Method and apparatus for performing health tests of units of a data processing system

• US 5,210,757 A
• Filed: 10/05/1990
• Issued: 05/11/1993
• Est. Priority Date: 10/05/1990
• Status: Expired due to Term

• Current Assignee: Bull HN Information Systems Incorporated (Atos SE)
• Original Assignee: Bull HN Information Systems Incorporated (Atos SE)
• Inventors: Keeley, James W., Barlow, George J., Zelley, Richard C.
• Primary Examiner(s): Beausoliel, Robert W.
• Assistant Examiner(s): LE, DIEU MINH T
• Application Number:
  US07/593,408
• Time in Patent Office: 949 Days
• Field of Search: 371/16.1, 371/11.3, 371/29.5, 371/9.1, 364/187, 364/186, 364/267.1, 364/267.2, 364/267.4, 364/229.2, 364/230.4, 364/242.92, 364/945.7, 364/931.44, 364/935.41
• US Class Current: 714/25
• CPC Class Codes: G06F 11/0757 by exceeding a time limit, i.e. time-out, e.g. watchdogs
• 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
• CPC Class Codes: G06F 11/2736 using a dedicated service processor for test

Abstract

A means for ascertaining the health, or basic operational status, of a system unit. A "health check" provides an indication of either "yes", the system unit is operational, or "no", the system unit is either inoperative or there is a question as to whether the system is operational. The test is performed by requesting that the system unit perform a high priority "short" operation and noting the response provided to the request; the actual execution of the request is unimportant and it is the response of the unit under test to the receipt of the request for a bus operation that is the actual indicator of the status of the unit being tested. The requested operation is not directed at the unit whose operational status is to be determined, but instead at a bus interface unit which performs bus operations for the unit to be tested and whose responses to requests for bus operations are effected by the operational status of the unit that is to be tested. The operation is not directed at an actual element in the bus interface unit, but at a phantom, or nonexistent, element.

Claims

1. In a data processing system having at least one data processing unit for performing data processing operations, a system manager unit for performing administrative functions of the system, the administrative functions including system fault testing and detection, and a system bus connected between the data processing units and the system manager unit for performing bus operations, the system manager unit and each data processing unit including bus control means for asserting a request for a bus operation, the system manager unit having priority of access to the bus and each data processing unit bus control means being responsive to requests for bus operations asserted on the bus by the system manager unit and by other data processing units and responsive to the state of operation of the data processing unit for responding to the bus operation requests, a method for periodically testing the basic state of operation of a data processing unit during operation of the data processing system, comprising the steps of:

(a) in the system manager unit and by operation of a timer means, periodically generating a timing signal initiating a test of the basic state of operation of the data processing units,

(b) in the system manager unit and responsive to the timing signal,

(c) selecting a data processing unit to be tested and asserting a request to the selected data processing unit for a bus operation,

(d) in the selected data processing unit, providing on the bus a response to the bus operation request, the response being dependent upon the state of operation of the data processing unit, and

(e) in the system manager unit, testing the response provided on the bus by the selected data processing unit in response to the bus operation request asserted by the system manger unit, and

(f) in the system manager unit, determining when the response provided by the selected data processing unit in response to the bus operation request indicates that the selected data processing unit is at least operation for receiving and responding to bus operation requests, and

(g) in the system manager unit,

returning to step (c) and selecting a next data processing unit to be tested when the selected data processing unit is not the last data processing unit to be tested, and

returning to step (a) when the selected data processing unit is the last data processing unit to be tested.

2. The method for testing the basic state of operation of a data processing unit of claim 1, wherein:

the system manager unit is responsive to a data processing unit response indicating acceptance of the request to determine that the data processing unit is at least operational for receiving and responding to bus operation requests.

3. The method for testing the basic state of operation of a data processing unit of claim 1, wherein:

the system manager unit is responsive to a data processing unit response indicating that the request has not been accepted to determine that the data processing unit is not operational for receiving and responding to bus operation requests.

4. The method for testing the basic state of operation of a data processing unit of claim 1, wherein:

the bus operation requested by the system manger unit is a request for a short bus operation.

5. The method for testing the basic state of operation of a data processing unit of claim 1, wherein:

the bus operation requested by the system manager unit is for a write operation into a register of the data processing unit.

6. The method for testing the basic state of operation of a data processing unit of claim 5, wherein:

the bus operation requested by the system manager is for a write operation into a phantom register of the data processing unit, wherein

a phantom register is a non-existent register having an address among the addresses recognized by the data processing unit to be tested.

7. The method for testing the basic state of operation of a data processing unit of claim 1, wherein:

the data processing unit is comprised of a central processor means for performing data processing operations and a bus interface means responsive to the state of operation of the central processor means for performing bus operations for the central processor means, and

the bus operation requested by the system manager unit is for a short bus operation to a register of the bus interface means.

8. The method for testing the basic state of operation of a data processing unit of claim 7, wherein:

the short bus operation requested by the system manager unit is for a write operation into the register of the bus interface means.

9. The method for testing the basic state of operation of a data processing unit of claim 8, wherein:

the bus control element to be written into is a phantom register of the bus interface means, wherein

a phantom register is a non-existent register having an address among the addresses recognized by the bus interface means of the data processing unit to be tested.

10. In a data processing system having at least one data processing unit for performing data processing operations, a system manager unit for performing administrative functions of the system the administrative functions including system fault testing and detection, and a system bus connected between the data processing units and the system manger unit for performing bus operations, the system manager unit and data processing unit including bus control means for asserting a request for a bus operation, the system manger unit having priority of access to the system bus and each data processing unit bus control means being responsive to requests for bus operations asserted on the system bus by the system manager unit and by other data processing units and responsive to the state of operation of the data processing unit for responding to the requests for bus operations, a means for periodically testing the basic state of operation of a data processing unit during operation of the data processing system, comprising:

in the system manager unit, time means for periodically generating a timing signal for initiating a test of the basic state of operation of the data processing units,

in the system manager unit and responsive to the timing signal,

means for selecting a data processing unit to be tested and asserting a request to the selected data processing unit for a bus operation by the selected data processing unit,

in the selected data processing unit, means for providing on the system bus a response to the bus operation request, the response being dependent upon the state of operation of the data processing unit, and

in the system manager unit, test means responsive to the response provided on the system bus by the selected data processing unit in response to the bus operation request asserted by the system manager unit for determining when the response to the request indicates that the selected data processing unit is at least operational for receiving and responding to bus operation requests, and

in the system manger unit, means for selecting a next at a processing unit to be tested when the selected data processing unit is not the last data processing unit and terminating the test of the basic operation of the data processing unit when the selected data processing unit is the last data processing unit to be tested.

11. The means for testing the basic state of operation of a data processing unit of claim 10, wherein:

the system manager unit test mean is responsive to a data processing unit response indicating acceptance of the request to determine that the selected data processing unit is at least operational for receiving and responding to bus operation requests.

12. The means for testing the basic state of operation of a data processing unit of claim 10, wherein:

the system manager unit test means is responsive to a data processing unit response indicating that the request has not been accepted to determine that the data processing unit is not operational for receiving and responding to bus operation requests.

13. The means for testing the basic state of operation of a data processing unit of claim 10, wherein:

the bus operation requested by the system manager unit is for a short bus operation.

14. The means for testing the basic state of operation of a data processing unit of claim 10, wherein:

the bus operation requested by the system manger unit is for a write operation into a register of the data processing unit.

15. The means for testing the basic state of operation of a data processing unit of claim 14, wherein:

the bus operation requested by the system manager unit is for a write operation into a phantom register of the data processing unit, wherein

a phantom register is a non-existent register having an address among the addresses recognized by the bus interface means of the data processing unit to be tested.

16. The means for testing the basic state of operation of a data processing unit of claim 10, wherein:

the data processing unit is comprised of a data processing means for performing data processing operations and a bus interface means responsive to the state of operation of the data processing means for performing bus operations for the data processing means, and

the bus operation requested by the system manager unit is for a short bus operation to a register of the bus interface means.

17. The means for testing the basic state of operation of a data processing unit of claim 16, wherein:

the short bus operation requested by the system manager unit is for a write operation into a register of the bus interface means.

18. The means for testing the basic state of operation of a data processing unit of claim 16, wherein:

the bus control register to be written into is a phantom register of the bus control element, wherein

a phantom register is a non-existent register having an address among the addresses recognized by the bus interface means of the data processing unit to be tested.