Replacement, upgrade and/or addition of hot-pluggable components in a computer system

• US 6,487,623 B1
• Filed: 04/30/1999
• Issued: 11/26/2002
• Est. Priority Date: 04/30/1999
• Status: Expired due to Fees

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Compaq Computer Corporation (HP Inc.)
• Inventors: Michels, Peter, Clohset, Steve, Nguyen, Vincent, Emerson, Theodore F.
• Primary Examiner(s): Auve, Glenn A.
• Application Number:
  US09/303,369
• Time in Patent Office: 1,306 Days
• Field of Search: 710/103, 710/102, 710/104, 710/301, 710/302, 714/7, 714/42, 714/710
• US Class Current: 710/302
• CPC Class Codes: G06F 13/4081 Live connection to bus, e.g. hot-plugging current or voltage limitation during live insertion H02H9/004

Abstract

A computer system adapted for hot-pluggable components such as memory modules that may be replaced, upgraded and/or added without disturbing normal operation of the computer system. A failing memory module may be replaced by copying its contents to a new memory module in a background operation while the computer system runs its operating system and applications programs. When all contents are copied to the new memory module, the failing memory module may be removed without having to shut down the computer system. Computer system memory may be upgraded or added to by inserting the new memory module(s) into vacant disconnected memory connectors, whereupon the computer system automatically recognizes the new memory module(s), synchronously connects the new memory module(s) to the computer system memory bus, initializes the new memory module(s), and then notifies the operating system that the new memory module(s) is available, all without disturbing normal operation of the computer system.

Claims

1. A computer system having hot-pluggable components, said system comprising:

a central processing unit;

a component controller connected to said central processing unit;

a component bus connected to said component controller;

a plurality of component connectors adapted to receive component modules;

a plurality of component bus switches connected between said component bus and said plurality of component connectors;

a plurality of component power switches connected between said plurality of component connectors and a power source;

a first component module installed in a one of said plurality of component connectors; and

a logic circuit connected to said component bus, said plurality of component connectors, said plurality of component bus switches and said plurality of component power switches, wherein

when said component controller determines that said first component module is failing but still operational, said component controller asserts a system management interrupt to said central processing unit;

when said central processing unit receives the system management interrupt, said central processing unit runs a system management program which determines whether a second component module is installed in another one of said plurality of component connectors;

if said second component module is not installed then the system management program continues determining until said second component module is installed;

if said second component module is installed then the system management program causes said central processing unit to transfer information stored in said first component module to said second component module until all information is transferred, the transfer of information is done as a background operation which does not materially affect other programs running in said central processing unit;

said logic circuit causing some of said plurality of component bus switches to disconnect said first component module from said component bus after all of the information is transferred; and

said logic circuit causing some of said plurality of component power switches to disconnect said first component module from said power source after the some of said plurality of component bus switches has disconnected said first component module from said component bus.

2. The computer system of claim 1, further including a plurality of central processing units.

3. The computer system of claim 1, wherein said plurality of component bus switches comprise a plurality of field effect transistor switches.

4. The computer system of claim 1, wherein said plurality of component power switches comprise a plurality of field effect transistor power switches.

5. The computer system of claim 1, wherein said first and second component modules are selected from the group consisting of a random access memory, a network interface, a modem, a disk interface, a peripheral component interconnect (PCI) interface, an accelerated graphics port (AGP) interface, a co-processor, a universal serial bus (USB) interface, a fibre channel interface, an industry standard architecture (ISA) controller, an extension to industry standard architecture (EISA) controller, a super input-output (SIO) controller, and a small computer system interface (SCSI).

6. The computer system of claim 1, wherein said first and second component modules are first and second random access memory (RAM) modules, respectively, said component controller is a memory controller having error checking and correcting logic, and said first component module is failing with correctable bit errors.

7. The computer system of claim 6, further comprising:

said second RAM module having a larger storage capacity than said first RAM module;

the system management program initializes a portion of said second RAM module which is not written to during transfer of the information from said first RAM module; and

the system management program generates an interrupt to an operating system program to inform the operating system program of the additional memory capacity available from said second RAM module.

8. The computer system of claim 1, further comprising detection logic for determining when a component module is installed in and removed from a one of said plurality of component connectors.

9. The computer system of claim 8, wherein said detection logic determines when said component module is installed in and removed from the one of said plurality of component connectors by sensing an electrical connection to said component module and sensing a loss of the electrical connection to said component module, respectively.

10. The computer system of claim 8, wherein said detection logic waits a specified time before connecting said component module to said power source and then to said component bus after determining when said component module is installed in the one of said plurality of component connectors.

11. The computer system of claim 10, wherein said detection logic resets and does not connect said component module if it senses during the specified time that said component module is not installed.

12. The computer system of claim 1, further comprising a plurality of light emitting diodes associated with said plurality of component connectors, each one of said plurality of light emitting diodes indicating status of an associated one of said plurality of component connectors.

13. The computer system of claim 12, wherein a steady red indication from said one of said plurality of light emitting diodes represents a failed one of said component modules located in said associated one of said plurality of component connectors.

14. The computer system of claim 12, wherein a steady green indication from said one of said plurality of light emitting diodes represents a fully functional one of said component modules located in said associated one of said plurality of component connectors.

15. The computer system of claim 12, wherein no indication from said one of said plurality of light emitting diodes represents a disconnected one of said plurality of component connectors.

16. The computer system of claim 12, wherein a steady amber indication from said one of said plurality of light emitting diodes represents a failing but operational one of said component modules located in said associated one of said plurality of component connectors.

17. The computer system of claim 12, wherein a blinking amber indication from said one of said plurality of light emitting diodes represents a one of said component modules located in said associated one of said plurality of component connectors being initialized with information from another one of said component modules.

18. The computer system of claims 12, wherein a first one of said plurality of light emitting diodes associated with said first component module and a second one of said plurality of light emitting diodes associated with said second component module alternately blink with amber indications and a pause to represent transfer of information and the direction thereof.

19. The computer system of claim 1, further comprising the system management software sending an alert to an operator when said first component module is failing and said second component module is not installed.

20. The computer system of claim 1, wherein:

if a second component module is not installed and then is subsequently installed in said another one of said plurality of component connectors, then

said logic circuit causes some other of said plurality of component power switches to connect said second component module to said power source; and

said logic circuit causes some other of said plurality of component bus switches to connect said second component module to said component bus when said component bus is inactive; and

said first and second component modules writing the information to the same addresses, but only the first component module responding to a read request during transfer of the information.

21. A computer system having hot-pluggable components, said system comprising:

a central processing unit;

a component controller connected to said central processing unit;

a component bus connected to said component controller;

a plurality of component connectors adapted to receive component modules;

a plurality of component bus switches connected between said component bus and said plurality of component connectors;

a plurality of component power switches connected between said plurality of component connectors and a power source;

a new component module installed in a one of said plurality of component connectors; and

a logic circuit connected to said component bus, said plurality of component connectors, said plurality of component bus switches and said plurality of component power switches, wherein

when said logic circuit determines that said new component module is installed in the one of said plurality of component connectors, said logic circuit causes some of said plurality of power switches to connect the one of said plurality of component connectors to said power source, and then said logic circuit causes some of said component bus switches to connect the one of said plurality of component connectors to said component bus when said component bus is inactive;

said logic circuit asserting a system management interrupt to said central processing unit after the one of said plurality of component connectors is connected to said power source and said component bus; and

when said central processing unit receives the system management interrupt, said central processing unit runs a system management program for initializing said new component module and then the system management program notifies an operating system program of the availability of said new component module.

22. The computer system of claim 21, further including a plurality of new component modules.

23. The computer system of claim 21, wherein said new component module is selected from the group consisting of a random access memory, a network interface, a modem, a disk interface, a peripheral component interconnect (PCI) interface, an accelerated graphics port (AGP) interface, a co-processor, a universal serial bus (USB) interface, a fibre channel interface, an industry standard architecture (ISA) controller, an extension to industry standard architecture (EISA) controller, a super input-output (SIO) controller, and a small computer system interface (SCSI).

24. The computer system of claim 21, wherein said new component module is a new random access memory (RAM) module, said component controller is a memory controller having error checking and correcting logic, and said component bus is a computer system memory bus.

25. The computer system of claim 24, further comprising detection logic for determining when said new RAM module is installed in and removed from the one of said plurality of component connectors.

26. The computer system of claim 25, wherein said detection logic waits a specified time before connecting said new RAM module to said power source and then to said computer system memory bus after determining when said new RAM module is installed in the one of said plurality of component connectors.

27. The computer system of claim 25, wherein said detection logic determines when said new RAM module is installed in and removed from the one of said plurality of component connectors by sensing an electrical connection to said new RAM module and sensing a loss of the electrical connection to said new RAM module, respectively.

28. The computer system of claim 24, wherein the system management program initializes said new RAM module by writing zero values to all address locations thereof.

29. The computer system of claim 24, wherein the system management program determines the size of said new RAM module.

30. The computer system of claim 24, wherein the system management program determines what address space is assigned to said new RAM module.

31. The computer system of claim 24, wherein the system management program generates an interrupt to an operating system program to inform the operating system program that said new RAM module is available for use.

32. The computer system of claim 31, wherein the operating system program responds to the interrupt, retrieves status information of said new RAM module and then utilizes said new RAM module when running programs in the computer system.

33. The computer system of claim 31, wherein the operating system program uses an advanced Configuration Power Interface (ACPI) for retrieving the status information.

34. A method, in a computer system comprising a central processing unit, a component controller connected to the central processing unit, a component bus connected to the component controller, a plurality of component connectors adapted to receive component modules, a plurality of component bus switches connected between the component bus and the plurality of component connectors;

a plurality of component power switches connected between the plurality of component connectors and a power source; and

a logic circuit connected to the component bus, the plurality of component connectors, the plurality of component bus switches and the plurality of component power switches;

said method comprising the steps of;

providing a first component module installed in a one of the plurality of component connectors;

detecting a failing but still operational first component module;

alerting an operator when the first component module is determined to be failing;

determining whether a second component module is installed in another one of the plurality of component connectors and is available to replace the failing first component module;

if the second component module is installed and available in the another one of the plurality of component connectors, then

connecting the power source to the another one of the plurality of component connectors with some of the plurality of component power switches; and

connecting the component bus to the another one of the plurality of component connectors with some of the plurality of component bus switches when the component bus is not active;

transferring information from the failing first component module to the second component module until all information has been transferred; and

disconnecting the first component module from the component bus after the information has been transferred.

35. The method of claim 34, further comprising the step of waiting a predetermined time after detecting the second module being installed in the another one of the plurality of component connectors before connecting the another one of the plurality of component connectors to the power source and then the component bus.

36. The method of claim 34, further comprising the step of indicating status of the first component module with a light emitting diode located proximate to the one of the plurality of component connectors.

37. The method of claim 34, further comprising the step of indicating status of the second component module with a light emitting diode located proximate to the another one of the plurality of component connectors.

38. The method of claim 34, wherein the step of transferring information from the failing first component module to the second component module is done by the component controller.

39. A method, in a computer system comprising a central processing unit, a component controller connected to the central processing unit, a component bus connected to the component controller, a plurality of component connectors adapted to receive component modules, a plurality of component bus switches connected between the component bus and the plurality of component connectors;

a plurality of component power switches connected between the plurality of component connectors and a power source; and

a logic circuit connected to the component bus, the plurality of component connectors, the plurality of component bus switches and the plurality of component power switches;

said method comprising the steps of;

providing a first component module installed in a one of the plurality of component connectors;

detecting a failing but still operational first component module;

determining whether a second component module is installed in another one of the plurality of component connectors and is available to replace the failing first component module;

alerting an operator if the second component module is not available;

if the second component module is installed and available in the another one of the plurality of component connectors, then

connecting the power source to the another one of the plurality of component connectors with some of the plurality of component power switches; and

connecting the component bus to the another one of the plurality of component connectors with some of the plurality of component bus switches when the component bus is not active;

transferring information from the failing first component module to the second component module until all information has been transferred; and

disconnecting the first component module from the component bus after the information has been transferred.

40. A method, in a computer system comprising a central processing unit, a component controller connected to the central processing unit, a component bus connected to the component controller, a plurality of component connectors adapted to receive component modules, a plurality of component bus switches connected between the component bus and the plurality of component connectors;

a plurality of component power switches connected between the plurality of component connectors and a power source; and

a logic circuit connected to the component bus, the plurality of component connectors, the plurality of component bus switches and the plurality of component power switches;

said method comprising the steps of;

providing a first component module installed in a one of the plurality of component connectors;

detecting a failing but still operational first component module;

determining whether a second component module is installed in another one of the plurality of component connectors and is available to replace the failing first component module;

alerting the operator when the second component module is not installed;

if the second component module is installed and available in the another one of the plurality of component connectors, then

connecting the power source to the another one of the plurality of component connectors with some of the plurality of component power switches; and

connecting the component bus to the another one of the plurality of component connectors with some of the plurality of component bus switches when the component bus is not active;

transferring information from the failing first component module to the second component module until all information has been transferred; and

disconnecting the first component module from the component bus after the information has been transferred.

41. A method, in a computer system comprising a central processing unit, a component controller connected to the central processing unit, a component bus connected to the component controller, a plurality of component connectors adapted to receive component modules, a plurality of component bus switches connected between the component bus and the plurality of component connectors;

a plurality of component power switches connected between the plurality of component connectors and a power source; and

a logic circuit connected to the component bus, the plurality of component connectors, the plurality of component bus switches and the plurality of component power switches;

said method comprising the steps of;

providing a first component module installed in a one of the plurality of component connectors;

detecting a failing but still operational first component module;

determining whether a second component module is installed in another one of the plurality of component connectors and is available to replace the failing first component module;

if the second component module is installed and available in the another one of the plurality of component connectors, then

connecting the power source to the another one of the plurality of component connectors with some of the plurality of component power switches; and

connecting the component bus to the another one of the plurality of component connectors with some of the plurality of component bus switches when the component bus is not active;

transferring information from the failing first component module to the second component module until all information has been transferred, said central processing unit performs this step by performing locked reads of portions of the contents of the failing first component module and then writes these portions to the second component module; and

disconnecting the first component module from the component bus after the information has been transferred.

42. The method of claim 41, wherein the step of transferring information from the failing first component module to the second component module by the central processing unit is done in a background operation during normal operation of the computer system.

43. A method, in a computer system comprising a central processing unit, a component controller connected to the central processing unit, a component bus connected to the component controller, a plurality of component connectors adapted to receive component modules, a plurality of component bus switches connected between the component bus and the plurality of component connectors;

a plurality of component power switches connected between the plurality of component connectors and a power source; and

a logic circuit connected to the component bus, the plurality of component connectors, the plurality of component bus switches and the plurality of component power switches;

said method comprising the steps of;

installing a new component module into a one of the plurality of component connectors;

determining when the new component module is installed;

waiting a predetermined time before connecting the new component module to the power source and then to the component bus;

initializing the new component module connected to the component bus for operation in the computer system, said central processing unit performs the initialization by- writing a predetermined bit pattern to all portions of the new component module;

notifying a computer system operating software of the new component module; and

utilizing the new component module in the computer system.

44. The method of claim 43, wherein the step of initializing the new component module by the central processing unit is done in a background operation during normal operation of the computer system.

45. An apparatus, comprising:

a component controller adapted for connection to a central processing unit;

a component bus connected to said component controller;

a plurality of component connectors adapted to receive component modules;

a plurality of component bus switches connected between said component bus and said plurality of component connectors;

a plurality of component power switches connected between said plurality of component connectors and a power source;

a first component module installed in a one of said plurality of component connectors; and

a logic circuit connected to said component bus, said plurality of component connectors, said plurality of component bus switches and said plurality of component power switches, wherein

when said component controller determines that said first component module is failing but still operational, said component controller determines whether a second component module is installed in another one of said plurality of component connectors;

if said second component module is not installed then said component controller continues determining until said second component module is installed;

if said second component module is installed then said component controller transfers information stored in said first component module to said second component module until all information is transferred;

said logic circuit causing some of said plurality of component bus switches to disconnect said first component module from said component bus after all of the information is transferred; and

said logic circuit causing some of said plurality of component power switches to disconnect said first component module from said power source after the some of said plurality of component bus switches has disconnected said first component module from said component bus.

46. An apparatus, comprising:

a component controller adapted for connection to a central processing unit;

a component bus connected to said component controller;

a plurality of component connectors adapted to receive component modules;

a plurality of component bus switches connected between said component bus and said plurality of component connectors;

a plurality of component power switches connected between said plurality of component connectors and a power source;

a new component module installed in a one of said plurality of component connectors; and

a logic circuit connected to said component bus, said plurality of component connectors, said plurality of component bus switches and said plurality of component power switches, wherein

when said logic circuit determines that said new component module is installed in the one of said plurality of component connectors, said logic circuit causes some of said plurality of power switches to connect the one of said plurality of component connectors to said power source, and then said logic circuit causes some of said component bus switches to connect the one of said plurality of component connectors to said component bus when said component bus is inactive;

said component controller initializing said new component module after the one of said plurality of component connectors is connected to said power source and said component bus; and

said component controller notifies an operating system program of the availability of said new component module.