Method and system for autonomously rebuilding a failed server and a computer system utilizing the same

• US 20040255189A1
• Filed: 06/12/2003
• Published: 12/16/2004
• Est. Priority Date: 06/12/2003
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chu, Simon C., Dayan, Richard A.
• Granted Patent: US 7,194,655 B2
• Time in Patent Office: Days
• US Class Current: 714/13
• CPC Class Codes: G06F 11/1658 Data re-synchronization of a redundant component, or initial sync of replacement, additional or spare unit
• CPC Class Codes: G06F 11/1662 the resynchronized component or unit being a persistent storage device re-synchronization of failed mirror storage G06F11/2082; rebuild or reconstruction of parity RAID storage G06F11/1008
• CPC Class Codes: G06F 11/2025 using centralised failover control functionality
• CPC Class Codes: G06F 11/2028 eliminating a faulty processor or activating a spare
• CPC Class Codes: G06F 11/2051 in regular structures

Abstract

A method and system for autonomously rebuilding a failed one of a plurality of servers and a computer system utilizing the same is disclosed. In a first aspect, the method comprises providing a bus for allowing a recovery mechanism to access each of the plurality of servers and utilizing the recovery mechanism to rebuild the failed server onto another server. In a second aspect, the computer system comprises a plurality of servers, a management module for monitoring and managing the plurality of servers, a recovery mechanism coupled to the management module, and a bus coupling the recovery mechanism to each of the plurality of servers, wherein the recovery mechanism rebuilds a failed server onto another of the plurality of servers.

Claims

1. A method for rebuilding a failed one of a plurality of servers onto another of the plurality of servers comprising the steps of:

a) providing a bus for allowing a recovery mechanism to access each of the plurality of servers; and

b) utilizing the recovery mechanism to rebuild the failed server onto another server.

2. The method of claim 1, wherein the providing step (a) further comprising the step of coupling a hard drive in each of the plurality of servers to the bus via a select module in each of the plurality of servers.

3. The method of claim 2, wherein utilizing step (b) further comprises:

(b1) disabling access to the hard drive in the failed server by a processor in the failed server; and

(b2) enabling the bus, thereby allowing the recovery mechanism to have direct access to the hard drive of the failed server.

4. The method of claim 3, wherein the recovery mechanism performs the disabling step (b1) via a control line coupled to the select module in each of the plurality of servers.

5. The method of claim 4, wherein the select module controls access to the hard drive by the processor or by the bus.

6. The method of claim 3, wherein the utilizing step (b) further comprising the steps of:

(b3) copying data from the failed server'"'"'s hard drive; and

(b4) transferring the copied data to the another server'"'"'s hard drive across the bus.

7. The method of claim 6, wherein the entire contents of the failed server'"'"'s hard drive is copied and transferred.

8. The method of claim 6, wherein the utilizing step (b) further comprising:

(b5) disabling the bus; and

(b6) enabling the processor in the another server to access the hard drive.

9. The method of claim 1, further comprising the step of:

(c) enabling the another server to resume duties of the failed server.

10. The method of claim 9, wherein enabling step (c) further comprising:

(c1) reassigning resources from the failed server to the another server; and

(c2) allowing the another server to assume the identity of the failed server.

11. The method of claim 9, further comprising the steps of:

(d) powering down the failed server; and

(e) alerting an administrator of the failed server.

12. A computer readable medium containing program instructions for rebuilding a failed one of a plurality of servers onto another of the plurality of servers, the instructions for:

a) providing a bus for allowing a recovery mechanism to access each of the plurality of servers; and

b) utilizing the recovery mechanism to rebuild the failed server onto another server.

13. The computer readable medium of claim 12, wherein the providing instruction (a) further comprising the instruction for coupling a hard drive in each of the plurality of servers to the bus via a select module in each of the plurality of servers.

14. The computer readable medium of claim 13, wherein the utilizing instruction (b) further comprises:

(b1) disabling access to the hard drive in the failed server by a processor in the failed server; and

(b2) enabling the bus, thereby allowing the recovery mechanism to have direct access to the hard drive of the failed server.

15. The computer readable medium of claim 14, wherein the recovery mechanism performs the disabling instruction (b1) via a control line coupled to the select module in each of the plurality of servers.

16. The computer readable medium of claim 15, wherein the select module controls access to the hard drive by the processor or the bus.

17. The computer readable medium of claim 14, wherein the utilizing instruction (b) further comprising the instructions for:

(b3) copying data from the failed server'"'"'s hard drive; and

(b4) transferring the copied data to the another server'"'"'s hard drive across the bus.

18. The computer readable medium of claim 17, wherein the entire contents of the failed server'"'"'s hard drive is copied and transferred.

19. The computer readable medium of claim 17, wherein the utilizing instruction (b) further comprising:

(b5) disabling the bus; and

(b6) enabling the processor in the another server to access the hard drive.

20. The computer readable medium of claim 12, further comprising the instruction for:

(c) enabling the another server to resume duties of the failed server.

21. The computer readable medium of claim 20, wherein the enabling instruction (c) further comprising:

(c1) reassigning resources from the failed server to the another server; and

(c2) allowing the another server to assume the identity of the failed server.

22. The computer readable medium of claim 20, further comprising the instructions for:

(d) powering down the failed server; and

(e) alerting an administrator of the failed server.

23. A system for rebuilding a failed one of a plurality of servers onto another of the plurality of servers comprising:

a circuit board for coupling a recovery mechanism to the plurality of servers; and

a bus in the circuit board for allowing the recovery mechanism to access each of the plurality of servers, wherein the recovery mechanism rebuilds the failed server onto the another server.

24. The system of claim 23, wherein a hard drive in each of the plurality of servers is coupled to the bus via a select module in each of the plurality of servers.

25. The system of claim 24 further comprising:

means for disabling access by a processor in the failed server to the hard drive in the failed server; and

means for enabling and disabling the bus, wherein when the bus is enabled, the recovery mechanism has direct access to the hard drive of the failed server.

26. The system of claim 25, wherein the means for disabling/enabling access by the processor comprises a control line in the circuit board coupled to the select module in each of the plurality of servers, wherein the recovery mechanism utilizes the control line to activate the select module which controls access to the hard drive by the processor or by the bus.

27. The system of claim 25 further comprising:

means for copying data from the failed server'"'"'s hard drive; and

means for transferring the copied data to the another server'"'"'s hard drive across the bus.

28. The system of claim 23 further comprising:

means for enabling the another server to resume duties of the failed server.

29. The system of claim 23, wherein the another server is a spare server.

30. A computer system comprising:

a plurality of servers;

a management module for monitoring and managing the plurality of servers;

a recovery mechanism coupled to the management module; and

a bus coupling the recovery mechanism to each of the plurality of servers, wherein the recovery mechanism rebuilds a failed server onto another of the plurality of servers.

31. The system of claim 30 further comprising a control line coupling the recovery mechanism to a select module in each of the plurality of servers, wherein the select module controls traffic on a peripheral device interface coupling the hard drive to the bus and to a processor in each server.

32. The system of claim 31, wherein the recovery mechanism utilizes the control line to direct the select module in the failed server and the select module in the another server to disable access by the processor in the failed server and access by the processor in the another server.

33. The system of claim 30, wherein a hard drive in each of the plurality of servers is coupled to the bus.

34. The system of claim 33, wherein the recovery mechanism copies data on the failed server'"'"'s hard drive and transfers the copied data to the another server'"'"'s hard drive across the bus.

35. The system of claim 30, wherein the recovery mechanism is in the management module.

36. A computer system comprising:

a plurality of servers;

a management module for monitoring and managing the plurality of servers;

a recovery mechanism coupled to the management module;

a bus coupling the recovery mechanism to a hard drive in each of the plurality of servers;

means for disabling access to the hard drive in a failed server by a processor in the failed server; and

means for enabling the bus, wherein the recovery mechanism rebuilds the failed server onto another of the plurality of servers.

37. The computer system of claim 36, wherein the means for disabling access comprising a control line coupling the recovery mechanism to a select module in each of the plurality of servers, wherein the select module controls traffic on a peripheral device interface coupling the hard drive to the bus and to the processor.

38. The computer system of claim 37, wherein the recovery mechanism utilizes the control line to direct the select module in the failed server and the select module in the another server to disable access by the processor in the failed server and access by the processor in the another server.