Redundant multi-processor and logical processor configuration for a file server

• US 7,028,218 B2
• Filed: 12/02/2002
• Issued: 04/11/2006
• Est. Priority Date: 12/02/2002
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Schwarm, Stephen C., Machardy, Earle T. Jr.
• Primary Examiner(s): Beausoliel, Robert
• Assistant Examiner(s): GUYTON, PHILIP A
• Application Number:
  US10/308,161
• Publication Number:
  US 20040153749A1
• Time in Patent Office: 1,226 Days
• Field of Search: 714/4, 714/11, 714/13, 714/12, 711/162
• US Class Current: 714/11
• CPC Class Codes: G06F 11/2028 eliminating a faulty processor or activating a spare
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• CPC Class Codes: G06F 11/2041 with more than one idle spare processing component
• CPC Class Codes: G06F 11/2043 where the redundant components share a common memory address space
• CPC Class Codes: G06F 11/2046 where the redundant components share persistent storage G06F11/2043 takes precedence

Abstract

A redundant file server includes at least two dual processor boards. Each physical processor has two logical processors. The first logical processor of the first physical processor of each board executes storage system code under the Microsoft NT™ operating system. The second logical processor of the first physical processor of each board executes control station code under the Linux operating system. The first logical processor of the second physical processor of each board executes data mover code. The second logical processor of the second physical processor of each board is kept in a stand-by mode for assuming data mover functions upon failure of the first logical processor of the second physical processor on the first or second board.

Claims

1. A redundant file server comprising at least a first processor board and a second processor board, each of the first and second processor boards being programmed to perform file server functions, the first processor board being programmed to assume the file server functions of the second processor board upon failure of the second processor board, and the second processor board being programmed to assume the file server functions of the first processor board upon failure of the first processor board,

wherein each of the first and second processor boards includes at least a first physical processor and a second physical processor,

wherein at least the first physical processor on each of the first and second processor boards has an on-chip cache, multiple functional units, and more than one processor register set sharing the on-chip cache and the multiple functional units to provide a first logical processor and a second logical processor;

wherein the first logical processor of the first physical processor of each of the first and second processor boards is programmed to perform storage functions including logical-to-physical mapping and access to multiple storage devices, the second logical processor of the first physical processor of each of the first and second processor boards is programmed to execute file server control functions, and the second physical processor of each of the first and second processor boards is programmed to execute data mover functions including network communication with clients and file system access; and

wherein the first logical processor of the first physical processor of the first processor board is programmed to assume the storage system functions of the first logical processor of the first physical processor of the second processor board upon failure of the first logical processor of the first physical processor of the second processor board; and

the first logical processor of the first physical processor of the second processor board is programmed to assume the storage system functions of the first logical processor of the first physical processor of the first processor board upon failure of the first logical processor of the first physical processor of the first processor board;

wherein the second logical processor of the first physical processor of the first processor board is programmed to assume the file server control functions of the second logical processor of the first physical processor of the second processor board upon failure of the second logical processor of the first physical processor of the second processor board; and

the second logical processor of the first physical processor of the second processor board is programmed to assume the file server control functions of the second logical processor of the first physical processor of the first processor board upon failure of the second logical processor of the first physical processor of the first processor board; and

wherein the second physical processor of the first processor board is programmed to assume the data mover functions of the second physical processor of the second processor board upon failure of the second physical processor of the second processor board, and the second physical processor of the second processor board is programmed to assume the data mover functions of the second physical processor of the first processor board upon failure of the second physical processor of the first processor board.

2. The redundant file server as claimed in claim 1, which includes multiple dual-port disk drives, each of the multiple dual-port disk drives having a first port linked to the first processor board for data transmission to the first processor board, and a second port linked to the second processor board for data transmission to the second processor board.

3. The redundant file server as claimed in claim 1, wherein the first and second processor boards are dual processor boards.

4. The redundant file server as claimed in claim 1, wherein the first logical processor of the first physical processor of each of the first and second processor boards executes storage system code under a first operating system, and the second logical processor of the first physical processor of each of the first and second processor boards executes file server control code under a second operating system, and the second operating system is different from the first operating system.

5. The redundant file server as claimed in claim 1, wherein the first logical processor of the first physical processor of each of the first and second processor boards executes storage system code under the Microsoft NT (trademark) operating system, and the second logical processor of the first physical processor of each of the first and second processor boards executes file server control code under the Linux operating system.

6. The redundant file server as claimed in claim 1, wherein the first processor board has random access memory for containing a first storage cache, and the second processor board has random access memory for containing a second storage cache, and the first logical processors of the first physical processors of the first and second processor boards are programmed to write new storage cache data to both the first storage cache and the second storage cache so that the new storage cache data is not lost upon failure of either the first storage cache or the second storage cache.

7. The redundant file server as claimed in claim 1, wherein the file server control functions include recovery from failure in the redundant file server, configuration of the redundant file server, and collection and reporting of loading statistics and failure information of the redundant file server.

8. The redundant file server as claimed in claim 1, wherein the file server functions include establishing a master-slave relationship between the second logical processor of the first physical processor of the first processor board and the second logical processor of the first physical processor of the second processor board.

9. A redundant file server comprising at least a first processor board and a second processor board, each of the first and second processor boards being programmed to perform file server functions, the first processor board being programmed to assume the file server functions of the second processor board upon failure of the second processor board, and the second processor board being programmed to assume the file server functions of the first processor board upon failure of the first processor board,

wherein each of the first and second processor boards includes a physical processor,

wherein the physical processor on each of the first and second processor boards has an on-chip cache, multiple functional units, and more than one processor register set sharing the on-chip cache and the multiple functional units to provide a first logical processor and a second logical processor;

wherein the first logical processor of the physical processor of each of the first and second processor boards is programmed to execute file server code under a first operating system, and the second logical processor of the physical processor of each of the first and second processor boards is programmed to execute file server code under a second operating system, and the second operating system is different from the first operating system.

10. The redundant file server as claimed in claim 9, wherein the first operating system is the Microsoft NT (trademark) operating system, and the second operating system is the Linux operating system.

11. The redundant file server as claimed in claim 9, wherein the first logical processor of the physical processor of each of the first and second processor boards is programmed to execute file server functions including storage system functions, and the second logical processor of the physical processor of each of the first and second processor boards is programmed to execute file server functions including file server control functions.

12. The redundant file server as claimed in claim 11, wherein the storage system functions include access to a storage system cache, logical-to-physical mapping, staging of data to the storage system cache from storage devices, and write-back from the storage system cache to the storage devices, and

wherein the file server control functions include recovery from failure in the redundant file server, configuration of the redundant file server, and collection and reporting of loading statistics and failure information of the redundant file server.

13. A redundant file server comprising at least a first processor board and a second processor board, each of the first and second processor boards being programmed to perform file server functions, the first processor board being programmed to assume the file server functions of the second processor board upon failure of the second processor board, and the second processor board being programmed to assume the file server functions of the first processor board upon failure of the first processor board,

wherein each of the first and second processor boards includes at least a first physical processor and a second physical processor,

wherein each of the first and second physical processors has an on-chip cache, multiple functional units, and more than one processor register set sharing the on-chip cache and the multiple functional units to provide a first logical processor and a second logical processor;

wherein the first logical processor of the first physical processor of each of the first and second processor boards is programmed to perform storage functions including logical-to-physical mapping and access to multiple storage devices, the second logical processor of the first physical processor of each of the first and second processor boards is programmed to execute file server control functions, the first logical processor of the second physical processor of each of the first and second processor boards is programmed to execute data mover functions including network communication with clients and file system access, and the second logical processor of the second physical processor of each of the first and second processor boards is programmed to be in a stand-by state for execution of data mover functions;

wherein the first logical processor of the first physical processor of the first processor board is programmed to assume the storage system functions of the first logical processor of the first physical processor of the second processor board upon failure of the first logical processor of the first physical processor of the second processor board; and

the first logical processor of the first physical processor of the second processor board is programmed to assume the storage system functions of the first logical processor of the first physical processor of the first processor board upon failure of the first logical processor of the first physical processor of the first processor board;

wherein the second logical processor of the first physical processor of the first processor board is programmed to assume the file server control functions of the second logical processor of the first physical processor of the second processor board upon failure of the second logical processor of the first physical processor of the second processor board; and

the second logical processor of the first physical processor of the second processor board is programmed to assume the file server control functions of the second logical processor of the first physical processor of the first processor board upon failure of the second logical processor of the first physical processor of the first processor board; and

wherein the second logical processor of the second physical processor of the first processor board is programmed to assume the data mover functions of the first logical processor of the second physical processor of the second processor board upon failure of the second physical processor of the second processor board, and the second logical processor of the second physical processor of the second processor board is programmed to assume the data mover functions of the first logical processor of the second physical processor of the first processor board upon failure of the second physical processor of the first processor board.

14. The redundant file server as claimed in claim 13 which includes multiple dual-port disk drives, each of the multiple dual-port disk drives having a first port linked to the first processor board for data transmission to the first processor board, and a second port linked to the second processor board for data transmission to the second processor board.

15. The redundant file server as claimed in claim 13, wherein the first and second processor boards are dual processor boards.

16. The redundant file server as claimed in claim 13, wherein the first logical processor of the first physical processor of each of the first and second processor boards executes storage system code under a first operating system, and the second logical processor of the first physical processor of each of the first and second processor boards executes file server control code under a second operating system, and the second operating system is different from the first operating system.

17. The redundant file server as claimed in claim 13, wherein the first logical processor of the first physical processor of each of the first and second processor boards executes the storage system code under the Microsoft NT (trademark) operating system, and the second logical processor of the first physical processor of each of the first and second processor boards executes the file server control code under the Linux operating system.

18. The redundant file server as claimed in claim 13, wherein the first processor board has random access memory for containing a first storage cache, and the second processor board has random access memory for containing a second storage cache, and the first logical processors of the first physical processors of the first and second processor boards are programmed to write new storage cache data to both the first storage cache and the second storage cache so that the new storage cache data is not lost upon failure of either the first storage cache or the second storage cache.

19. The redundant file server as claimed in claim 13, wherein the file server control functions include recovery from failure in the redundant file server, configuration of the redundant file server, and collection and reporting of loading statistics and failure information of the redundant file server.

20. The redundant file server as claimed in claim 13, wherein the file server control code defines a master-slave relationship between the second logical processor of the first physical processor of the first processor board and the second logical processor of the first physical processor of the second processor board.

21. The redundant file server as claimed in claim 13, wherein the second logical processor of the second physical processor of the first processor board is programmed to assume the data mover functions of the first logical processor of the second physical processor of the first processor board upon failure of the first logical processor of the second physical processor of the first processor board, and the second logical processor of the second physical processor of the second processor board is programmed to assume the data mover functions of the first logical processor of the second physical processor of the second processor board upon failure of the first logical processor of the second physical processor of the second processor board.

22. A redundant file server comprising:

a first processor board,

a second processor board, and

multiple storage devices;

wherein each of the first and second processor boards includes at least a first physical processor, a second physical processor, random access memory shared between the first physical processor and the second physical processor, a first port for responding to file access requests from clients in a data network, a second port, and a third port;

wherein the second port of the first processor board is linked to the second port of the second processor board for transfer of data between the first processor board and the second processor board;

wherein each of the first and second physical processors has an on-chip cache, multiple functional units, and more than one processor register set sharing the on-chip cache and the multiple functional units to provide a first logical processor and a second logical processor;

wherein each of the multiple storage devices has at least one port linked to the third port of the first processor board for data transmission from said each of the multiple storage devices to the third port of the first processor board, and another port linked to the third port of the second processor board for data transmission from said each of the multiple storage devices to the third port of the second processor board;

wherein the first logical processor of the first physical processor of each of the first and second processor boards is programmed to execute storage system code, the second logical processor of the first physical processor of each of the first and second processor boards is programmed to execute file server control station code, the first logical processor of the second physical processor of each of the first and second processor boards is programmed to execute data mover code, the second logical processor of the second physical processor of each of the first and second processor boards is programmed to be in a stand-by state for execution of data mover code;

wherein the first logical processor of the first physical processor of the first processor board is programmed to assume storage system functions of the first logical processor of the first physical processor of the second processor board upon failure of the first logical processor of the first physical processor of the second processor board; and

the first logical processor of the first physical processor of the second processor board is programmed to assume storage system functions of the first logical processor of the first physical processor of the first processor board upon failure of the first logical processor of the first physical processor of the first processor board;

wherein the second logical processor of the first physical processor of the first processor board is programmed to assume file server control station functions of the second logical processor of the first physical processor of the second processor board upon failure of the second logical processor of the first physical processor of the second processor board; and

the second logical processor of the first physical processor of the second processor board is programmed to assume file server control station functions of the second logical processor of the first physical processor of the first processor board upon failure of the second logical processor of the first physical processor of the first processor board; and

wherein the second logical processor of the second physical processor of the first processor board is programmed to assume data mover functions of the first logical processor of the second physical processor of the second processor board upon failure of the second physical processor of the second processor board, and the second logical processor of the second physical processor of the second processor board is programmed to assume data mover functions of the first logical processor of the second physical processor of the first processor board upon failure of the second physical processor of the first processor board.

23. The redundant file server as claimed in claim 22, wherein the multiple storage devices are dual-port disk drives.

24. The redundant file server as claimed in claim 22, wherein each of the first and second processor boards is a dual processor board.

25. The redundant file server as claimed in claim 22, wherein the first logical processor of the first physical processor of each of the first and second processor boards executes the storage system code under a first operating system, and the second logical processor of the first physical processor of each of the first and second processor boards executes the file server control station code under a second operating system, and the second operating system is different from the first operating system.

26. The redundant file server as claimed in claim 22, wherein the first logical processor of the first physical processor of each of the first and second processor boards executes the storage system code under the Microsoft NT (trademark) operating system, and the second logical processor of the first physical processor of each of the first and second processor boards executes the file server control station code under the Linux operating system.

27. The redundant file server as claimed in claim 22, wherein the first processor board has random access memory for containing a first storage cache, and the second processor board has random access memory for containing a second storage cache, and the first logical processor of the first physical processors of the first and second processor boards are programmed to write new storage cache data to both the first storage cache and the second storage cache so that the new storage cache data is not lost upon failure of either the first storage cache or the second storage cache.

28. The redundant file server as claimed in claim 22, wherein the storage system code defines storage system functions that are shared between the first logical processor of the first physical processor of the first processor board and the first logical processor of the first physical processor of the second processor board, and the storage system functions include access to a storage system cache, logical-to-physical mapping, staging from the multiple storage devices to the storage system cache, and write-back from the storage system cache to the multiple storage devices.

29. The redundant file server as claimed in claim 22, wherein the file server control station code defines file server control station functions including recovery from failure in the redundant file server, configuration of the redundant file server, and collection and reporting of loading statistics and failure information of the redundant file server.

30. The redundant file server as claimed in claim 22, wherein the file server control station code defines a master-slave relationship between the second logical processor of the first physical processor of the first processor board and the second logical processor of the first physical processor of the second processor board.

31. The redundant file server as claimed in claim 22, wherein the data mover code defines data mover functions including network communication with clients and file system access.

32. The redundant file server as claimed in claim 22, wherein the first processor board and the second processor board are substantially identical.

33. The redundant file server as claimed in claim 22, further comprising a third processor board and a fourth processor board linked to the second port of the first processor board and linked to the second port of the second processor board, the third processor board and the forth processor board each being programmed to perform data mover functions, the third processor board being programmed to assume the data mover functions of the fourth processor board upon failure of the fourth processor board, and the fourth processor board being programmed to assume the data mover functions of the third processor board upon failure of the third processor board.

34. The redundant file server as claimed in claim 22, wherein the second logical processor of the second physical processor of the first processor board is programmed to assume the data mover functions of the first logical processor of the second physical processor of the first processor board upon failure of the first logical processor of the second physical processor of the first processor board, and the second logical processor of the second physical processor of the second processor board is programmed to assume the data mover functions of the first logical processor of the second physical processor of the second processor board upon failure of the first logical processor of the second physical processor of the second processor board.