Method and apparatus for indicating the severity of a fault within a computer system

• US 5,596,716 A
• Filed: 03/01/1995
• Issued: 01/21/1997
• Est. Priority Date: 03/01/1995
• Status: Expired due to Term

• Current Assignee: Unisys Corporation
• Original Assignee: Unisys Corporation
• Inventors: Byers, Larry L., Robeck, Gary R., Brunmeier, Terry J.
• Primary Examiner(s): Beausoliel, Jr., Robert W.
• Assistant Examiner(s): LE, DIEU MINH T
• Application Number:
  US08/396,953
• Time in Patent Office: 692 Days
• Field of Search: 395/575, 395/500, 395/650, 395/725, 395/185.01, 395/183.2, 395/182.03, 395/184.01, 395/40.4, 395/51.1, 371/8.2, 371/11.3, 371/12, 371/16.1, 371/19, 364/285, 364/241.2, 364/266.5, 364/267.7, 364/265
• US Class Current: 714/48
• CPC Class Codes: G06F 11/0721 within a central processing unit [CPU]
• CPC Class Codes: G06F 11/0772 Means for error signaling, e.g. using interrupts, exception flags, dedicated error registers
• CPC Class Codes: G06F 11/22 Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing

Abstract

A method and apparatus for efficiently identifying and indicating the severity of the fault within a computer system. In an exemplary embodiment of the present invention, the circuitry of a computer system may be divided into a number of groups. Each group may contain circuitry which may result in the same fault type. For example, predetermined circuitry which, when a fault is detected therein, may have a minimal affect on the normal operation of the computer system may be provided in a first group. Similarly, predetermined circuitry which, when a fault is detected therein, may have an immediate affect on the normal operation of the computer system may be provided in a second group. Each group may provide an error priority signal to a support controller. The support controller may interpret the number of error priority signals provided by the number of groups and may determine the appropriate time to take corrective action thereon.

Claims

1. In an electrical apparatus having a plurality of hardware elements and a number of error detection circuits, the number of error detection circuits being coupled to predetermined ones of the plurality of hardware elements, each of the number of error detection circuits continuously monitoring a corresponding one of the predetermined ones of the plurality of hardware elements and providing a corresponding error bit whenever an error is detected thereby, each of the corresponding error bits being serviced by a support controller, the improvement of the electrical apparatus comprising:

a. receiving means coupled to at least one of the number of error detection circuits for receiving a corresponding error bit from each of said at least one of the number of error detection circuits; and

b. determining means coupled to said receiving means for determining which of the corresponding error bits provided by said at least one of the number of error detection circuits are to be serviced immediately by the support controller, and which of the corresponding error bits provided by said at least one of the number of error detection circuits are to be serviced at a predetermined time later by the support controller.

2. An electrical apparatus according to claim 1 wherein a first subset of the number of error detection circuits are associated with a first group and a second subset of the number of error detection circuits are associated with a second group, said determining means allowing each of the number of error detection circuits associated with said first group to be serviced by the support controller at a first predetermined time, and said determining means allowing each of the number of error detection circuits associated with said second group to be serviced by the support controller at a second predetermined time.

3. An electrical apparatus according to claim 2 wherein said receiving means comprises a number of error detection registers.

4. A data processing system for executing a number of sequential instructions including a current instruction, comprising:

a. a first group of hardware elements and a second group of hardware elements wherein said first group of hardware elements further includes a first error detecting means and said second group of hardware elements further includes a second error detection means, said first error detection means continuously monitoring preselected ones of said first group of hardware elements and detecting a number of predefined errors in the preselected ones of said first group of hardware elements, and said second error detecting means continuously monitoring predefined ones of said second group of hardware elements and detecting a number of predefined errors in the preselected ones of said second group of hardware elements; and

b. servicing means coupled to said first group of hardware element and to said second group of hardware elements for servicing said number of predefined errors detected by said first error detecting means and said number of predefined errors detected by said second error detecting means, said servicing means servicing said predefined errors detected in said first group of hardware elements before servicing said predefined errors detected in said second group of hardware elements.

5. A data processing system according to claim 4 wherein said servicing means services said predefined errors detected in said first group of hardware elements immediately and services said predefined errors detected in said second group of hardware elements at a predetermined time later.

6. A data processing system according to claim 5 wherein said servicing means further includes interrupting means, wherein said interrupting means interrupts the execution of the data processing system before said servicing means services said predefined errors detected in said first group of hardware elements.

7. A data processing system according to claim 6 wherein said servicing means further includes determining means for determining when the execution of the current instruction is complete, and control means coupled to said determining means for controlling when said servicing means services said predefined errors detected in said second group of hardware elements, said control means prompting said servicing means to service said predefined errors detected in said second group of hardware elements after the execution of the current instruction is completed.

8. A data processing system according to claim 6 wherein a utilization factor is defined by the number of sequential instructions executed by the data processing system per unit time, said servicing means further including control means wherein said control means prompts said servicing means to service said predefined errors detected in said second group of hardware elements after said utilization factor of the data processing system drops below a predetermined level.

9. A data processing system according to claim 6 wherein said servicing means further includes determining means for determining when the data processing system is rebooted, and control means coupled to said determining means for controlling when said servicing means services said predefined errors detected in said second group of hardware elements, said control means prompting said servicing means to service said predefined errors detected in said second group of hardware elements during the next reboot of the data processing system.

10. A data processing system according to claim 6 wherein said servicing means further includes means for notifying a service technician of said predefined errors detected in said second group of hardware elements for a next preventive maintenance session.

11. A data processing system according to claim 5 wherein said predefined errors detected in said first group of hardware elements are critical errors.

12. A data processing system according to claim 5 wherein said predefined errors detected in said second group of hardware elements are passive errors.

13. A data processing system for executing a number of sequential instructions including a current instruction, comprising:

a. a support controller;

b. a first group of hardware element;

c. a number of first error detecting means coupled to preselected ones of said first group of hardware elements, said number of first error detecting means for continuously monitoring the preselected ones of said first group of hardware elements and detecting a number of corresponding first errors in said preselected ones of said first group of hardware elements;

d. first error storage means coupled to said number of first error detecting means for storing said number of corresponding first errors;

e. first disabling means coupled to said first error storage means for disabling said first error storage means once a first one of said number of corresponding first errors is detected;

f. first providing means coupled to said first error storage means and further coupled to said support controller for providing a first fault type to said support controller when said first one of said number of corresponding first errors is detected;

g. a second group of hardware elements;

h. a number of second error detecting means coupled to preselected ones of said second group of hardware elements, said number of second error detecting means for continuously monitoring the preselected ones of said second group of hardware elements and detecting a number of corresponding second errors in said preselected ones of said second group of hardware elements;

i. second error storage means coupled to said number of second error detecting means for storing said number of corresponding second errors;

j. second disabling means coupled to said second error storage means for disabling said second error storage means once a first one of said number of corresponding second errors is detected;

k. second providing means coupled to said second error storage means and further coupled to said support controller for providing a second fault type to said support controller when the first one of said number of corresponding second errors is detected; and

l. servicing means coupled to said support controller wherein said servicing means services said first fault type before servicing said second fault type.

14. A data processing system according to claim 13 wherein said servicing means further includes means for prioritizing said first fault type and said second fault type such that said servicing means services said first fault type immediately and services said second fault type at a predetermined time later.

15. A data processing system according to claim 14 wherein said servicing means further includes interrupting means, said interrupting means interrupts the execution of the data processing system before said servicing means services said first fault type.

16. A data processing system according to claim 14 wherein said servicing means further includes determining means for determining when the execution of the current instruction is complete, and control means coupled to said determining means for controlling when said servicing means services said second fault type, said control means prompting said servicing means to service said second fault type after the execution of the current instruction is completed.

17. A data processing system according to claim 14 wherein a utilization factor is defined by the number of sequential instructions executed by the data processing system per unit time, said servicing means further includes control means for controlling when said servicing means services said second fault type, said control means prompting said servicing means to service said second fault type after said utilization factor of the data processing system drops below a predetermined level.

18. A data processing system according to claim 14 wherein said servicing means further includes determining means for determining when the data processing is rebooted, and control means coupled to said determining means for controlling when said servicing means services said second fault type, said control means prompting said servicing means to service said second fault type during the next reboot of the data processing system.

19. A data processing system according to claim 14 wherein said servicing means further includes means for notifying a service technician of said second fault type for a next preventive maintenance session.

20. A data processing system according to claim 13 wherein said first fault type corresponds to a critical error.

21. A data processing system according to claim 20 wherein said second fault type corresponds to a passive error.

22. A data processing system according to claim 21 wherein each of said number of first error detecting means comprise a parity checking circuit.

23. A data processing system according to claim 22 wherein each of said number of second error detecting means comprise a parity checking circuit.

24. In an electrical apparatus having a plurality of hardware elements and a number of error detection circuits, the number of error detection circuits being coupled to predetermined ones of the plurality of hardware elements, each of the number of error detection circuits continuously monitoring a corresponding one of the predetermined ones of the plurality of hardware elements and providing a corresponding error bit whenever an error is detected thereby, each of the corresponding error bits being serviced by a support controller, the improvement of the electrical apparatus comprising:

a. a receiving circuit coupled to at least one of the number of error detection circuits for receiving a corresponding error bit from each of said at least one of the number of error detection circuits; and

b. determining circuit coupled to said receiving circuit for determining which of the corresponding error bits provided by said at least one of the number of error detection circuits are to be serviced immediately by the support controller, and which of the corresponding error bits provided by said at least one of the number of error detection circuits are to be serviced at a predetermined time later by the support controller.

25. An electrical apparatus according to claim 24 wherein a first subset of the number of error detection circuits are associated with a first group and a second subset of the number of error detection circuits are associated with a second group, said determining circuit allowing each of the number of error detection circuits associated with said first group to be serviced by the support controller at a first predetermined time, and said determining circuit allowing each of the number of error detection circuits associated with said second group to be serviced by the support controller as a second predetermined time.

26. An electrical apparatus according to claim 25 wherein said receiving circuit comprises a number of error detection registers.

27. A data processing system for executing a number of sequential instructions including a current instruction, comprising:

a. a first group of hardware elements and a second group of hardware elements wherein said first group of hardware elements further includes a first error detecting circuit and said second group of hardware elements further includes a second error detection circuit, said first error detection circuit continuously monitoring preselected ones of said first group of hardware elements and detecting a number of predefined errors in the preselected ones of said first group of hardware elements each of said, and said second error detecting circuit continuously monitoring preselected ones of said second group of hardware elements and detecting a number of predefined errors in the preselected ones of said second group of hardware elements; and

b. a servicing circuit coupled to said first group of hardware element and to said second group of hardware elements for servicing said number of predefined errors detected by said first error detecting circuit and said number of predefined errors detected by said second error detecting circuit, said servicing circuit servicing said predefined errors detected in said first group of hardware elements before servicing said predefined errors detected in said second group of hardware elements.

28. A data processing system according to claim 27 wherein said servicing circuit services said predefined errors detected in said first group of hardware elements immediately and services said predefined errors detected in said second group of hardware elements at a predetermined time later.

29. A data processing system according to claim 28 wherein said servicing circuit further includes an interrupting circuit, wherein said interrupting circuit interrupts the execution of the data processing system before said servicing means services said predefined errors detected in said first group of hardware elements.

30. A data processing system according to claim 29 wherein said servicing circuit further includes a determining circuit for determining when the execution of the current instruction is complete, and a control circuit coupled to said determining circuit for controlling when said servicing circuit services said predefined errors detected in said second group of hardware elements, said control circuit prompting said servicing circuit to service said predefined errors detected in said second group of hardware elements after the execution of the current instruction is completed.

31. A data processing system according to claim 29 wherein a utilization factor is defined by the number of sequential instructions executed by the data processing system per unit time, said servicing circuit further including a control circuit wherein said control circuit prompts said servicing circuit to service said predefined errors detected in said second group of hardware elements after said utilization factor of the data processing system drops below a predetermined level.

32. A data processing system according to claim 29 wherein said servicing circuit further includes a determining circuit for determining when the data processing system is rebooted, and a control circuit coupled to said determining circuit for controlling when said servicing circuit services said predefined errors detected in said second group of hardware elements, said control circuit prompting said servicing circuit to service said predefined errors detected in said second group of hardware elements during the next reboot of the data processing system.

33. A data processing system according to claim 29 wherein said servicing circuit further includes a notifying circuit for notifying a service technician of said predefined errors detected in said second group of hardware elements for a next preventive maintenance session.

34. A data processing system according to claim 28 wherein said predefined errors detected in said first group of hardware elements are critical errors.

35. A data processing system according to claim 28 wherein said predefined errors detected in said second group of hardware elements are passive errors.

36. A data processing system for executing a number of sequential instructions including a current instruction, comprising:

a. a support controller;

b. a first group of hardware elements;

c. a number of first error detecting circuits coupled to preselected ones of said first group of hardware elements, said number of first error detecting circuits for continuously monitoring a corresponding one of the preselected ones of said first group of hardware elements and detecting a number of corresponding first errors in said preselected ones of said first group of hardware elements;

d. a first error storage circuit coupled to said number of first error detecting circuits for storing said number of corresponding first errors;

e. a first disabling circuit coupled to said first error storage circuit for disabling said first error storage circuit once a first one of said number of corresponding first errors is detected;

f. a first providing circuit coupled to said first error storage circuit and further coupled to said support controller for providing a first fault type to said support controller when said first one of said number of corresponding first errors is detected;

g. a second group of hardware elements;

h. a number of second error detecting circuits coupled to preselected ones of said second group of hardware elements, said number of second error detecting circuits for continuously monitoring a corresponding one of the preselected ones of said second group of hardware elements and detecting a number of corresponding second errors in said preselected ones of said second group of hardware elements;

i. a second error storage circuit coupled to said number of second error detecting circuit for storing said number of corresponding second errors;

j. a second disabling circuit coupled to said second error storage circuit for disabling said second error storage circuit once a first one of said number of corresponding second errors is detected;

k. a second providing circuit coupled to said second error storage circuit and further coupled to said support controller for providing a second fault type to said support controller when the first one of said number of corresponding second errors is detected; and

l. a servicing circuit coupled to said support controller wherein said servicing circuit services said first fault type before servicing said second fault type.

37. A data processing system according to claim 36 wherein said servicing circuit further includes a control circuit wherein said control circuit ensures that said servicing circuit services said first fault immediately and services said second fault type at a predetermined time later.

38. A data processing system according to claim 37 wherein said servicing circuit further includes an interrupting circuit, said interrupting circuit interrupts the execution of the data processing system before said servicing circuit services said first fault type.

39. A data processing system according to claim 38 wherein said servicing circuit further includes a determining circuit for determining when the execution of the current instruction is complete, and a control circuit coupled to said determining circuit for controlling when said servicing circuit services said second fault type, said control circuit prompting said servicing circuit to service said second fault type after the execution of the current instruction is completed.

40. A data processing system according to claim 38 wherein a utilization factor is defined by the number of sequential instructions executed by the data processing system per unit time, said servicing circuit further includes a control circuit for controlling when said servicing circuit services said second fault type, said control circuit prompting said servicing circuit to service said second fault type after said utilization factor of the data processing system drops below a predetermined level.

41. A data processing system according to claim 38 wherein said servicing circuit further includes a determining circuit for determining when the data processing is rebooted, and a control circuit coupled to said determining circuit for controlling when said servicing circuit services said second fault type, said control circuit prompting said servicing circuit to service said second fault type during the next reboot of the data processing system.

42. A data processing system according to claim 38 wherein said servicing circuit further includes a notifying circuit for notifying a service technician of said second fault type for a next preventive maintenance session.

43. A data processing system according to claim 36 wherein said first fault type correspond to a critical error.

44. A data processing system according to claim 43 wherein said second fault type corresponds to a passive error.

45. A data processing system according to claim 44 wherein each of said number of first error detecting circuits comprise a parity checking circuit.

46. A data processing system according to claim 45 wherein each of said number of second error detecting circuits comprise a parity checking circuit.

47. A method for servicing errors within a computer system, the computer system having a number of hardware elements therein, each of the number of hardware elements capable of experiencing an error, and each of the errors having a predefined effect on the operation of the computer system, the number of hardware elements being partitioned into at least two groups wherein an error detected in any of the number of hardware elements of a particular one of the at least two groups having the same predefined effect on the operation of the computer system, the method comprising the steps of:

a. providing an error detecting means for each of said at least two groups for continuously monitoring the number of hardware elements in said corresponding one of said at least two groups and detecting errors in said corresponding one of said at least two groups;

b. providing a predefined condition for each of said at least two groups;

c. executing a program on the computer system;

d. detecting an error in at least one of said at least two groups via said error detecting means of step (a);

e. determining what group produced the detected error; and

f. servicing the detected error when said predefined condition of said corresponding group is satisfied.

48. A method for servicing errors within a computer system, the computer system having a number of hardware elements therein, each of the number of hardware elements capable of experiencing an error, and each of the errors having a predefined effect on the operation of the computer system, the number of hardware elements being partitioned into a first group of hardware elements and a second group of hardware elements wherein an error in any of the number of hardware elements of the first group of hardware elements causes a critical error in the operation of the computer system and an error in any of the number of hardware elements of the second group of hardware elements causes a passive error in the operation of the computer system, the method comprising the steps of:

a. executing a program on the computer system;

b. detecting an error;

c. determining if the detected error was produced by the first group of hardware elements or by the second group of hardware elements;

d. aborting the operation of the computer system and servicing the detected error if said determining step (c) determined that the detected error was produced by the first group of hardware elements; and

e. servicing the detected error a predetermined time later if said determining step (c) determined that the detected error was produced by said second group of hardware elements.