Method and apparatus for monitoring variations in a parameter over time

• US 8,374,823 B1
• Filed: 02/19/2004
• Issued: 02/12/2013
• Est. Priority Date: 02/19/2004
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Oracle America, Inc. (Oracle Corporation)
• Inventors: Williams, Emrys J.
• Primary Examiner(s): Moffat, Jonathan C Teixeira
• Assistant Examiner(s): VO, HIEN XUAN
• Application Number:
  US10/782,490
• Time in Patent Office: 3,281 Days
• Field of Search: 702/187, 702/185, 702/34, 702/81, 702/194, 702/183, 714/25, 714/726, 714/728, 324/115
• US Class Current: 702/187
• CPC Class Codes: G06F 11/3058 Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations thermal management in cooling arrangements of a computing system G06F1/206

Abstract

A method and apparatus are provided for monitoring a parameter such as temperature in a system such as a computer server. The method involves defining a monitoring range for the parameter. Typically, the parameter initially lies within the monitoring range. The parameter is then tracked by determining whenever the parameter exceeds an upper or lower limit of the monitoring range. If such a limit is reached, the monitoring range is adjusted to try to accommodate the parameter within the adjusted monitoring range. A time history of the monitoring range may be recorded, including details of all the adjustments of the monitoring range. This allows the behavior of the parameter to be subsequently investigated for diagnostic purposes.

Claims

1. A computer-implemented method of monitoring a parameter in a system, comprising:

defining a monitoring range for the parameter;

tracking the parameter by determining whenever the parameter exceeds a limit of the monitoring range;

responding to a determination that the parameter exceeds the limit of the monitoring range by adjusting the monitoring range to try to accommodate the parameter; and

recording a time history of the monitoring range.

2. The method of claim 1, wherein said recording is performed in response to the determination that the parameter exceeds the limit of the monitoring range.

3. The method of claim 1, wherein said monitoring range is defined by an upper threshold and a lower threshold.

4. The method of claim 3, further comprising storing the upper threshold in a first register and the lower threshold in a second register, wherein said determining whenever the parameter exceeds a limit of the monitoring range comprises comparing the parameter against the upper threshold in the first register and the lower threshold in the second register.

5. The method of claim 4, further comprising performing a digital to analogue conversion of the upper threshold and of the lower threshold, wherein said comparing against the upper threshold is performed by a first analogue comparator, and said comparing against the lower threshold is performed by a second analogue comparator.

6. The method of claim 5, further comprising latching the output of the first analogue comparator in a first latch, latching the output of the second analogue comparator in a second latch, and combining the outputs of the first and second latches using OR logic.

7. The method of claim 1, further comprising raising an interrupt in response to determining that the parameter has reached a limit of the monitoring range.

8. The method of claim 7, wherein in response to the interrupt the adjustment of the monitoring range is performed, and details of the adjustment of the monitoring range are recorded in a time history.

9. The method of claim 8, wherein said tracking is performed by a monitor which transmits said interrupt to a control unit in response to determining that the parameter exceeds a limit of the monitoring range, and wherein the control unit responds to the interrupt by notifying the monitor of the adjusted monitoring range and recording details of the adjustment in local storage.

10. The method of claim 1, wherein said monitoring range has a fixed width.

11. The method of claim 1, wherein said monitoring range has a variable width, and said method further comprises the step of trying to contract the monitoring range.

12. The method of claim 11, further comprising using the variable width of the monitoring range to estimate a noise level for the parameter.

13. The method of claim 1, wherein the adjustment of the monitoring range is performed using an adaptive algorithm.

14. The method of claim 1, further comprising triggering an alarm if said parameter exceeds the limit of said monitoring range corresponding to a predetermined alarm level.

15. The method of claim 1, further comprising defining multiple overlapping monitoring ranges for the parameter, and wherein the parameter is tracked by determining whenever the parameter exceeds a limit of any of said monitoring ranges.

16. The method of claim 1, wherein said parameter corresponds to temperature.

17. The method of claim 1, wherein said parameter corresponds to voltage.

18. Apparatus for tracking a parameter within a defined monitoring range, said apparatus comprising:

a monitor unit operable to determine whenever the parameter exceeds a limit of said defined monitoring range;

a control system linked to the monitor unit and responsive to a determination by the monitor unit that the parameter exceeds the limit of the defined monitoring range to adjust the defined monitoring range to try to accommodate the parameter; and

a storage facility operable to hold a time history of the defined monitoring range.

19. The apparatus of claim 18, wherein the storage facility is further operable to update the time history of the defined monitoring range in response to the determination by the monitor unit that the parameter exceeds the limit of the defined monitoring range.

20. The apparatus of claim 18, wherein said defined monitoring range is specified by an upper threshold and a lower threshold, and said monitor unit comprises a first register operable to store the upper threshold and a second register operable to store the lower threshold.

21. The apparatus of claim 20, further comprising a first analogue comparator and a second analogue comparator, wherein in operation the first analogue comparator determines whether the parameter exceeds said upper threshold, and the second analogue comparator determines whether the parameter exceeds said lower threshold.

22. The apparatus of claim 21, further comprising a first latch for latching an output of the first analogue comparator and a second latch for latching an output of the second analogue comparator.

23. The apparatus of claim 22, further comprising an OR gate having as a first input an output of the first latch and as a second input an output of the second latch.

24. The apparatus of claim 18, wherein an interrupt is generated in response to determining that the parameter exceeds a limit of the monitoring range.

25. The apparatus of claim 24, wherein said monitor unit is operable to transmit said interrupt to the control system in response to determining that the parameter exceeds a limit of the monitoring range, and wherein the control system is operable to respond to the interrupt by notifying the monitor unit of the adjusted monitoring range and by recording details of the adjustment in local storage.

26. The apparatus of claim 18, wherein said monitoring range has a fixed width.

27. The apparatus of claim 18, wherein said monitoring range has a variable width, wherein the apparatus is responsive to at least one condition to try to contract the monitoring range.

28. The apparatus of claim 27, wherein said apparatus further comprises at least one timer, and said at least one condition comprises expiry of the at least one timer.

29. The apparatus of claim 18, wherein the adjustment of the monitoring range is performed using an adaptive algorithm.

30. The apparatus of claim 18, further comprising an alarm which is triggered if said parameter exceeds the limit of said monitoring range corresponding to a predetermined alarm level.

31. The apparatus of claim 18, wherein said parameter corresponds to temperature.

32. The apparatus of claim 18, wherein said parameter corresponds to voltage.

33. The apparatus of claim 18, wherein there are multiple monitor units attached to a single control system, and wherein the time history for each of said multiple monitor units is recorded in a storage facility.

34. The apparatus of claim 18, wherein multiple overlapping monitoring ranges are defined for the parameter, and wherein the apparatus determines whenever the parameter exceeds a limit of any of said monitoring ranges.

35. Apparatus for tracking a parameter, said apparatus comprising:

two or more monitor units operable to determine whenever the parameter exceeds a limit of a defined monitoring range, wherein each of the two or more monitor units has a respective defined monitoring range, and wherein the monitoring ranges of the different monitor units are defined to have a hierarchical configuration; and

a control system linked to the monitor units and responsive to a determination by at least one of said two or more monitor units that the parameter exceeds the limit of the defined monitoring range for that monitor unit to adjust the defined monitoring range to try to accommodate the parameter; and

a storage facility operable to hold a time history of the defined monitoring range.

36. Apparatus for monitoring a parameter in a system comprising:

means for defining a monitoring range for the parameter;

means for tracking the parameter by determining whenever the parameter exceeds a limit of the monitoring range;

means for responding to a determination that the parameter exceeds the limit of the monitoring range by adjusting the monitoring range to try to accommodate the parameter; and

means for recording a time history of the monitoring range.

37. A computer program product comprising program code in a non-transitory storage medium, said program code when executed by a machine causing the machine to:

define a monitoring range for the parameter;

track the parameter by determining whenever the parameter exceeds a limit of the monitoring range;

respond to a determination that the parameter exceeds the limit of the monitoring range by adjusting the monitoring range to try to accommodate the parameter; and

record details of the adjustment of the monitoring range in a time history.

38. The computer program product of claim 37, wherein said program code further causes the machine to raise an interrupt in response to determining that the parameter exceeds a limit of the monitoring range.

39. The computer program product of claim 38, wherein in response to the interrupt the monitoring range is adjusted, and details of the adjustment of the monitoring range are recorded in the time history.

40. The computer program product of claim 37, wherein said monitoring range has a fixed width.

41. The computer program product of claim 37, wherein said monitoring range has a variable width, and said program code further causes the machine to try to contract the monitoring range.

42. The computer program product of claim 37, wherein the adjustment of the monitoring range is performed using an adaptive algorithm.

43. The computer program product of claim 37, wherein the program code further causes the machine to trigger an alarm if said parameter exceeds the limit of said monitoring range corresponding to a predetermined alarm level.

44. The computer program product of claim 37, wherein said parameter corresponds to temperature.

45. The computer program product of claim 37, wherein said parameter corresponds to voltage.