Fast software fault detection and notification to a backup unit

• US 7,770,055 B2
• Filed: 12/16/2008
• Issued: 08/03/2010
• Est. Priority Date: 11/26/2003
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Krishnamoorthi, Venkatram, Jebara, Alain, Khurana, Neeraj, Joffe, Neil
• Primary Examiner(s): Beausoliel; Robert
• Assistant Examiner(s): Manoskey; Joseph D
• Application Number:
  US12/336,323
• Publication Number:
  US 20090100288A1
• Time in Patent Office: 595 Days
• Field of Search: 714/4, 714/11, 714/13, 714/30, 714/43, 714/48
• US Class Current: 714/4.11
• CPC Class Codes: G06F 11/2005 using redundant communication controllers
• CPC Class Codes: H04L 12/40045 Details regarding the feeding of energy to the node from the bus
• CPC Class Codes: H04L 41/06 Management of faults, events, alarms or notifications
• CPC Class Codes: H04L 43/0817 by checking functioning
• CPC Class Codes: H04L 69/40 for recovering from a failure of a protocol instance or entity, e.g. service redundancy protocols, protocol state redundancy or protocol service redirection management of faults, events, alarms or notifications in data switching networks H04L41/06

Abstract

A method and system for quickly informing a backup unit that a primary unit has failed. Normally an exception handler is activated when a software failure occurs and network controller chips or the ASIC interface to a signal bus can operate even though there is a software failure. A software failure notification packet is programmed and stored in a location that is not affected by a software system failure. When a software failure occurs, control is shifted to the exception handler. The exception handler sends a pre-established and pre-addressed packet to the network controller card which transmits this packet to the backup unit. Upon receipt of the packet, the backup unit goes into operation. In some alternate embodiments that include multiple line cards in a single unit, the exception handler sends a signal to a backup unit via a signal bus or a data bus.

Claims

1. A computer-implemented method, comprising:

activating a notification program in response to an activation of an exception handler, wherein the activation of the exception handler is in response to a first unit suffering a software fault, the first unit comprising the exception handler and an operating system; and

using the notification program, sending a control packet to a backup unit without using the operating system.

2. The computer-implemented method of claim 1, wherein the exception handler comprises the notification program.

3. The computer-implemented method of claim 1, further comprising activating the backup unit in response to the backup unit receiving the control packet.

4. The computer-implemented method of claim 1, wherein the software fault occurs in the operating system.

5. The computer-implemented method of claim 1, wherein sending the control packet to the backup unit comprises sending the control packet to a network controller card.

6. The computer-implemented method of claim 5, wherein sending the control packet to the backup unit further comprises placing the control packet in a DMA ring of the network controller card.

7. The computer-implemented method of claim 5, wherein sending the control packet to the backup unit further comprises, using the network controller card, transmitting the control packet to the backup unit.

8. The computer-implemented method of claim 5, wherein the first unit further comprises the network controller card.

9. The computer-implemented method of claim 1, wherein sending the control packet to the backup unit is performed immediately upon the first unit suffering the software fault.

10. One or more computer-readable media storing computer-executable instructions that, when executed by a processor, are operable to perform the computer-implemented method of claim 1.

11. A computer-implemented method, comprising:

responsive to an activation of an exception handler of a first line card, wherein the activation of the exception handler is responsive to the first line card becoming inoperable, activating programming code; and

using the programming code, notifying a backup line card that the first line card has become inoperable.

12. The computer-implemented method of claim 11, wherein notifying the backup line card comprises sending a signal to an ASIC connected to a control signal bus.

13. The computer-implemented method of claim 12, wherein notifying the backup line card further comprises sending the signal from the ASIC to the backup line card via the control signal bus.

14. The computer-implemented method of claim 13, further comprising instructing the backup line card to begin operating responsive to receiving the signal from the ASIC.

15. One or more computer-readable media storing computer-executable instructions that, when executed by a processor, are operable to perform the computer-implemented method of claim 11.

16. A computer-implemented method, comprising:

responsive to a first line card failing, wherein the first line card comprises an exception handler, activating an exception handler;

responsive to activating the exception handler, wherein the exception handler comprises an exception handler extension, activating the exception handler extension; and

sending a control packet from the exception handler extension to a second line card.

17. The computer-implemented method of claim 16, wherein sending the control packet to the second line card comprises sending the control packet on a data bus.

18. The computer-implemented method of claim 16, further comprising activating the second line card responsive to receiving the control packet from the exception handler extension.

19. The computer-implemented method of claim 16, wherein sending the control packet comprises injecting the control packet into a data plane stream, the control packet comprising a pre-created crash notification packet.

20. The computer-implemented method of claim 19, wherein sending the control packet further comprises diverting the pre-created crash notification packet from the data plane stream to the second line card without interrupt support or network controller support.