Multi-server fault tolerance using in-band signalling

• US 5,812,751 A
• Filed: 10/03/1997
• Issued: 09/22/1998
• Est. Priority Date: 05/19/1995
• Status: Expired due to Term

• Current Assignee: QNAP Systems Incorporated
• Original Assignee: Compaq Computer Corporation (HP Inc.)
• Inventors: Hemphill, John M., Alexander, Dennis J., Galloway, William C., Autor, Jeffrey S., Ekrot, Alexander C., Singer, James H.
• Primary Examiner(s): DECADY, ALBERT
• Application Number:
  US08/943,655
• Time in Patent Office: 354 Days
• Field of Search: 395/180, 395/181, 395/182.11, 395/182.13, 395/182.14, 395/182.08, 395/182.09, 395/182.1, 395/182.15, 395/182.01, 395/182.02, 364/228.3, 364/229, 364/229.4
• US Class Current: 714/4.5
• CPC Class Codes: G06F 11/0757 by exceeding a time limit, i.e. time-out, e.g. watchdogs
• CPC Class Codes: G06F 11/20 using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
• CPC Class Codes: G06F 11/2002 where interconnections or communication control functionality are redundant flexible arrangements for bus networks involving redundancy H04L12/40176
• CPC Class Codes: G06F 11/2028 eliminating a faulty processor or activating a spare
• CPC Class Codes: G06F 11/2033 switching over of hardware resources
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• CPC Class Codes: G06F 11/2046 where the redundant components share persistent storage G06F11/2043 takes precedence
• 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 13/4022 using switching circuits, e.g. switching matrix, connection or expansion network G06F13/4009 takes precedence

Abstract

A primary server/standby server network configuration according to the invention includes a primary server executing network operating system software and a standby server monitoring for the proper operation of the primary server, where both the primary server and the standby server are connected to a storage system. If the primary server fails, the standby server instructs the storage system to switch its hardware connections to the standby server, allowing the standby server to boot the operating system. This instruction is done via in-band signaling. Further, multiple primary servers can be backed up by a single standby server.

Claims

1. A method of operating a computing device in a standby mode, the method comprising the steps of:

monitoring an input node of the computing device for a determination that the computing device must be transferred from the standby mode to an active mode;

upon determining that the computing device must be transferred from the standby mode to an active mode, sending an indication to a storage system to cause the storage system to switch from communicating with a second computing device as a primary device to communicating with the computing device as the primary device, the indication being sent along a first signal line;

receiving a boot program from the storage system along the first signal line; and

booting the computing device in the active mode.

2. The method of claim 1 wherein the computing device is a server.

3. The method of claim 1 wherein the monitoring step comprises monitoring the input node for periodic signals and upon failing to receive the period signals determining that the computing device must be transferred from the standby mode to an active mode.

4. The method of claim 1 wherein the computing device is coupled to a port of the storage unit, wherein the port includes signal lines for carrying signals according to a bus standard and wherein the first signal line comprises at least one signal line of the port.

5. The method of claim 4 wherein the port comprises a SCSI port.

6. The method of claim 1 wherein the step of sending an indication to a storage unit comprises sending a series of reset pulses.

7. The method of claim 6 wherein the series of reset pulses comprises eight sequential resets.

8. The method of claim 6 wherein the series of reset pulses are each of a predetermined length of time and are uninterrupted by any intervening busy pulses.

9. The method of claim 1 wherein the step of sending an indication to a storage unit comprises changing a voltage level on a terminator power line.

10. A computer-implemented process to control a server in a primary or standby mode, the process comprising the steps of:

(1) determining whether the server is configured in a primary mode;

(2) if the server is configured in a primary mode, performing the steps of;

(a) determining the presence of a storage medium;

(b) loading an operating system from a storage medium through a first port; and

(c) booting the operating system;

(3) if the server is not configured in a primary mode, performing the steps of;

(a) initializing a timer;

(b) monitoring an input node to determine the receipt of a heartbeat signal;

(c) resetting the timer if the heartbeat signal is received;

(d) initiating a switch command if the heartbeat signal is not received within a predetermined amount of time, the step of initiating a switch command including outputting a signal to the first port to cause the storage medium to switch the coupling of the storage medium from a failed server to the server;

(e) loading the operating system from the storage medium through the first port; and

(f) booting the operating system.

11. The process of claim 10 and further comprising the step of determining whether the server is configured for standby operation before determining whether the server is configured in a primary mode.

12. The process of claim 10 and, if the server is configured in the primary mode, performing the further steps of determining if the server is restarting from a non-graceful shutdown and if so indicating a desire to run a diagnostic program.

13. The process of claim 10 and, if the server is not configured in the primary mode, determining whether there is a cable fault at the input node prior to monitoring the input node.

14. The process of claim 10 and, if the server is not configured in the primary mode, further comprising the step of initiating the switch command upon receipt of a user input indicating that the user wishes to switch the server mode.

15. The process of claim 10 wherein the first port comprises a SCSI port.

16. The process of claim 10 wherein the step of outputting a signal to the first port comprises outputting a series of reset pulses.

17. The process of claim 16 wherein the series of reset pulses comprises eight sequential resets.

18. The process of claim 16 wherein the series of reset pulses are each of a predetermined length of time and are uninterrupted by any intervening busy pulses.

19. The method of claim 10 wherein the step of outputting a signal to the first port comprises changing a voltage level on a terminator power line.

20. A computer system comprising:

a microprocessor;

a memory array;

a bus coupling the microprocessor to the memory array;

a non-volatile memory device for storing a computer program which can be run by the computer system, the computer program encompassing a process to control the computer system in a primary or standby mode, the process comprising the steps of;

(1) determining whether the computer system is configured in a primary mode;

(2) if the computer system is configured in a primary mode, performing the steps of;

(a) determining the presence of a storage medium;

(b) loading an operating system from a storage medium through a first port; and

(c) booting the operating system;

(3) if the computer system is not configured in a primary mode, performing the steps of;

(a) initializing a timer;

(b) monitoring an input node to determine the receipt of a heartbeat signal;

(c) resetting the timer if the heartbeat signal is received;

(d) initiating a switch command if the heartbeat signal is not received within a predetermined amount of time, the step of initiating a switch command including outputting a signal to the first port to cause the storage medium to switch the coupling of the storage medium from a failed computer system to the computer system;

(e) loading the operating system from the storage medium through the first port; and

(f) booting the operating system.

21. The system of claim 20 wherein the non-volatile memory device comprises a read only memory.

22. The system of claim 21 wherein the non-volatile memory device comprises a flash EEPROM.

23. The system of claim 20 wherein the non-volatile memory device comprises a local boot drive or disk.

24. The system of claim 20 wherein the computer system comprises a server.

25. The system of claim 20 wherein the first port comprises a SCSI port.