenance of the respective portion of the multilayer directory structure.

13. The storage system as claimed in claim 1, wherein each of at least some of the servers is programmed to take over responsibility for maintenance of a respective portion of the nested multilayer directory structure by broadcasting an intention to take over responsibility for maintenance of the respective portion of the nested multilayer directory structure, receiving replies from the other of said at least some of the servers, resolving conflict in the replies, and taking over responsibility for maintenance of the respective portion of the nested multilayer directory upon resolving the conflict in favor of said each of at least some of the servers.

14. The storage system of claim 1, wherein at least one of the servers is comprised of a group of data mover computers coupled to a storage array storing a respective portion of the nested multilayer directory structure, and wherein the global index identifies the data mover computers in the group of data mover computers and identifies a particular one of the data mover computers in the group of data mover computers as having responsibility for maintenance of the respective portion of the nested multilayer directory structure.

15. The storage system as claimed in claim 1, wherein a root directory portion of the nested multilayer directory structure is stored in an active server that also stores the global index, network configuration information, and personality parameters of the primary server, and the storage system also includes a hot stand-by server kept in a state of readiness for failover from the active server by mirroring of the nested multilayer directory structure, the global index, the network configuration information, and the personality parameters of the active server into storage of the hot stand-by server.

16. A storage system comprising a plurality of servers for interconnection in a data network for servicing client requests for access to files, the servers storing a nested multilayer directory structure distributed among the servers and indexing the files,

wherein the storage system is programmed to store a global index to the nested multilayer directory structure, the global index is an abstract of the nested multilayer directory structure, the global index identifies respective portions of the nested multilayer directory structure in respective ones of the servers, the global index identifies paths through the nested multilayer directory structure linking the respective portions of the nested multilayer directory structure, and the global index excludes directories that are not on the paths through the nested multilayer directory structure linking the respective portions of the nested multilayer directory structure,

wherein the respective portions of the nested multilayer directory structure are file systems, and the global index includes pathnames of the respective portions of the nested multilayer directory structure, and

wherein the storage system is further programmed to respond to a client request to open a file specified by a pathname by performing a top-down search through the nested multilayer directory structure along a path identified by the pathname, and to access the global index to continue the search upon finding that a directory in the pathname is offline.

17. The storage system as claimed in claim 16, wherein the global index identifies the respective server storing each of the respective portions of the nested multilayer directory structure.

18. The storage system as claimed in claim 16, wherein the global index identifies whether or not each of the respective portions of the nested multilayer directory structure is known to be offline.

19. A method of operating a storage system having a plurality of servers interconnected in a data network for servicing client requests for data, the servers storing a nested multilayer directory structure distributed among the servers and indexing the data, said method comprising:

maintaining, in storage of the storage system, a global index to the nested multilayer directory structure, the global index being an abstract of the nested multilayer directory structure, the global index identifying respective portions of the nested multilayer directory structure in respective ones of the servers, and the global index identifying paths through the nested multilayer directory structure linking the respective portions of the nested multilayer directory structure; and

performing a top-down search of the nested multilayer directory structure in response to a client request, and upon finding that a portion of the nested multilayer directory structure is offline, searching the global index for portions of the nested multilayer directory structure that are located below the offline portion of the nested multilayer directory structure.

20. The method as claimed in claim 19, wherein the search is performed by passing search requests to the servers containing portions of the nested multilayer directory structure that are located on a search path specified by the client request.

21. The method as claimed in claim 19, wherein the respective portions of the nested multilayer directory structure are respective file systems, the global index includes pathnames of the respective portions of the nested multilayer directory structure, and the method includes perform a search through the nested multilayer directory structure in response to a client request to open a file specified by a pathname, and accessing the global index to continue the search upon finding that a directory in the pathname is offline.

22. The method as claimed in claim 19, wherein the global index identifies the respective server storing each of the respective portions of the nested multilayer directory structure, and the method includes accessing the global index during the search in order to pass search requests to the servers containing the portions of the nested multilayer directory structure that are located on a search path specified by the client request.

23. The method as claimed in claim 19, which includes one of the servers taking over responsibility for maintenance of a respective portion of the nested multilayer directory structure by broadcasting an intention to take over responsibility for maintenance of the respective portion of the nested multilayer directory structure, receiving replies from the other of said at least some of the servers, resolving conflict in the replies, and taking over responsibility for maintenance of the respective portion of the nested multilayer directory upon resolving the conflict in favor of said one of the servers.

24. A storage system comprising a plurality of data mover computers and at least one storage array coupled to the data mover computers for interconnection in a data network for servicing client requests for data stored in the storage array, the data mover computers being programmed for accessing a nested multilayer directory structure so that respective ones of the data mover computers manage access to respective portions of the nested multilayer directory structure,

wherein the storage system is programmed to store a global index to the nested multilayer directory structure, the global index is an abstract of the nested multilayer directory structure, the global index identifies the respective portions of the nested multilayer directory structure and the respective ones of the data mover computers that manage access to the respective portions of the nested multilayer directory structure, and the global index identifies paths through the nested multilayer directory structure linking the respective portions of the nested multilayer directory structure.

25. The storage system as claimed in claim 24, which is further programmed to perform a top-down search of the nested multilayer directory structure in response to a client request, and upon finding that a portion of the nested multilayer directory structure is offline, to search the global index for portions of the nested multilayer directory structure that are located below the offline portion of the nested multilayer directory structure.

26. The storage system as claimed in claim 25, which is further programmed to perform the search by passing search requests to the data movers managing access to portions of the nested multilayer directory structure that are located on a search path specified by the client request.

27. The storage system as claimed in claim 24, wherein the respective portions of the nested multilayer directory structure are respective file systems, and the global index includes pathnames of the respective portions of the nested multilayer directory structure.

28. The storage system as claimed in claim 27, which is further programmed to perform a search through the nested multilayer directory structure for a file specified by a pathname, and to access the global index to continue the search upon finding that a directory in the pathname is offline.

29. The storage system as claimed in claim 28, wherein the search is performed in response to a client request to open a file.

30. The storage system as claimed in claim 27, wherein the nested multilayer directory structure includes directories, some of the directories are named in the pathnames of the respective portions of the nested multilayer directory structure, some of the directories are not named in the pathnames of the respective portions of the nested multilayer directory structure, and the global index excludes the directories that are not named in the pathnames of the respective portions of the nested multilayer directory structure.

31. The storage system as claimed in claim 24, wherein the global index indicates whether or not each of the respective portions of the nested multilayer directory structure is known to be offline.

32. The storage system of claim 24, wherein at least one of the data mover computers is programmed to take over responsibility for managing access to a respective portion of the nested multilayer directory structure by requesting permission from another of the data move computers having responsibility for managing access to the respective portion of the multilayer directory structure, and taking over responsibility for managing access to the respective portion of the nested multilayer directory structure upon obtaining permission from said another of the data movers having responsibility for managing access to the respective portion of the multilayer directory structure.

33. The storage system of claim 24, wherein at least one of the data mover computers is programmed to take over responsibility for managing access to a respective portion of the nested multilayer directory structure by requesting permission from another of the data mover computers having responsibility for managing access to the respective portion of the multilayer directory structure, and taking over responsibility for managing access to the respective portion of the nested multilayer directory structure upon failing to receive a reply from said another of the data mover computers having responsibility for managing access to the respective portion of the multilayer directory structure.

34. The storage system as claimed in claim 24, wherein each of at least some of the data mover computers is programmed to take over responsibility for managing access to a respective portion of the nested multilayer directory structure by broadcasting an intention to take over responsibility for managing access to the respective portion of the nested multilayer directory structure, receiving replies from the other of said at least some of the data movers, resolving conflict in the replies, and taking over responsibility for managing access to the respective portion of the nested multilayer directory upon resolving the conflict in favor of said each of at least some of the data movers.