System and method for memory failure recovery using lockstep processes

• US 20030140281A1
• Filed: 01/24/2002
• Published: 07/24/2003
• Est. Priority Date: 01/24/2002
• Status: Active Grant

• Current Assignee: Valtrus Innovations Limited (f/k/a Dolya Holdco 9 Limited) (Key Patent Innovations Limited)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Messer, Alan, Milojicic, Dejan S., Fu, Guangrui, Bernadat, Philippe
• Granted Patent: US 7,020,800 B2
• Time in Patent Office: Days
• US Class Current: 714/38
• CPC Class Codes: G06F 11/1492 by run-time replication performed by the application software

Abstract

A system and method for memory failure recovery is disclosed. The method discloses the steps of maintaining a predetermined number of duplicate and primary processes; keeping the processes in synchronization; managing the processes so that a single process image is presented to an external environment; detecting a computer system exception which affects one of the processes; and terminating the affected process. The system discloses, a primary process memory space which hosts a primary process; a duplicate process memory space which hosts a duplicate process corresponding to the primary process; a synchronization buffer which keeps the duplicate process in synchronization with the primary process; a processor which generates an exception signal in response to detection of a memory failure condition which affects the primary process; and an operating system which receives the exception signal, terminates the affected primary process, and maintains a predetermined number of primary and duplicate processes.

Claims

1. A method for memory failure recovery, comprising:

maintaining a predetermined number of duplicate and primary processes;

keeping the processes in synchronization;

managing the processes so that a single process image is presented to an external environment;

detecting a computer system exception which affects one of the processes; and

terminating the affected process.

2. The method of claim 1 wherein the detecting element includes detecting a memory failure.

3. The method of claim 1 further comprising:

allocating a new memory space to each of the duplicate processes, which is separate from a memory space allocated to the primary process.

4. The method of claim 1 wherein the maintaining element includes:

identifying a primary process;

monitoring a fault-tolerance value corresponding to the primary process; and

setting a number of duplicate processes equal to the fault-tolerance value.

5. The method of claim 4 wherein the monitoring element includes assigning a predetermined fault-tolerance value to a primary process.

6. The method of claim 4 wherein the monitoring element includes dynamically modifying the fault-tolerance value of the primary process, in response to a computer command.

7. The method of claim 4 wherein the setting element includes adding a new duplicate processes, if the number of duplicate processes is less than the fault-tolerance value.

8. The method of claim 4 wherein the setting element includes deleting a duplicate process, if the number of duplicate processes is more than the fault-tolerance value.

9. The method of claim 1 wherein the keeping element includes synchronizing the processes upon receipt of data from an external environment.

10. The method of claim 1 wherein the keeping element includes synchronizing the processes upon receipt of signals from an external environment.

11. The method of claim 1 wherein the keeping element includes synchronizing the processes upon transmission by one of the processes to an external environment.

12. The method of claim 1 wherein the managing element includes permitting only one of the processes to transmit to an external environment.

13. The method of claim 1 wherein the managing element includes permitting only one of the processes to perform a system call to an external environment.

14. The method of claim 1 wherein the managing element includes permitting only one of the processes to perform a library call to an external environment.

21. The medium of claim 1 wherein the managing element includes permitting only one of the processes to transmit to an external environment.

15. A method for memory failure recovery, comprising:

maintaining a predetermined number of duplicate and primary processes;

keeping the processes in synchronization;

managing the processes so that a single process image is presented to an external environment;

detecting a computer system exception which affects one of the processes; and

terminating the affected process;

wherein the maintaining element includes,

identifying a primary process;

monitoring a fault-tolerance value corresponding to the primary process; and

setting a number of duplicate processes equal to the fault-tolerance value; and

wherein the managing element includes,

permitting only one of the processes to perform a system call to an external environment.

16. A data structure for memory failure recovery within a computer system, comprising the fields of:

a primary process field, for identifying primary processes within the computer system; and

a fault-tolerance variable field, for identifying a predetermined number of duplicate processes, corresponding to the primary processes, to be maintained within the computer system.

17. A computer-usable medium embodying computer program code for commanding a computer to perform memory failure recovery comprising:

maintaining a predetermined number of duplicate and primary processes;

keeping the processes in synchronization;

managing the processes so that a single process image is presented to an external environment;

detecting a computer system exception which affects one of the processes; and

terminating the affected process.

18. The medium of claim 17 wherein the detecting element includes detecting a memory failure.

19. The medium of claim 17 further comprising:

allocating a new memory space to each of the duplicate processes, which is separate from a memory space allocated to the primary process.

20. The medium of claim 17 wherein the maintaining element includes:

identifying a primary process;

monitoring a fault-tolerance value corresponding to the primary process; and

setting a number of duplicate processes equal to the fault-tolerance value.

22. A system for memory failure recovery, comprising:

means for maintaining a predetermined number of duplicate and primary processes;

means for keeping the processes in synchronization;

means for managing the processes so that a single process image is presented to an external environment;

means for detecting a computer system exception which affects one of the processes; and

means for terminating the affected process.

23. A system for memory failure recovery, comprising:

a primary process memory space hosting a primary process;

a duplicate process memory space hosting a duplicate process corresponding to the primary process;

a synchronization buffer for keeping the duplicate process in synchronization with the primary process;

a processor for generating an exception signal in response to detection of a memory failure condition which affects the primary process; and

an operating system for receiving the exception signal, terminating the affected primary process, and maintaining a predetermined number of primary and duplicate processes.

24. The system of claim 23, further comprising:

a buffer controller for permitting the processes to receive communications from an external environment while permitting only one of the processes to transmit the external environment.

25. The system of claim 23, wherein the exception signal is a machine check abort signal.