Methods and systems for conducting processor health-checks

• US 20060230308A1
• Filed: 02/17/2006
• Published: 10/12/2006
• Est. Priority Date: 02/18/2005
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Kuntz, Guy, Sedmak, Michael, Pomaranski, Ken, Barlow, Jeff, Brauch, Jeff, Joyal, Lacey, Hack, Stephen, Calkin, Howard, Gratias, Raymond
• Granted Patent: US 7,694,175 B2
• Time in Patent Office: Days
• US Class Current: 714/11
• CPC Class Codes: G06F 11/0724 in a multiprocessor or a multi-core unit multiprocessors per se G06F15/80
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40
• CPC Class Codes: G06F 11/2236 to test CPU or processors

Abstract

Systems and methods for conducting processor health-checks are provided. In one embodiment, a method for evaluating the status of a processor is provided. The method includes, for example, initializing and executing an operating system, de-allocating the processor from the available pool or system resources and performing a health-check on the processor while the operating system is executing.

Claims

1. A method for evaluating the status of a processor comprising the steps of:

initializing and executing an operating system;

de-allocating said processor from an available pool of system resources while said operating system is executing;

conducting a health-check on said processor while said operating system is executing;

re-allocating said processor into said available pool of system resources if said processor is healthy; and

repairing said processor if said processor is unhealthy.

2. The method of claim 1 further comprising the step of:

swapping in a non-allocated processor for said de-allocated processor.

3. The method of claim 1 further comprising the step of:

reporting actions taken on a memory device.

4. The method of claim 1 further comprising the steps of:

determining if said repair of said processor was successful;

re-allocating said processor into said available pool of system resources if said repair was successful; and

keeping said processor de-allocated if said repair was unsuccessful.

5. The method of claim 1 wherein said repair step comprises the steps of:

determining that a cache element of said processor is faulty based on said health-check;

determining whether said non-allocated cache element is available; and

swapping in a non-allocated cache element for said faulty cache element if said non-allocated cache element is available.

6. The method of claim 5 further comprising the step of:

reporting that said repair is unsuccessful if said non-allocated cache element is not available.

7. The method of claim 5 further comprising the step of:

updating cache configuration of said processor if said non-allocated cache element is swapped in for said faulty cache element.

8. The method of claim 5 further comprising the step of:

reporting that said repair is successful if said non-allocated cache element is swapped in for said faulty cache element.

9. The method of claim 5 wherein said swapping step is performed while said operating system is executing.

10. The method of claim 5 wherein said swapping step is performed during a system reboot.

11. The method of claim 1 wherein said conducting a health-check further comprising the steps of:

reading error logs of said processor;

storing data from said error logs in a memory;

clearing said error logs;

conducting at least one diagnostic test on said processor; and

reading said error logs following said at least one diagnostic test.

12. The method of claim 9 wherein said testing includes conducting at least one cache memory diagnostic test on said processor.

13. The method of claim 9 wherein said at least one diagnostic test is conducted by starting at least one of the processor'"'"'s BIST engines.

14. The method of claim 9 wherein said processor is determined to be healthy if no errors are contained in said error logs following said at least one diagnostic test.

15. The method of claim 9 wherein said processor is determined to be unhealthy if errors are contained in said error logs following said at least one diagnostic test.

16. A system comprising:

at least one processor; and

health-check logic operable to de-allocate said at least one processor from an available pool of system resources and conduct a health-check on said processor while an operating system is executing, operable to re-allocate said processor into said available pool of system resources if said processor is healthy and operable to repair said at least one processor if said processor is unhealthy.

17. The system of claim 16 wherein said health-check logic is further operable to swap in a non-allocated processor for said at least one de-allocated processor.

18. The system of claim 16, wherein said health-check logic is further operable to report actions taken on a memory device.

19. The system of claim 16, wherein said health-check logic is further operable to read error logs of said at least one processor, store data from said error logs in a memory, clear said error logs, conduct at least one diagnostic test on said at least one processor, and read said error logs following said at least one diagnostic test.

20. The system of claim 19 wherein said at least one diagnostic test includes conducting at least one cache memory diagnostic test on said at least one processor.

21. The system of claim 19 wherein said at least one diagnostic test is conducted by starting said at least one processor'"'"'s at least one BIST engine.

22. The system of claim 19 wherein said health-check logic is further operable to determine that said de-allocated at least one processor is healthy if no errors are contained in said error logs following said at least one diagnostic test.

23. The system of claim 19 wherein said health-check logic is further operable to determine that said de-allocated at least one processor is unhealthy if errors are contained in said error logs following said at least one diagnostic test.

24. A computer system comprising:

at least one processor; and

health-check logic operable to de-allocate said at least one processor from an available pool of system resources and conduct a health-check on said processor while an operating system is executing, operable to re-allocate said processor into said available pool of system resources if said processor is healthy, operable to repair said at least one processor if said processor is unhealthy.

25. The computer system of claim 24 wherein said health-check logic is further operable to swap in a non-allocated processor for said at least one de-allocated processor.

26. The computer system of claim 24, wherein said health-check logic is further operable to report actions taken on a memory device.

27. The computer system of claim 24, wherein said health-check logic is further operable to read error logs of said at least one processor, store data from said error logs in a memory, clear said error logs, conduct at least one diagnostic test on said at least one de-allocated processor, and read said error logs following said at least one diagnostic test.

28. The computer system of claim 27 wherein said at least one diagnostic test includes conducting at least one cache element diagnostic test on said at least one de-allocated processor.

29. The computer system of claim 27 wherein said at least one diagnostic test is conducted by starting said at least one processor'"'"'s at least on BIST engine.

30. The computer system of claim 27 wherein said health-check logic is further operable to determine that said de-allocated at least one de-allocated processor is healthy if no errors are contained in said error logs following said at least one diagnostic test.

31. The computer system of claim 27 wherein said health-check logic is further operable to determine that said at least one de-allocated processor is unhealthy if errors are contained in said error logs following said at least one diagnostic test.

32. A method for diagnosing the error status of a processor comprising the steps of:

de-allocating an allocated processor;

clearing error logs of said de-allocated processor;

conducting at least one diagnostic test on said processor;

reading said error logs following said at least one diagnostic test; and

determining that said processor is healthy if no errors are contained in said error logs following said at least one diagnostic test.

33. The method of claim 32 further comprising the step of:

determining that said processor is unhealthy if errors are contained in said error logs following said at least one diagnostic test.

34. The method of claim 32 further comprising the steps of:

reading said error logs of said processor before said clearing step; and

storing data from said error logs in a memory.

35. The method of claim 32 wherein said at least one diagnostic test includes conducting at least one cache memory diagnostic test on said processor.

36. The method of claim 32 wherein said at least one diagnostic test is conducted by starting said processor'"'"'s at least one BIST engines.